A METHOD AND SYSTEM FOR EVALUATING QUALITY OF SEMEN SAMPLE

Disclosed herein is method and system for evaluating semen quality. Plurality of images of stained semen sample are captured and analyzed for eliminating unusable images. Further, visible objects in the images are extracted and classified into sperm objects and non-sperm objects. The sperm objects are further classified into normal/abnormal sperm objects based on morphological characteristics of sperm objects, and a differential count of normal/abnormal sperm objects is determined. Subsequently, an aggregate count of the non-sperm objects is determined. Finally, a sperm quality index, indicative of quality of the semen sample, is computed based on morphological characteristics of sperm objects, differential count of normal/abnormal sperm objects, aggregate count of non-sperm objects and total motility estimate of semen sample. The method of present disclosure helps in accurate estimation of the semen quality, since the aggregate count of the non-sperm objects is considered as a crucial parameter for computing the semen quality index.

Skip to: Description  ·  Claims  · Patent History  ·  Patent History
Description
TECHNICAL FIELD

The present subject matter is related, in general, to physiological analysis of biological samples, and more particularly, but not exclusively, to a method and system for evaluating quality of semen sample.

BACKGROUND

Semen quality is a measure of the ability of a sample of semen to accomplish fertilization. Generally, identifying various objects in the semen sample, classification of the objects into sperm objects and non-sperm objects, measurement of motility of the sperm objects, identification of morphological characteristics of the sperm objects, and determining concentration of the sperm objects are all necessary to estimate the quality of the semen sample.

However, one of the major challenges that results in inaccuracies in the estimation of the semen quality is inefficient techniques used for handling non-sperm objects present in the semen sample. For example, the non-sperm objects may include various pathological and non-pathological artefacts such as White Blood Cells (WBCs), Red Blood Cells (RBCs), spermatogonium cells, pathological casts, and one or more microbes. Analyzing each of these non-sperm objects may be critical to understand their significance on the quality of the semen sample, and overall health of a person whose semen sample is being analyzed,

The existing methodologies for estimating the semen quality involve estimation of the semen quality, based on various environmental factors and lifestyle of a person, which are known to significantly affect the semen quality of the person. However, the existing methodologies does not assess the semen quality as a whole. Therefore, a method for accurately measuring the semen quality is necessary.

SUMMARY

Disclosed herein is a method for evaluating quality of semen sample. The method comprises capturing, by a semen quality analysis system, a plurality of microscopic images of a stained semen sample being examined. Further, the method comprises eliminating one or more unusable images from the plurality of microscopic images based on one or more predetermined conditions. Upon eliminating the one or more unusable images, the method comprises identifying one or more sperm objects and one or more non-sperm objects in each of the plurality of microscopic images. Thereafter, one or more morphological characteristics of each of the one or more sperm objects, identified in each of the plurality of microscopic images, is determined for classifying each of the one or more sperm objects into one or more normal sperm objects and one or more abnormal sperm objects based on predetermined classification techniques. Subsequently, the method comprises determining a differential count of the one or more normal sperm objects and the one or more abnormal sperm objects, Further, the method comprises determining an aggregate count of the one or more non-sperm objects identified in each of the plurality of microscopic images. Finally, the method comprises computing a semen quality index based on the one or more morphological characteristics of each of the one or more sperm objects, the differential count of the one or more normal sperm objects and the one or more abnormal sperm objects, a total motility estimate of the semen sample, and the aggregate count of the one or more non-sperm objects, for evaluating the quality of the semen sample.

Further, the present disclosure relates to a semen quality analysis system for evaluating quality of semen sample. The semen quality analysis system comprises a processor and a memory. The memory is communicatively coupled to the processor and stores processor-executable instructions, which on execution, cause the processor to capture a plurality of microscopic images of a stained semen sample being examined. Further, the processor eliminates one or more unusable images from the plurality of microscopic images based on one or more predetermined conditions. Upon eliminating the one or more unusable images, the processor identifies one or more sperm objects and one or more non-sperm objects in each of the plurality of microscopic images. Further, the processor determines one or more morphological characteristics of each of the one or more sperm objects, identified in each of the plurality of microscopic images, to classify each of the one or more sperm objects into one or more normal sperm objects and one or more abnormal sperm objects based on predetermined classification techniques. Subsequently, the processor determines a differential count of the one or more normal sperm objects and the one or more abnormal sperm objects. Further, the processor determines an aggregate count of the one or more non-sperm objects identified in each of the plurality of microscopic images. Finally, the processor computes a semen quality index based on the one or more morphological characteristics of each of the one or more sperm objects, the differential count of the one or more normal sperm objects and the one or more abnormal sperm objects, a total motility estimate of the semen sample, and the aggregate count of the one or more non-sperm objects, for evaluating the quality of the semen sample.

The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and regarding the accompanying figures, in which:

FIG. 1 illustrates an exemplary environment of evaluating quality of semen sample in accordance with some embodiments of the present disclosure;

FIG. 2 shows a detailed block diagram illustrating a semen quality analysis system for evaluating quality of semen sample in accordance with some embodiments of the present disclosure;

FIGS. 3A-3H show exemplary views of plurality of microscopic images during processing of the plurality of microscopic images in accordance with some embodiments of the present disclosure;

FIG. 4 shows a flowchart illustrating a method for evaluating quality of semen sample in accordance with some embodiments of the present disclosure; and

FIG. 5 illustrates a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.

It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether such computer or processor is explicitly shown.

DETAILED DESCRIPTION

In the present document, the word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any embodiment or implementation of the present subject matter described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the specific forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the spirit and the scope of the disclosure.

The terms “comprises”, “comprising”, “includes”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus preceded by “comprises . . . a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or method.

The present disclosure relates to a method and a semen quality analysis system for evaluating quality of semen sample. The present disclosure envisages a method, which can efficiently analyze and classify objects in the semen sample to evaluate the quality of semen. The method involves estimating various parameters of the semen sample such as, number of sperm objects in the semen sample, number of non-sperm objects in the semen sample, morphological characteristics of the sperm objects, a differential count of normal and abnormal sperm objects, and an aggregate count of the non-sperm objects. In an embodiment, the method includes computing a semen quality index, which is indicative of the quality of the semen sample being examined, using each of the critical parameters listed above.

In an embodiment, detecting presence of the non-sperm objects in the semen sample may be critical to understand different types of pathological and non-pathological objects of interest in the semen sample. As an example, the non-sperm objects may include, without limiting to, White Blood Cells (WBCs), Red Blood Cells (RBCs), spermatogonium cells, pathological casts, and one or more microbes. Hence, analyzing the proportion and characteristics of each of the pathological and/or non-pathological objects in the semen may be necessary for an accurate estimation of the semen quality. Consequently, the present method induces performing an advanced statistical analysis of the sperm objects, as well as the pathological and/or non-pathological objects of interest in the semen sample, for computing a more accurate semen quality index for the semen sample being examined.

In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

FIG. 1 illustrates an exemplary environment 100 of evaluating quality of semen sample in accordance with some embodiments of the present disclosure.

The environment 100 includes a semen quality analysis system 103 that analyses plurality of microscopic images 101 of the semen sample and computes a semen quality index 109. In an embodiment, the plurality of microscopic images 101 of the semen sample are captured using an image capturing device. As an example, each of the plurality of microscopic images 101 may be captured at a magnification range of 400×, to ensure that each object in the semen sample are clearly visible in the plurality of microscopic images 101. In an implementation, the image capturing device may be configured in the semen quality analysis system 103. In another implementation, the image capturing device may be configured external to the semen quality analysis system 103, and may be communicatively associated with the semen quality analysis system 103 for transferring each of the plurality of microscopic images 101 to the semen quality analysis system 103. As an example, the image capturing device may be a camera, placed on eyepiece or on ocular of a standard light microscope.

In an embodiment, the semen quality analysis system 103 includes analyzing each of the plurality of microscopic images 101 using one or more predetermined image processing techniques for identifying one or more unusable images in the plurality of microscopic images 101. The one or more unusable images may be identified based on one or more predetermined conditions, which determine whether the plurality of microscopic images 101 are suitable for further processing.

As an example, the one or more predetermined conditions for determining usability of the plurality of microscopic images 101 may include, without limitation, blur level in each of the plurality of microscopic images 101 exceeding a predefined threshold blur value, count of the sperm objects, the non-sperm objects and other objects that are visibly present in each of the plurality of microscopic images 101 being less than a predefined threshold count and staining proportion in each of the plurality of microscopic images 101 exceeding a predefined threshold staining proportion. The step of eliminating (105) the one or more unusable images among the plurality of microscopic images 101, before further processing of the plurality of microscopic images 101, helps in enhancing efficiency and accuracy of evaluating the semen sample. In an embodiment, the plurality of microscopic images 101 that do not satisfy the one or more predetermined conditions stated above are considered to be unusable and are eliminated from further processing.

In an embodiment, upon identifying and eliminating the one or more unusable images from the plurality of microscopic images 101, the semen quality analysis system 103 further processes the plurality of microscopic images 101 to identify one or more sperm objects and one or more non-sperm objects in the plurality of microscopic. images 101. The one or more sperm objects may include actual sperm bodies in the semen sample that are capable of undergoing fertilization. Similarly, the one or more non-sperm objects may include, without limitation, the White Blood Cells (WBCs), Red Blood Cells (RBCs), spermatogonium cells, pathological casts, and one or more microbes that are incapable of undergoing fertilization.

Upon identifying the one or more sperm objects in the plurality of microscopic images 101, the semen quality analysis system 103 extracts each of the one or more sperm objects for determining one or more morphological characteristics of each of the one or more sperm objects. As an example, the one or more morphological characteristics may include, without limiting to, texture of the sperm object, shape of the sperm object, and size of the sperm object. Further, based on the one or more morphological characteristics of each of the one or more sperm objects, the semen quality analysis system 103 classifies each of the one or more sperm objects into one or more normal sperm objects and one or more abnormal sperm objects.

As an example, the one or more sperm objects may be classified as normal, when each of the one or more morphological characteristics of the one or more sperm objects is compliant with a predefined standard for morphological characteristics. Similarly, the one or more sperm objects may be classified as abnormal, when at least one of the one or more morphological characteristics of the one or more sperm objects deviates from the predefined standard for morphological characteristics. In an embodiment, upon classifying the one or more sperm objects into the one or more normal sperm objects and the one or more abnormal sperm objects, the semen quality analysis system 103 determines a differential count of the one or more normal sperm objects and the one or more abnormal sperm objects. The differential count helps in determining total proportion of normal sperm objects and/or abnormal sperm objects in the one or more sperm objects.

In an embodiment, the semen quality analysis system 103 includes determining an aggregate count of the one or more non-sperm objects identified in the plurality of microscopic images 101. The aggregate count of the one or more non-sperm objects helps in determining significance of various non-sperm objects in the semen sample, which in turn helps in determining the pathological status of the semen sample.

Finally, the semen quality analysis system 103 computes a semen quality index 109 for the semen sample based on the one or more morphological characteristics of each of the one or more sperm objects, the differential count of the one or more normal sperm objects and the one or more abnormal sperm objects, the total motility estimate 107 of the semen sample, and the aggregate count of the one or more non-sperm objects. In an embodiment, semen quality index 109 of the semen sample may be an indicative measure of the quality of the semen.

In an embodiment, the total motility estimate 107 of the semen sample may be determined using one or more predefined techniques, by analyzing movement of each of the one or more sperm objects in the semen sample, when the one or more sperm objects are moving/alive in the semen sample. As per embodiments of the present disclosure the total motility estimate 107 of the semen sample is considered to be a predetermined parameter for computing the semen quality index 109. In an embodiment, the total motility estimate 107 may be received as an external input to the semen quality analysis system 103. In another embodiment, the total motility estimate 107 may be pre-calculated and stored in the semen quality analysis system 103.

As an example, the total motility estimate 107 of the semen sample may be determined by identifying an individual motility class of each of the one or more sperm objects in the semen sample. Here, the motility class of each of the one or more sperm objects may be at least one of a rapid motility class, a slow motility class, a non-motility class, or an immotile class. The one or more sperm objects that exhibit an active movement, either linearly or in large circles, may be considered to have rapid motility. Similarly, the one or more sperm objects that move in small circles, and exhibit only flagellar movements, or that lack progression may be classified as a slow motile or a non-motile sperm objects. Further, the one or more sperm objects that do not exhibit any movement may be classified as immotile sperm objects. In an embodiment, the total motility estimate 107 of the semen sample is determined before staining of the semen sample. The semen sample may be stained using a standard staining process prescribed by the World Health Organization (WHO).

FIG. 2 shows a detailed block diagram illustrating a semen quality analysis system 103 for evaluating quality of semen sample in accordance with some embodiments of the present disclosure.

In an embodiment, the semen quality analysis system 103 may include an I/O interface 201, a processor 203, and a memory 205. The I/O interface 201 may be configured to communicate with an image capturing device associated with the semen quality analysis system 103, for receiving plurality of microscopic images 101 of semen sample. The memory 205 may be communicatively coupled to the processor 203. The processor 203 may be configured to perform one or more functions of the semen quality analysis system 103 for evaluating quality of the semen sample.

In some implementations, the semen quality analysis system 103 may include data 207 and modules 209 for performing various operations in accordance with the embodiments of the present disclosure. In an embodiment, the data 207 may be stored within the memory 205 and may include, without limiting to, data related to the plurality of microscopic images 101, morphological characteristics 211, differential count 213 of the one or more normal sperm objects and the one or more abnormal sperm objects (referred to as the differential count 213 hereinafter), an aggregate count 215 of one or more non-sperm objects (referred to as the aggregate count 215 hereinafter), semen quality index 109 and other data 217.

In some embodiments, the data 207 may be stored within the memory 205 in the form of various data structures. Additionally, the data 207 may be organized using data models, such as relational or hierarchical data models. The other data 217 may store data, including temporary data and temporary files, generated by the modules 209 for evaluating quality of the semen sample.

In an embodiment, the plurality of microscopic images 101 of the semen sample are captured using the image capturing device associated with the semen quality analysis system 103. As an example, each of the plurality of microscopic images 101 may be captured at a precision of 400× magnification range. Further, each of the plurality of microscopic images 101 may correspond to different Field of View (FOV) of the semen sample being examined. FIG. 3G shows an exemplary microscopic image of the semen sample.

In an implementation, the image capturing device may be a camera, placed on eyepiece or on ocular of a standard light microscope. Further, the camera may have dedicated computing resources, that enable the camera to perform various functionalities, including automatically capturing the plurality of microscopic images 101 of the semen sample, performing primary analysis of the plurality of microscopic images 101, transmitting the plurality of microscopic images 101 to the semen quality analysis system 103, and the like. Further, the microscopic assembly, including a microscopic stage on which the semen sample to be examined is placed, may be operated manually or automatically.

In an embodiment, the one or more morphological characteristics 211 of each of the one or more sperm objects indicates physical appearance of each of the one or more sperm objects. As an example, the one or more morphological characteristics 211 may include, without limiting to, texture of the sperm object, shape of the sperm object, and size of the sperm object. In an embodiment, each of the one or more sperm objects may be classified into one or more normal sperm objects and one or more abnormal sperm objects based on the one or more morphological characteristics 211 of each of the one or more sperm objects.

Generally, every sperm object is known to consist of a head region, a neck region, a middle piece (or midpiece), a principal piece, and an end piece. For evaluation purposes, the sperm object may be considered to comprise a head (combining the head region and the neck region) and a tail (combining the midpiece, principal piece and the end piece). In respect of the above structural convention, the one or more sperm objects may be considered to be normal only when both its head and tail are normal.

In an embodiment, the head region of the sperm objects may be considered to be normal when the head region is smooth, regularly contoured and generally oval in shape, as shown in FIG. 3A and FIG. 3B. Also, there must be a well-defined acrosomal region comprising 40-70% of the head area, such that the acrosomal region should contain no large vacuoles, and not more than two small vacuoles, which should not occupy more than 20% of the sperm head. The post-acrosomal region of the head should not contain any vacuoles.

In an embodiment, the tail is considered to be normal when the midpiece is slender, regular and about the same length as the sperm head. The major axis of the midpiece should be aligned with the major axis of the sperm head. Presence of residual cytoplasm on the midpiece may be considered an anomaly when it is in excess, i.e. when the residual cytoplasm exceeds one third of the sperm head size. Further, the principal piece should have a uniform caliber along its length, and it should be thinner than the midpiece, and be approximately 45 um long (about 10 times the head length). Also, the tail that appears to be looped back on itself, without any sharp angles indicative of a flagellar break, may be considered to be normal.

In an embodiment, the one or more sperm objects that deviate from any of the aforementioned morphological conditions may be considered as defective or abnormal. For example, as shown in FIG. 3C and FIG. 3D, the one or more sperm objects may be considered to be abnormal when the head region is irregular (FIG. 3C) or when there is a flagellar break in the midpiece or tail region of the sperm object (FIG. 3D). Further, to enhance accuracy in the evaluation, the one or more sperm objects that exhibit borderline morphological characteristics 211 may also be considered as abnormal.

In an embodiment, the differential count 213 of the one or more sperm objects and the one or more non-sperm objects may be determined subsequent to classifying the one or more sperm objects and determining a count/proportion of each of the one or more normal sperm objects and each of the one or more abnormal sperm objects.

For example, consider ‘S’ number of sperm objects in the semen sample, out of which, ‘A’ number of sperm objects are determined to be normal, and ‘B’ number of sperm objects are determined to be abnormal. Thus, S=A+B. Here, a relative proportion or the differential count 213 of the one or more normal sperm objects and the one or more abnormal sperm objects may be determined as following:


Differential count of the one or more normal sperm objects [M]=[A/(A+B)]


Differential count of the one or more abnormal sperm objects [N]=[B/(A+B)]

In an embodiment, the aggregate count 215 of the one or more non-sperm objects may be determined by estimating total count of each type of the non-sperm objects in the semen sample, and then collating the total count of each type of the non-sperm objects to determine the aggregate count 215. The aggregate count 215 of the one or more non-sperm objects may be useful for making prediction about pathological health of the semen sample.

For example, existence of the one or more non-sperm artifacts like White Blood Cells (WBC), Crystals, agglutination sperm cells, spermatogonia, etc. may be attributed to providing the following insights on the health of the individual whose semen sample is being examined:

    • 1. When WBCs are detected in semen sample, it may raise concern because, it indicates a genital tract infection. If it is not treated, there can be damage to the testis. Additional damage can be caused by the WBCs because they produce superoxide radicals, which damage the sperm, along with its DNA. This damage can also affect the ability of the one or more sperm objects to fertilize an oocyte.
    • 2. Agglutination of sperm cells impairs sperm motility and prevents the sperm from swimming through the cervix towards the egg.
    • 3. Spermatogonia are immature sperm cells. The number of spermatogonia of the testicles is an important criterion for the assessment of the probable fertility prognosis. The determination of the mean content of spermatogonia per cross section of one Tubulus Seminiferus is considered as a standardized procedure in clinical practice.
    • 4. The presence of crystals in the semen sample can indicate the probable calcification of the one or more sperm objects or possibility of infections along the urinary tract.

In an embodiment, the semen quality index 109 of the semen sample may be computed based on the one or more morphological characteristics 211 of each of the one or more sperm objects, the differential count 213 of the one or more normal sperm objects and the one or more abnormal sperm objects, the total motility estimate 107 of semen sample, and the aggregate count 215 of the one or more non-sperm objects. As an example, the semen quality index 109 may be in the form of a tabular summary, as illustrated in Table A below.

Volume of semen sample taken for observation: 10 micro liters Count of sperm objects (in millions) 100  A. Normal sperm objects (A) 80 B. Abnormal sperm objects (B)   2.0 C. Differential count of sperm objects (M) 70% D. Differential count of non-sperm objects 30% (N) Total motility estimate A. Count of Progressive sperm objects (I) 80 B. Count of non-progressive sperm objects 10 (J) C. Count of immotile sperm objects (K) 10 D. Percentage of sperm objects with 80% Progressive motility (X) E. Percentage of sperm objects with Non- 10% progressive motility (Y) F. Percentage of immotile sperm objects (Z) 10%

Here, information about the total motility estimate 107 of the semen sample may be determined prior to staining of the semen sample, by tracking and analyzing the movement of the one or more sperm objects when they are alive. Thus, the semen quality index 109 of the semen sample indicates the overall quality of the semen sample.

In an embodiment, the data 207 may be processed by one or more modules 209 of the semen quality analysis system 103. In one implementation, the one or more modules 209 may be stored as a part of the processor 203. In another implementation, the one or more modules 209 may be communicatively coupled to the processor 203 for performing one or more functions of the semen quality analysis system 103. The modules 209 may include, without limiting to, an image quality analysis module 219, an object identification module 221, morphology analysis module 223, semen quality index computation module 225 and other modules 227.

As used herein, the term module refers to an application specific integrated circuit (ASIC), an electronic circuit, a processor (shared, dedicated, or group) and memory that execute one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that provide the described functionality. in an embodiment, the other modules 227 may be used to perform various miscellaneous functionalities of the sperm quality analysis system 103. It will be appreciated that such modules 209 may be represented as a single module or a combination of different modules.

In an embodiment, the image quality analysis module 219 may be responsible for analyzing and/or processing each of the plurality of microscopic images 101 before taking the plurality of microscopic images 101 for further evaluation. Further, the image quality analysis module 219 may eliminate one or more unusable images from the plurality of microscopic images 101 based on one or more predetermined conditions.

As an example, the one or more predetermined conditions may include, without limiting to, blur level in each of the plurality of microscopic images 101 exceeding a predefined threshold blur value, count of the sperm objects, the non-sperm objects and other objects, visibly present in each of the plurality of microscopic images 101, less than a predefined threshold count, and staining proportion in each of the plurality of microscopic images 101 exceeding a predefined threshold staining proportion. The significance of each of the one or more predetermined conditions for determining usability of the plurality of microscopic images 101 are as illustrated in the following paragraphs:

    • 1. Count of objects (Density of the image);
      • Generally, it is observed that, objects in the semen sample (either sperm objects or non-sperm objects) are not evenly spread all over the slide As shown in FIG. 3E and FIG. 3F, the one or more sperm objects may be clumped together in certain areas, while being totally absent in other areas of the slide. However, for the evaluation purpose, images captured from those areas where the sperm objects are more or less well separated from each other are required. The density of the plurality of microscopic images 101 is computed to detect whether an image has an acceptable distribution of the sperm objects.
      • Further, the density of the plurality of plurality of microscopic images 101 may be determined using the follows steps:
      • A. Converting the colour of each of the plurality of microscopic images 101 into grayscale. The grayscale image consists of a single channel only, with pixel values ranging from 0 to 255.
      • B. Thresholding the grayscale images using Otsu's thresholding method, and then inverting the images. Upon inverting the images, as shown in FIG. 3H, the dark coloured stained sperm objects appear as white (pixel intensity 255), while the light background appears black (pixel value 0).
      • C. After thresholding, the image may have “holes”. The “holes” are filled using common mathematical morphological operation called ‘dilation’, with a circular mask.
      • D. Analysing a central square patch of the inverted image as follows:
        • Computing number of “white” pixels contained in the central patch, and denoting them by ‘N’. Here, the white pixels correspond to the foreground, i.e. the objects visible in the image. Intuitively, an image of an empty area where no sperm objects are present, will have a lower value of N, whereas an image of an area where sperm objects are clumped together will have a higher value of N.
        • Computing the density ‘D’ of the image as D=N/P2, where ‘P’ is the length of each side of the central patch.
      • In an embodiment, upon computing the density of the plurality of microscopic images 101, a minimum and maximum threshold value of the density is determined. Thereafter, only images which have ‘D’ in the range of minimum and maximum threshold are accepted as usable images, and other images are eliminated from further processing.
    • 2. Blur level:
      • Generally, the blur effect in the plurality of microscopic images 101 can be of two types, namely focus blur (or defocus aberration) and motion blur.
      • A. Defocus aberration:
        • In general, defocus is an aberration in which the image under consideration is out of focus. Optically, defocus refers to a translation along the optical axis, away from the plane, or surface of best focus. Defocus reduces the sharpness and the contrast of the plurality of microscopic images 101 captured and turns the sharp edges or sharp transitions into gradual transitions.
      • B. Motion Blur:
        • Motion blur is the apparent streaking of rapidly moving objects in a still image or a sequence of images. It results when the image being recorded changes during the recording of a single exposure, either due to rapid movement or long exposure. Due to the inherent nature of image capturing mechanism, where the motion of the camera is inevitable, a versatile blur check is required to overcome motion blur.
      • A common measure of the perceived sharpness of a digital image is the variance of Laplacian ‘V’. Wherein, ‘V’ is higher for a sharp image and lower for a blurry image. However, the absolute value of ‘V’ is dependent on the number of objects (specifically, the number of edges) visible in the image. Thus, a very sharply focused image with only a few images may have a lower value of ‘V’ than a blurry image containing many objects (or texture). Therefore, the value of ‘V’ must be normalized to make it independent of the number of objects visible in the image. Further, the quantity ‘V’ is computed on the same central patch of green channel of original color images.
      • In an embodiment, the sharpness ‘S’ of the image may be defined as S=V/D, where ‘D’ is the density as calculated in the preceding paragraph. The normalization operation is known to effectively normalize the sharpness measure to take into account the number of visible objects. An upper and a lower bound of ‘S’ were determined through careful experimentation. Any image where the ‘S’ lies beyond this range is deemed unacceptable for further analysis, and such images are eliminated.
    • 3. Overstating of the sample:
      • In an ideal scenario, the background area of a sample will be clear, without any stain coloration or smudges. However, due to manual staining process, some areas in the sample can have dark, stain induced coloration of the background, and large smudges. Such areas are not suitable for evaluating the sperm quality, and hence are eliminated from further processing.
      • In an embodiment, the coloration of the background may be detected by using value of the Otsu threshold in the above two steps. In case of a stained background, the overall image has a darker shade and thus, the threshold value obtained by Otsu's method is expected to be lower. Through experimentation, a lower limit on the threshold value for images with unstained backgrounds is determined. Any of the plurality of microscopic images 191 with a threshold lower than determined lower limit may be deemed as overstained and thus eliminated.

In an embodiment, the object identification module 221 may be responsible for identifying the one or more sperm objects and the one or more non-sperm objects in each of the plurality of microscopic images 101, upon eliminating the one or more unusable images from the plurality of microscopic images 101. The object identification module 221 helps in extracting the objects of interest (both sperm objects and non-sperm objects) from the plurality of microscopic images 101.

In an embodiment, extraction of the objects of interest starts with applying the Otsu's threshold on the grayscale version of the plurality of microscopic image, followed by inversion (as described earlier) of the plurality of microscopic images 101 to obtain a binary image, as shown in FIG. 3H. This ensures that foreground of the plurality of microscopic images 101 (comprising the objects of interest) is effectively separated from background of the plurality of microscopic images 101 as the grayscale images reveal a bi-modal distribution of pixel intensities. Further, inverted plurality of microscopic images 101 are then dilated with a circular or elliptical mask to fill gaps and holes in the binary image.

Upon dilation of the plurality of microscopic images 101, the object identification module 221 identifies one or more connected components in the image. The connected components correspond to the objects visible in the image, not all of which may be sperm cells. Further, each connected components are analyzed separately. In an embodiment, the connected components with larger areas may correspond to either sperm cells clumped together, or other artefacts or cells. Similarly, the connected component with smaller areas correspond to small artefacts that might be present due to stain. A lower threshold limit and an upper threshold limit of the area of the connected components may be predefined, such that, the threshold limits correspond to the minimum and maximum biological limits to the size of a sperm cell head, along with some margin value. Thereafter, only those connected components, whose area lies within the predefined threshold range may be accepted for further processing.

In an embodiment, the object identification module 221 may reject the one or more sperm objects which are close to each other, but not necessarily clumped together.

Generally, it is difficult to make an individual analysis of the one or more sperm objects that are in close vicinity, as they may have entangled their tails. For each object of interest which passes through the area threshold check as illustrated above, the object identification module 221 determines whether there is any other object within a radius of R pixels with respect to an already identified object. In an embodiment, if there are any objects present in the R pixel radius, all such objects are rejected. As an example, the ‘R’ may be set to correspond to a value of 10 μM.

The distance between the objects within the radius of R pixels may be determined based on the following steps:

    • 1. Computing a pair-wise Euclidean distance between any two points P and
      • Pj using the equation: √{square root over ((X1−X2)2+(Y1−Y2)2)}
    • 2. Threshold all the pair-wise distance based on the value of R, and reject all object which are less than R pixels apart from.
    • 3. Only those objects which are at least R pixels away from the nearest object are selected for further processing.

Due to the non-planarity of the slide surface, not all objects in the image may be at sharp focus, which reduces the quality of the data. To mitigate the above problem, individual patches which have a high sharpness are chosen for analysis. In an embodiment, the one or more patches having higher sharpness may be selected based on the following steps:

    • 1. Calculate the sharpness of each of the patches
    • 2. Sort the sharpness of each of the patches in a predetermined numerical order
    • 3. Eliminate the one or more patches having lowest sharpness. As an example, the one or more patches that fall within lower 20 percentile of all the patches may be eliminated.

In an embodiment, the one or more patches, thus selected, may be still susceptible to the following issues:

    • A. The one or more clumped sperm objects may be extracted due to the inconsistency of their connectivity. The area formed by the connected component corresponding to the one or more clumped sperm objects may be disjoint, and hence they may pass through the area threshold limit set in the process of extraction.
    • B. There are many non-sperm artefacts like crystals, stain deposits, etc., which resemble the dimension of a sperm head and may pass throughout the extraction process. To tackle these issues, a screening phase may be included in the analysis to identify the non-sperm objects and the clumped sperms. Also, a convolutional neural network may be trained to decide between the one or more sperm objects, the one or more non sperm objects/artefacts, and the one or more clumped sperm objects. The one or more patches that are classified as sperm objects by this screening model may be taken for analyzing the morphological characteristics 211.

In an embodiment, the morphology analysis module 223 may be responsible for determining the one or more morphological characteristics 211 of the objects of interest identified as the one or more sperm objects. Further, the morphology analysis module 223 may classify each of the one or more sperm objects into the one or more normal sperm objects and the one or more abnormal sperm objects, based on each of the one or more morphological characteristics 211 of the one or more sperm objects.

In an embodiment, upon determining the one or more normal sperm objects and the one or more abnormal sperm objects, the morphology analysis module 223 may generate certain statistical parameters that provide insights into the morphological characteristics 211 of the one or more sperm objects. As an example, the statistical parameters may include, without limiting to, a mean value, and standard deviation of head diameter for normal sperm objects, a mean value, and standard deviation of head diameter for abnormal sperm objects, a histogram of diameters for normal sperm objects and a histogram of diameters for abnormal sperm objects.

In an embodiment, the semen quality index computation module 225 may be responsible for computing the semen quality index 109 of the semen sample based on the one or more morphological characteristics 211 of each of the one or more sperm objects, the differential count 213 of the one or more normal sperm objects and the one or more abnormal sperm objects, the total motility estimate 107 of semen sample, and the aggregate count 215 of the each of the one or more non-sperm objects. As an example, the semen quality index 109 may be provided in the form of a table (as illustrated in Table A), wherein values of each of the one or more parameters that are used for computing the semen quality index 109 are indicated. Further, values of each of the one or more parameters, specified in the semen quality index 109, may be compared with a standard range of values for evaluating the quality of the semen sample being examined.

Optionally, the semen quality analysis system 103 may be configured to generate one or more reports such as graphs, charts, tables and the like for indicating the quality of semen sample to a user. Further, the semen quality analysis system 103 may be configured to transmit the one or more reports, thus generated, to the user through one or more user devices pre-registered with the semen quality analysis system 103.

FIG. 4 shows a flowchart illustrating a method for evaluating quality of semen sample in accordance with some embodiments of the present disclosure.

As illustrated in FIG. 4, the method 400 includes one or more blocks illustrating a method for evaluating quality of semen sample using a semen quality analysis system 103, for example the semen quality analysis system 103 of FIG. 1. The method 400 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform specific functions or implement specific abstract data types.

The order in which the method 400 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the spirit and scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.

At block 401, the method 400 comprises capturing, by the semen quality analysis system 103, a plurality of microscopic images 101 of a stained semen sample being examined. In an implementation, the plurality of microscopic images 101 of the stained sample may be captured using an image capturing unit associated with the semen quality analysis system 103. In an implementation, the image capturing unit may be a camera, placed on an eyepiece or on an ocular of a standard light microscope.

At block 403, the method 400 comprises eliminating, by the semen quality analysis system 103, one or more unusable images from the plurality of microscopic images 101 based on one or more predetermined conditions. As an example, the one or more predetermined conditions for analyzing usability of each of the plurality of microscopic images 101 may include, without limiting to, blur level in each of the plurality of microscopic images 101 exceeding a predefined threshold blur value; count of the sperm objects, the non-sperm objects and other objects, visibly present in each of the plurality of microscopic images 101, less than a predefined threshold count; and staining proportion in each of the plurality of microscopic images 101 exceeding a predefined threshold staining proportion.

At block 405, the method 400 comprises identifying, by the semen quality analysis system 103, one or more sperm objects and one or more non-sperm objects in each of the plurality of microscopic images 101. As an example, the one or more non-sperm objects may include, without limiting to, at least one of White Blood Cells (WBCs), Red Blood Cells (RBCs), spermatogonium cells, pathological casts, and one or more microbes.

At block 407, the method 400 comprises determining, by the semen quality analysis system 103, one or more morphological characteristics 211 of each of the one or more sperm objects, identified in each of the plurality of microscopic images 101, As an example, the one or more morphological characteristics 211 may include, without limitation, at least one of texture of the sperm object, shape of the sperm object, and size of the sperm object. In an embodiment, the morphological characteristics 211 may be used for classifying each of the one or more sperm objects into one or more normal sperm objects and one or more abnormal sperm objects based on predetermined classification techniques such as, Convoluotional Neural Network (CNN) analysis technique.

At block 409, the method 400 comprises determining, by the semen quality analysis system 103, a differential count 213 of the one or more normal sperm objects and one or more abnormal sperm objects. At block 411, the method 400 comprises determining, by the semen quality analysis system 103, an aggregate count 215 of the one or more non-sperm objects identified in each of the plurality of microscopic images 101.

At block 413, the method 400 comprises computing, by the semen quality analysis system 103, a semen quality index 109 based on the one or more morphological characteristics 211 of each of the one or more sperm objects, the differential count 213 of the one or more normal sperm objects and the one or more abnormal sperm objects, a total motility estimate 107 of the semen sample, and the aggregate count 215 of the one or more non-sperm objects, for evaluating the quality of the semen sample. In an embodiment, the quality of the semen sample is directly proportional to the semen quality index 109 of the semen sample.

In an embodiment, the total motility estimate 107 of the semen sample may be determined prior to staining of the semen sample, and may be used as an external input factor while computing the semen quality index 109 of the sample based on the total motility estimate 107 of the semen sample.

Computer System

FIG. 5 illustrates a block diagram of an exemplary computer system 500 for implementing embodiments consistent with the present disclosure. In an embodiment, the computer system 500 may be semen quality analysis system 103, which is used for evaluating quality of semen sample. The computer system 500 may include a central processing unit (“CPU” or “processor”) 502. The processor 502 may comprise at least one data processor for executing program components for executing user- or system-generated business processes. A user, may include a person, a person whose semen sample is being examined, or an animal whose semen sample is being examined. The processor 502 may include specialized processing units such as integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, digital signal processing units, etc.

The processor 502 may be disposed in communication with one or more input/output (I/O) devices (511 and 512) via I/O interface 501. The I/O interface 501 may employ communication protocols/methods such as, without limitation, audio, analog, digital, stereo, IEEE-1394, serial bus, Universal Serial Bus (USB), infrared, PS/2, RNC, coaxial, component, composite, Digital Visual Interface (DVI), high-definition multimedia interface (HDMI), Radio Frequency (RF) antennas, S-Video, Video Graphics Array (VGA), IEEE 802.n /b/g/n/x, Bluetooth, cellular (e.g., Code-Division Multiple Access (CDMA), High-Speed Packet Access (HSPA+), Global System For Mobile Communications (GSM), Long-Term Evolution (LTE) or the like), etc. Using the I/O interface 501, the computer system 500 may communicate with one or more I/O devices 511 and 512. In some implementations, the I/O interface 501 may be used to connect to a user device, such as a smartphone associated with the user, to notify the user about semen quality index 109, and to optionally provide one or more semen quality reports to the user.

In some embodiments, the processor 502 may be disposed in communication with a communication network 509 via a network interface 503. The network interface 503 may communicate with the communication network 509. The network interface 503 may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10/100/1000 Base T), Transmission Control Protocol/Internet Protocol (TCP/IP), token ring, IEEE 802.11a/b/g/n/x, etc. Using the network interface 503 and the communication network 509, the computer system 500 may communicate with an image capturing device, causing the image capturing device to capture and transmit a plurality of microscopic images 101 of the semen sample being examined. Similarly, the communication network 509 may be used to retrieve the plurality of microscopic images 101 from an external server, when the plurality of microscopic images 101 are stored on the external server. Further, the communication network 509 may be used to provide the semen quality index 109 of the semen sample being examined to the user.

The communication network 509 can be implemented as one of the several types of networks, such as intranet or Local Area Network (LAN) and such within the organization. The communication network 509 may either be a dedicated network or a shared network, which represents an association of several types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), etc., to communicate with each other. Further, the communication network 509 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, etc.

In some embodiments, the processor 502 may be disposed in communication with a memory 505 (e.g., RAM 513, ROM 514, etc. as shown in FIG. 5) via a storage interface 504. The storage interface 504 may connect to memory 505 including, without limitation, memory drives, removable disc drives, etc., employing connection protocols such as Serial Advanced Technology Attachment (BATA), integrated Drive Electronics (IDE), IEEE-1394, Universal Serial Bus (USB), fiber channel, Small Computer Systems Interface (SCSI), etc. The memory drives may further include a drum, magnetic disc drive, magneto-optical drive, optical drive, Redundant Array of Independent Discs (RAID), solid-state memory devices, solid-state drives, etc.

The memory 505 may store a collection of program or database components, including, without limitation, user/application 506, an operating system 507, a web browser 508, and the like. In some embodiments, computer system 500 may store user/application data 506, such as the data, variables, records, etc. as described in this invention. Such databases may be implemented as fault-tolerant, relational, scalable, secure databases such as Oracle or Sybase.

The operating system 507 may facilitate resource management and operation of the computer system 500. Examples of operating systems include, without limitation, Apple Macintosh OS X, UNIX, Unix-like system distributions (e.g., Berkeley Software Distribution (BSD), FreeBSD, Net BSD, Open BSD, etc.), Linux distributions (e.g., Red Hat, Ubuntu, K-Ubuntu, etc.), international Business Machines (IBM) OS/2, Microsoft Windows (XP, Vista/7/8, etc.), Apple LOS, Google Android, Blackberry Operating System (OS), or the like. A user interface may facilitate display, execution, interaction, manipulation, or operation of program components through textual or graphical facilities. For example, user interfaces may provide computer interaction interface elements on a display system operatively connected to the computer system 500, such as cursors, icons, check boxes, menus, windows, widgets, etc. Graphical User Interfaces (GUIs) may be employed, including, without limitation, Apple Macintosh operating systems' Aqua, IBM OS/2, Microsoft Windows (e.g., Aero, Metro, etc.), Unix X-Windows, web interface libraries (e.g., ActiveX, Java, JavaScript, AJAX, HTML, Adobe Flash, etc.), or the like.

Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present invention. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., non-transitory. Examples include Random Access Memory (RAM), Read-Only Memory (ROM), volatile memory, nonvolatile memory, hard drives, Compact Disc (CD) ROMs, Digital Video Disc (DVDs), flash drives, disks, and any other known physical storage media.

Advantages of the Embodiment of the Present Disclosure are Illustrated Herein

In an embodiment, the present disclosure discloses a method for evaluating quality of a stained semen sample,

In an embodiment, the method of present disclosure is capable of determining morphological characteristics of sperm objects, and classifying the sperm objects as normal and abnormal sperm objects based on the morphological characteristics of the sperm objects.

In an embodiment, the method of present disclosure helps in determining a relative proportion of the normal sperm objects and the abnormal sperm objects by computing a differential count of the sperm objects and the non-sperm objects.

In an embodiment, the method of present disclosure computes an aggregate count of each of the non-sperm objects in the semen sample, and thereby helps in understating significance of various pathological and non-pathological artefacts comprised in the non-sperm object population.

In an embodiment, the method of present disclosure uses the aggregate count of the non-sperm objects for computing the semen quality index of the semen sample, thereby making the semen quality index a more accurate and reliable outcome of the semen quality analysis.

In an embodiment, the present disclosure discloses a completely automated method for analyzing the quality of semen sample, thereby helps in overcoming inconsistencies of manual methods of semen quality analysis, such as human errors, limited number of repetitions of analysis, and time required for the analysis.

The terms “an embodiment”, “embodiment”, “embodiments”, “the embodiment”, “the embodiments”, “one or more embodiments”, “some embodiments”, and “one embodiment” mean “one or more (but not all) embodiments of the invention(s)” unless expressly specified otherwise.

The terms “including”, “comprising”, “having” and variations thereof mean “including but not limited to”, unless expressly specified otherwise. The enumerated listing of items does not imply that any or all the items are mutually exclusive, unless expressly specified otherwise.

The terms “a”, “an” and “the” mean “one or more”, unless expressly specified otherwise, A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.

When a single device or article is described herein, it will be clear that more than one device/article (whether they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether they cooperate), it will be clear that a single device/article may be used in place of the more than one device or article or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality/features. Thus, other embodiments of the invention need not include the device itself.

Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the embodiments of the present invention are intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.

While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.

Referral Numerals: Reference Number Description 100 Environment 101 Plurality of microscopic images 103 Semen quality analysis system 107 Total motility estimate 109 Semen quality index 201 I/O interface 203 Processor 205 Memory 207 Data 209 Modules 211 Morphological characteristics 213 Differential count 215 Aggregate count 217 Other data 219 Image quality analysis module 221 Object identification module 223 Morphology analysis module 225 Semen quality index computation module 227 Other modules 500 Exemplary computer system 501 I/O Interlace of the exemplary computer system 502 Processor of the exemplary computer system 503 Network interface 504 Storage interface 505 Memory of the exemplary computer system 506 User/Appiication 507 Operating system 508 Web browser 509 Communication network 511 Input devices 512 Output devices 513 RAM 514 ROM

Claims

1. A method for evaluating quality of semen sample, the method comprising:

capturing, by a semen quality analysis system, a plurality of microscopic images of a stained semen sample being examined;
eliminating, by the semen quality analysis system, one or more unusable images from the plurality of microscopic image based on one or more predetermined conditions;
identifying, by the semen quality analysis system, one or more sperm objects and one or more non-sperm objects in each of the plurality of microscopic images determining, by the semen quality analysis system, one or more morphological characteristics of each of the one or more sperm objects, identified in each of the plurality of microscopic images, for classifying each of the one or more sperm objects into one or more normal sperm objects and one or more abnormal sperm objects based on predetermined classification techniques;
determining, by the semen quality analysis system, a differential count of the one or more normal sperm objects and the one or more abnormal sperm objects;
determining, by the semen quality analysis system, an aggregate count of the one or more non-sperm objects identified in each of the plurality of microscopic images; and
computing, by the semen quality analysis system, a semen quality index based on the one or more morphological characteristics of each of the one or more sperm objects, the differential count of the one or more normal sperm objects and the one or more abnormal sperm objects, a total motility estimate of semen sample, and the aggregate count of the one or more non-sperm objects, for evaluating the quality of the semen sample.

2. The method as claimed in claim 1, wherein the one or more predetermined conditions for analyzing usability of each of the plurality of microscopic images comprises one of:

blur level in each of the plurality of microscopic images exceeding a predefined threshold blur value;
count of the sperm objects, the non-sperm objects and other objects, visibly present in each of the plurality of microscopic images, less than a predefined threshold count; and
staining proportion in each of the plurality of microscopic images exceeding a predefined threshold staining proportion.

3. The method as claimed in claim 1, wherein the one or more morphological characteristics comprises at least one of texture of the sperm object, shape of the sperm object, and size of the sperm object.

4. The method as claimed in claim 1, wherein the total motility estimate of the semen sample is determined prior to staining of the semen sample.

5. The method as claimed in claim 1, wherein the one or more non-sperm objects comprises at least one of White Blood Cells (WBCs), Red Blood Cells (RBCs), spermatogonium cells, pathological casts, and one or more microbes.

6. The method as claimed in claim 1, wherein the quality of the semen sample is directly proportional to the semen quality index of the semen sample.

7. A semen quality analysis system for evaluating quality of semen sample, the semen quality analysis system comprising:

a processor; and
a memory, communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which on execution, cause the processor to: capture a plurality of microscopic images of a stained semen sample being examined; eliminate one or more unusable images from the plurality of microscopic images based on one or more predetermined conditions; identify one or more sperm objects and one or more non-sperm objects in each of the plurality of microscopic images; determine one or more morphological characteristics(of each of the one or more sperm objects, identified in each of the plurality of microscopic images, to classify each of the one or more sperm objects into one or more normal sperm objects and one or more abnormal sperm objects based on predetermined classification techniques; determine a differential count) of the one or more normal sperm objects and the one or more abnormal sperm objects; determine an aggregate count of the one or more non-sperm objects identified in each of the plurality of microscopic images; and computing, by the semen quality analysis system, a semen quality index based on the one or more morphological characteristics of each of the one or more sperm objects, the differential count of the one or more normal sperm objects and the one or more abnormal sperm objects, a total motility estimate of semen sample, and the aggregate count of the one or more non-sperm objects, for evaluating the quality of the semen sample.

8. The semen quality analysis system as claimed in claim 7, wherein the one or more predetermined conditions to analyze usability of each of the plurality of microscopic images comprises one of:

blur level in each of the plurality of microscopic images exceeding a predefined threshold blur value;
count of the sperm objects, the non-sperm objects and other objects, visibly present in each of the plurality of microscopic images, less than a predefined threshold count; and
staining proportion in each of the plurality of microscopic images exceeding a predefined threshold staining proportion.

9. The semen quality analysis system as claimed in claim 7, wherein the one or more morphological characteristics comprises at least one of texture of the sperm object, shape of the sperm object, and size of the sperm object.

10. The semen quality analysis system as claimed in claim 7, wherein the processor determines the total motility estimate of the semen sample prior to staining of the semen sample.

11. The semen quality analysis system as claimed in claim 7, wherein the one or more non-sperm objects comprises at least one of White Blood Cells (WBCs), Red Blood Cells (RBCs), spermatogonium cells, pathological casts, and one or more microbes.

12. The semen quality analysis system as claimed in claim 7, wherein the quality of the semen sample is directly proportional to the semen quality index of the semen sample.

Patent History
Publication number: 20200209221
Type: Application
Filed: Nov 24, 2017
Publication Date: Jul 2, 2020
Applicant: Sigtuple Technologies Private Limited (Bangalore)
Inventors: Karan DEWAN (Bangalore), Rahul Borule (Bangalore), Bharath Cheluvaraju (Bangalore), Tathagato Rai Dastidar (Bangalore), Apurv Anand (Bangalore)
Application Number: 15/753,219
Classifications
International Classification: G01N 33/50 (20060101); A61B 10/00 (20060101); G01N 33/49 (20060101); G01N 1/30 (20060101); G02B 21/34 (20060101);