Abstract: The present disclosure provides method and system for auto focusing a microscopic imaging system using machine learned regression system such as Convolutional Neural Network (CNN). The method comprises receiving a first image of a sample under review and a second image of sample wherein the first image is captured at first focus position and second image is captured at second focus position. The CNN is trained using the plurality of historic difference images along with direction of focus and optimal focus position. The difference of two images are obtained in terms of difference in pixel values. The direction of focus and optimal focus position for difference image is identified based on plurality of historic difference images along with direction of focus and optimal focus position. The method enables automated stage comprising sample to move towards direction of focus and position at optimal focus position for capturing a focused image.

Abstract: Embodiments of present disclosure discloses system and method for reconstruction of FOV. Initially, presence of one of single object and distinct objects in FOV of image of sample comprising one or more objects is determined based on sharpness of one or more objects. A single optimal representation of FOV may be generated when presence of single object is determined. At least one of single optimal representation and a depth-based enhanced representation of FOV may be generated when presence of distinct objects is determined. For generating depth-based enhanced representation, one or more first optimal images associated with each of distinct objects in FOV may be retrieved. An optimal representation of each of distinct objects is generated based on corresponding one or more first optimal images. Further, optimal representation of each of distinct objects is placed at corresponding optimal depth associated with respective distinct object to generate depth-based enhanced representation.

Abstract: The present disclosure provides method and system for auto focusing a microscopic imaging system using machine learned regression system such as Convolutional Neural Network (CNN). The method comprises receiving a first image of a sample under review and a second image of sample wherein the first image is captured at first focus position and second image is captured at second focus position. The CNN is trained using the plurality of historic difference images along with direction of focus and optimal focus position. The difference of two images are obtained in terms of difference in pixel values. The direction of focus and optimal focus position for difference image is identified based on plurality of historic difference images along with direction of focus and optimal focus position. The method enables automated stage comprising sample to move towards direction of focus and position at optimal focus position for capturing a focused image.

Abstract: Disclosed subject matter relates to Peripheral Blood Smear (PBS) that determines an area to be scanned in PBS for analysis. A PBS analysing system captures a focused image at each of plurality of positions in the PBS and determines Quality Indicators (QIs) in focused image. Further, a region is identified in PBS where QIs of focused image satisfy predefined QI threshold limits, as a monolayer region of PBS and determines an initiation point in monolayer region based on cell count value and co-ordinates of each of the plurality of positions located in the monolayer region. Finally, the area to be scanned in monolayer region is determined based on the initiation point and a predefined scan pattern. Determining the area to be scanned yields accurate and faster results.

Abstract: The present disclosure relates to a method and system for determining Total Count (TC) of RBCs in a Peripheral Blood Smear (PBS). The system receives a plurality of images from the monolayer of the PBS. Further, the system extracts, segments and identifies RBCs in each of the plurality of images using deep learning models. The system computes a value of each variable of a set of variables for each of the plurality of images. The set of variables includes foreground non-pallor area, density of RBCs, cell count, cell count ratio, foreground area and foreground hole-filled area. Furthermore, the system computes statistical parameters for each variable, over the plurality of images. The statistical parameters are provided as an input to supervised learning model, to determine TC of RBCs. Thus, the TC estimation system provides an efficient and robust method for estimating TC of RBCs using plurality of images of the PBS.

Abstract: The present disclosure relates to a method and system for determining Total Count (TC) of RBCs in a Peripheral Blood Smear (PBS). The system receives a plurality of images from the monolayer of the PBS. Further, the system extracts, segments and identifies RBCs in each of the plurality of images using deep learning models. The system computes a value of each variable of a set of variables for each of the plurality of images. The set of variables includes foreground non-pallor area, density of RBCs, cell count, cell count ratio, foreground area and foreground hole-filled area. Furthermore, the system computes statistical parameters for each variable, over the plurality of images. The statistical parameters are provided as an input to supervised learning model, to determine TC of RBCs. Thus, the TC estimation system provides an efficient and robust method for estimating TC of RBCs using plurality of images of the PBS.

Abstract: Embodiments of present disclosure discloses system and method for reconstruction of FOV. Initially, presence of one of single object and distinct objects in FOV of image of sample comprising one or more objects is determined based on sharpness of one or more objects. A single optimal representation of FOV may be generated when presence of single object is determined. At least one of single optimal representation and a depth-based enhanced representation of FOV may be generated when presence of distinct objects is determined. For generating depth-based enhanced representation, one or more first optimal images associated with each of distinct objects in FOV may be retrieved. An optimal representation of each of distinct objects is generated based on corresponding one or more first optimal images. Further, optimal representation of each of distinct objects is placed at corresponding optimal depth associated with respective distinct object to generate depth-based enhanced representation.

Abstract: Disclosed herein is method and system for determining quality of semen sample. Trajectories of objects, identified in each of plurality of image frames of semen sample, are generated by tracking movement of the objects across image frames, and compensating a drift velocity of the semen sample. Further, generated trajectories are classified into sperm and non-sperm trajectories. Finally, total concentration estimate and total motility estimate of the semen sample are computed to generate a semen quality index, which indicates quality of the semen sample. In an embodiment, the method of present disclosure uses a multi-level Convolutional Neural Network (CNN) analysis technique for effectively classifying the object trajectories into sperm and non-sperm objects. Also, since the present method includes estimating and compensating drift velocity in the semen sample, it enhances overall accuracy of motility estimation and semen quality analysis.

Abstract: Disclosed subject matter relates to Peripheral Blood Smear (PBS) that determines an area to be scanned in PBS for analysis. A PBS analysing system captures a focused image at each of plurality of positions in the PBS and determines Quality Indicators (QIs) in focused image. Further, a region is identified in PBS where QIs of focused image satisfy predefined QI threshold limits, as a monolayer region of PBS and determines an initiation point in monolayer region based on cell count value and co-ordinates of each of the plurality of positions located in the monolayer region. Finally, the area to be scanned in monolayer region is determined based on the initiation point and a predefined scan pattern. Determining the area to be scanned yields accurate and faster results.

Abstract: The present disclosure provides method and system for generating a structure map for retinal images. The system receives one or more retinal images and extracts or more structures in the retinal images. The system identifies one or more gradable retinal images among the one the retinal images. The system identifies one or more structure types and condition states in each of identified gradable retinal images based on extracted one or more structures and information associated with pre-learnt structures in pre-stored gradable retinal images using a Convolution Neural Network (CNN). The CNN is trained using information associated with pre-learnt structures in pre-stored gradable retinal images. The system generates structure map indicating one or more structure types for the gradable retinal images.

Abstract: 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.

Abstract: Embodiments of present disclosure discloses system and method for acquisition of optimal images of object in multi-layer sample. Initially, images for FOV of multi-layer sample comprising objects are retrieved. Each of images are captured by varying focal depth of image capturing unit associated with system. Further, objects associated with multi-layer sample in FOV are identified. For identification, cumulative foreground mask of FOV is obtained based on adaptive thresholding performed on foreground image of FOV. Based on contour detection performed on cumulative foreground mask of FOV, object masks, corresponding to objects, is obtained for identifying objects. Further, sharpness of each of images associated with each of object masks is computed. Based on sharpness, optimal images from images for each of objects is selected for acquisition of optimal images of objects in multi-layer sample.

Abstract: Embodiments of present disclosure discloses system and method for acquisition of optimal images of object in multi-layer sample. Initially, images for FOV of multi-layer sample comprising objects are retrieved. Each of images are captured by varying focal depth of image capturing unit associated with system. Further, objects associated with multi-layer sample in FOV are identified. For identification, cumulative foreground mask of FOV is obtained based on adaptive thresholding performed on foreground image of FOV. Based on contour detection performed on cumulative foreground mask of FOV, object masks, corresponding to objects, is obtained for identifying objects. Further, sharpness of each of images associated with each of object masks is computed. Based on sharpness, optimal images from images for each of objects is selected for acquisition of optimal images of objects in multi-layer sample.

Abstract: The embodiments herein provides a system and method for capturing images or videos observed through a microscope by focusing the image and selecting the appropriate field of view using a smart computing device or any device with a camera capable of capturing images or videos, being programmed and configured to communicate with at least one of the short range communication protocols. The smart computing device is attached to the eyepiece of the microscope. The image is captured by activating an application installed on the smart computing device and is displayed in a split screen view. The user is enabled to focus the image and select the appropriate field of view using the split screen image. The smart computing device communicates with a robot attached to the control knobs of the microscope for focusing the image and selecting the appropriate field of view.

Abstract: The state nodes in a sequential digital circuit are identified by identifying the minimal combinatorial feedback loops that are present in the digital circuit. Each minimal combinatorial feedback loop has at least one driver node, and one driver node from each minimal combinatorial feedback loop is assigned to be the state node for the loop.

Abstract: A method is provided for simulating a sequential digital circuit module given a set of input conditions and a current state for the circuit. The method comprises initiating all state nodes of the circuit module to logic values stored in the current state, initializing all sequential submodules of the circuit module to the states stored in the current state, simulating the circuit module after initialization, and after completion of the simulation step, reporting the output logic values and associated delays and storing the logic values of the state nodes and the states of the sequential modules in the next state in the circuit module, multiple value changes in the state nodes of the circuit module being recorded on the next state.

Abstract: An integrated circuit design simulation method is provided that takes advantage of the fact that, when an instance of a circuit module has been simulated under a given set of input conditions, and the resulting output values and delays have been evaluated, another instance of the same module need not be re-simulated when it has the same input combination as the prior circuit module instance. The results computed earlier for the earlier circuit module instance can be re-used for the current circuit module instance.

Abstract: Sequential digital integrated circuits have stable state nodes that are capable of retaining their state (logic value) even in the absence of any input directly driving these points. However, in addition to stable state nodes, some custom-designed digital circuits have so-called transient state nodes. A transient state node is defined as node that can directly affect the value of a stable state node and is combinatorially driven by inputs of the circuit, but the transition delay from at least one input to the node is greater than a predefined threshold value. Identifying such transient state nodes, along with the stable state nodes, is critical for the efficient simulation of custom digital circuits by a hierarchical device level digital simulator. A method is provided herein for identifying transient state nodes in a digital circuit, given the circuit's netlist and the identity of the stable state nodes in the circuit.

Abstract: A method for device level simulation of a circuit modeled by a set of CCR graphs, a computer system programmed to perform such a method, and a computer readable medium which stores code for implementing such a method. Typically, the circuit includes MOS transistors having unknown gate potentials, each CCR graph includes a top rail, and a bottom rail, and variable nodes, each of the transistors having unknown gate potential is modeled in the CCR graphs as a selectable resistor having a selected one of a first resistance and a much larger second resistance, and the method includes the steps of determining potentials at variable nodes of one of the CCR graphs with each selectable resistor of the graph having its first resistance (and also with each selectable resistor of the graph having its second resistance) without determining effective resistances between the variable nodes of the graph and the top rail or bottom rail.

Abstract: The quality assurance of all released runset files should ideally be 100% complete to ensure the best quality of the runsets. This means that the designs used for testing should be sufficient to test all of the design rules with the appropriate data in the runset to reach 100% coverage, which is not easy to ensure. The present invention provides a methodology that addresses this problem by quantitatively measuring the test coverage of backend verification runsets. The methodology not only reports the uncovered rules, but also assists the quality assurance engineers in locating reasons as to why those rules are not covered and how coverage can be improved by designing appropriate test cases.