Abstract: This application relates to an endoscopic image display method, apparatus, computer device, and storage medium, and relates to the field of machine learning technologies. The method acquiring an endoscopic image; locating a target region image in the endoscopic image, the target region image being a partial image comprising a target region; inputting the target region image into a coding network to obtain a semantic feature of the target region image, the coding network being a part of an image classification network, and the image classification network being a machine learning network obtained through training with first training images; matching the semantic feature of the target region image against semantic features of image samples to obtain a matching result, the matching result indicating a target image sample that matches the target region image; and displaying the endoscopic image and the matching result in an endoscopic image display interface.

Abstract: An integrated “home” based system to measure and report vital patient physiological data via telemedicine is disclosed. The integrated medical device is a personal, affordable, portable medical monitor, providing multiple critical vital sign data for real-time face-to-face communication with qualified health care professionals, direct from the comfort of your home (or wherever you may be travelling), whenever you need it. It is also linked to a secure patient medical record so the patient and/or healthcare professional can collect, archive and track information and trends.

Abstract: Vascular filtering devices and methods for their use are disclosed. In some embodiments, the vascular filtering devices include an elongate member having an unsupported membrane bag portion attached thereto. The membrane may be porous in some examples. Multiple elongate extensions may also extend from the membrane, and may extend along the elongate member, such as to a proximal region of the elongate member. The unsupported membrane bag portion may be configured to inflate or otherwise radially expand away from the elongate member as a result of blood flowing through the vessel within which the vascular filtering device is positioned.

Abstract: The present utility model discloses a camera assembly of a visual earpick, which comprises: a sleeve, a camera module and a light-emitting assembly, wherein a front end of the camera module is provided with a first convex step, and the light-emitting assembly is arranged on the first convex step; the camera module comprises a lens and a circuit board assembly, the circuit board assembly comprises a flexible circuit board, a fixed plate and a support plate, the fixed plate is arranged below the lens, one end of the support plate is vertically fixed below the fixed plate, a clamping groove is arranged at a lower part of an inner side of the sleeve, and the other end of the support plate is at least partially inserted into the clamping groove to limit and fix the circuit board assembly.

Abstract: Camera head apparatus, systems, and methods for providing wide angle/panoramic images and/or video of the interior of pipes or other cavities using multiple imaging and illumination modules are disclosed.

Abstract: A method for measuring glucose and cortisol levels in earwax, wherein the measured levels of cortisol and glucose are interpreted as the average cortisol and glucose levels and a medical device that provides an effective, safe and hygienic self-extraction of earwax.

Abstract: There is a need for more effective and efficient predictive data analysis solutions and/or more effective and efficient solutions for generating image representations of categorical/scalar data. Various embodiments of the present invention address one or more of the noted technical challenges. In one example, a method comprises receiving the one or more categorical input features; generating an image representation of the one or more categorical input features, wherein the image representation comprises image region values each associated with a categorical input feature, and further wherein each image region value of the one or more image region values is determined based at least in part on the corresponding categorical input feature associated with the image region value; and processing the image representation using an image-based machine learning model to generate the image-based predictions.

Abstract: An optical device is provided. An optical device according to one aspect of the present invention comprises: a first main body including a first hole; a second main body including a second hole and connected to the first main body in a foldable manner; a sensor module disposed to be fixed to the first hole; a lens module disposed to be movable in the optical axis direction atop the sensor module; and a transparent member disposed in the second hole, wherein the lens module is disposed in the first hole when the first main body and the second main body are folded, and at least a part of the lens module is disposed over the first hole when the first main body and the second main body are unfolded.

Abstract: A disposable speculum for an otoscope provides a sheath adapted to cover an elongate otoscope probe and providing inwardly extending tabs that are adapted to flex outward when the speculum is inserted over the otoscope to engage corresponding grooves of the otoscope. The inwardly extending tabs provide precise alignment of the speculum with the elongate otoscope probe along an insertion axis to protect a length of the probe.

Abstract: An otoscope includes an instrument head, a tip element and an optical system. The instrument head has a distal insertion portion for insertion into an ear of a human or veterinary subject. The distal insertion portion has a distal opening. The tip element is releasably attached to the distal insertion portion. The tip element has a distal opening. The optical system is contained within the instrument head. The optical system includes a plurality of optical components. The optical system further comprises a viewing component for viewing of an image of a target of interest aligned along an optical axis disposed within said distal opening. The optical system is configured to provide a field of having a diameter equaling at least 7 mm at a distance of at least 15 mm from a distal opening of said attached tip element. The optical system is further configured to simultaneously provide a distance range of optimal focus having a range of at least 8 mm.

Abstract: Devices, systems, and methods can be employed to facilitate indirect viewing into cavities such as, but not limited to, the middle ear space. Some embodiments have uses such as, but not limited to, facilitating visualization and procedures in the outer, middle, and/or inner ear in order to diagnose and/or treat disorders including, but not limited to, hearing loss and other ear disorders. In particular implementations, a surgical microscope is used in conjunction with an inverter lens and a distal lens. In some cases, the distal lens transverses a membrane or septum such as, but not limited to, the tympanic membrane. The distal lens can be an assembly combining two or more lenses, in some embodiments. For example, in some cases wide angle lenses, zoom lenses, lenses of other various shapes and/or prisms can be used in the distal lens.

Abstract: An ear examination tool comprises a handle and a speculum mount coupled to the handle. The speculum mount is configured for retaining a disposable speculum. An spacing element is coupled to the handle and extends from the handle. A smartphone mount is coupled to the spacing element, and the spacing element is configured to maintain an optical separation distance between the speculum mount and the smartphone mount. The tool enables a clear view of the ear canal while allowing access by, and manipulation of, a microsuction tool being inserted into the ear canal. The extensive optical and data processing functionality of a “smartphone” can be integrated at low cost into an ear examination tool to provide a substantially improved piece of equipment for assisting in ear examination and microsuction of the ear.

Abstract: A control apparatus includes a first acquiring unit configured to acquire a hyperfocal length of a lens apparatus that is attachable to, detachable from, and communicable with an image pickup apparatus, using information acquired by communication between the lens apparatus and the image pickup apparatus, and a second acquiring unit configured to acquire a position of a focus lens in the lens apparatus according to the hyperfocal length.

Abstract: A device is described that can include a probe, a mobile device, and at least one processor. The probe can examine a corresponding anatomical part of a body. The mobile device can have a camera to take an image of the anatomical part of the body. The mobile device can execute a patient-application to process the image. The at least one processor can be configured to transmit the processed image to a server via a communication network. Related apparatuses, systems, methods, techniques and articles are also described.

Abstract: To simplify the use of a functional scope of a medical image recording system, for example an endoscopy system, a method is proposed in which an image processing unit of the image recording system recognizes predefined image recording situations on the basis of an image sequence recorded using an image sensor of the image recording system and in response thereto proposes an adaptation to a user that results in an improved display and/or an improved recording of the image sequence in the respective recognized image recording situation. The adaptation can relate here to an algorithm, using which the image sequence is processed after the recording, and/or an image recording method currently used to generate the image sequence.

Abstract: An endoscope may include a needle and a scope, which may optionally be contained in an elongated shaft. The endoscope may further include a handle comprising at least one button, a visualization component, a reservoir configured to contain a composition, and a dispensing mechanism. The at least one button, the needle, the reservoir, and the dispensing mechanism may be operably linked to cause the composition to be dispensed from the reservoir through the needle to a portion of an ear. A method for using such an endoscope may include inserting the endoscope into a portion of an ear, using the visualization component to visualize the portion of the ear, and pressing the at least one button to dispense the composition from the reservoir through the needle to the portion of the ear.

Abstract: A roll-detecting sensor assembly includes a coil extending along and disposed about an axis. The coil comprises one or more portions, with each portion defining a winding angle. At least one of the portions defines a winding angle that is substantially nonzero relative to a line perpendicular to the axis, whereby the projected area of the coil in an applied magnetic field changes as the coil rotates about the axis. As a result, the coil is configured to produce a signal responsive to the magnetic field indicative of the roll of the sensor about the axis. In an embodiment, at least one of the portions defines a winding angle that is at least 2 degrees. In an embodiment, at least one of the portions defines a winding angle that is about 45 degrees.

Abstract: There is a need for more effective and efficient predictive data analysis solutions and/or more effective and efficient solutions for generating image representations of categorical/scalar data. Various embodiments of the present invention address one or more of the noted technical challenges. In one example, a method comprises receiving the one or more categorical input features; generating an image representation of the one or more categorical input features, wherein the image representation comprises image region values each associated with a categorical input feature, and further wherein each image region value of the one or more image region values is determined based at least in part on the corresponding categorical input feature associated with the image region value; and processing the image representation using an image-based machine learning model to generate the image-based predictions.

Abstract: An ear ailment diagnostic device generally comprises a pair of earpieces, which both further comprise a light source, a magnification lens, an air conduction channel and a miniature camera. The earpieces may optionally comprise a thermometer and/or tympanometer. Each earpiece is coupled to an air conduction tube, an insufflator and an electrical wiring/data tube which is coupled to a computer. The insufflator may be manually, electronically, or battery powered. In the preferred embodiment the computer comprises a smart phone with data processing capability and wireless communication capability. Any data sent from the device can then be interpreted and diagnosed in a remote location so that an accurate treatment is prescribed.

Abstract: A computer-implemented method and a corresponding system for context-sensitive white balancing for a stereomicroscope are presented. The method comprises recording a first digital image by way of a first camera in a first optical path of the stereomicroscope, and recording a second digital image by way of a second camera in a second optical path of the stereomicroscope. Furthermore, the method comprises determining, by means of a trained machine learning system, the context identified in the images, and determining, by means of the trained machine learning system, camera parameters suitable for controlling color channels of the first and second cameras for white balancing.

Abstract: Camera head apparatus, systems, and methods for providing wide angle/panoramic images and/or video of the interior of pipes or other cavities using multiple imaging and illumination modules are disclosed.

Abstract: There is a need for more effective and efficient predictive data analysis solutions and/or more effective and efficient solutions for generating image representations of categorical/scalar data. Various embodiments of the present invention address one or more of the noted technical challenges. In one example, a method comprises receiving the one or more categorical input features; generating an image representation of the one or more categorical input features, wherein the image representation comprises image region values each associated with a categorical input feature, and further wherein each image region value of the one or more image region values is determined based at least in part on the corresponding categorical input feature associated with the image region value; and processing the image representation using an image-based machine learning model to generate the image-based predictions.

Abstract: An otoscope, comprising: (a) a flexible speculum, operable to be inserted into an ear canal; (b) a stopper, coupled to the flexible speculum, operable to limit penetration depth of the flexible speculum into the ear canal; and (c) an imaging sensor, located inside the flexible speculum, operable to capture an image of an eardrum of the ear canal; wherein a flexibility of the flexible speculum allows alignment of the imaging sensor according to a shape of the ear canal.

Abstract: There is a need for more effective and efficient predictive data analysis solutions and/or more effective and efficient solutions for generating image representations of categorical/scalar data. Various embodiments of the present invention address one or more of the noted technical challenges. In one example, a method comprises receiving the one or more categorical input features; generating an image representation of the one or more categorical input features, wherein the image representation comprises image region values each associated with a categorical input feature, and further wherein each image region value of the one or more image region values is determined based at least in part on the corresponding categorical input feature associated with the image region value; and processing the image representation using an image-based machine learning model to generate the image-based predictions.

Abstract: There is a need for more effective and efficient predictive data analysis solutions and/or more effective and efficient solutions for generating image representations of categorical/scalar data. Various embodiments of the present invention address one or more of the noted technical challenges. In one example, a method comprises receiving the one or more categorical input features; generating an image representation of the one or more categorical input features, wherein the image representation comprises image region values each associated with a categorical input feature, and further wherein each image region value of the one or more image region values is determined based at least in part on the corresponding categorical input feature associated with the image region value; and processing the image representation using an image-based machine learning model to generate the image-based predictions.

Abstract: An enhanced optical design for imaging of live human tissue as a supplemental attachment to wireless mobile devices such as smartphones. The improved imaging system includes a series of optical ball lenses coupled to a medical-grade light source to allow universal compatibility to mobile device (e.g., smartphone) cameras. The releasable optical attachment comprises optical enhancement elements allowing universal compatibility without the need of an application or special program to re-orient the image therein permitting less loss of picture acuity and blanket usability to HIPAA-verified smartphone applications used in hospitals and patient's electronic health records. The addition of an external light source and light-redirecting elements negates the need for a smartphone light source or smartphone re-programming to illuminate target.

Abstract: A video image segmentation method includes: obtaining an image segmentation model by performing machine learning based on a historical video image and a mask image of the historical video image; adjusting the image segmentation model based on an initial frame of an image to be segmented, a previous frame of a frame to be segmented and a mask image of the previous image; and performing segmentation on the image to be segmented using the image segmentation model after the adjusting.

Abstract: A device for visualizing and providing suction for a surgical procedure in an ear may include a handle, a main shaft extending from the handle, an imaging sensor at a distal end of the main shaft, a light source at the distal end of the main shaft, and a suction shaft extending from the handle. The device may also include a spring coupled with the suction shaft and/or the handle, such that when the suction shaft is advanced in a distal direction and then released, the suction shaft retracts automatically. The suction shaft may have a distal curved portion, and the device may have a thumb depress portion that allows a user to spin the suction shaft to suction in different directions. Some embodiments may include a suction shaft with a sharp distal tip that is configured for placing an ear tube in the tympanic membrane.

Abstract: The present invention relates to an otoscope for illuminating the outer ear and to methods of using the otoscope. In one embodiment, the otoscope includes a handle including a light source; and a speculum extending relative to the handle for directing light from the light source to illuminate the outer ear; wherein the speculum includes a lens for magnifying the outer ear, or a lens engager for releaseably engaging a lens.

Abstract: A disposable speculum for an otoscope provides a sheath adapted to cover an elongate otoscope probe and providing inwardly extending tabs that are adapted to flex outward when the speculum is inserted over the otoscope to engage corresponding grooves of the otoscope. The inwardly extending tabs provide precise alignment of the speculum with the elongate otoscope probe along an insertion axis to protect a length of the probe.

Abstract: There is described an apparatus comprising a first optical element, a second optical element and a spacing element for use with a mobile user device. The first optical element is configured to provide an image of an object to an intermediate image plane and the second optical element magnifies the image to provide a final image in a final image plane in which a camera aperture of the device is supported. The spacing element maintains a fixed separation between the object and the first optical element. Image magnification is achieved while also providing a space for tool access. Mirrors may be used to divert the optical path, allowing the optical path to be folded for more compact apparatus. A third optical element disposed at the intermediate image plane may be used to reduce vignetting effects in the final image.

Abstract: An embolic coil with a secondary, delivered shape utilizing regions of varying stiffness is described. In some embodiments, these regions of varying stiffness are created by utilizing a larger primary wind loop diameter to create selective regions with lower stiffness and higher flexibility. In some embodiments, these regions of higher flexibility correspond to inflection regions on a complex coil shape to ease deliverability of the coil during therapeutic procedures.

Abstract: Methods, systems, and apparatus for efficiently performing a computation of a convolutional neural network layer. One of the methods includes transforming a X by Y by Z input tensor into a X? by Y? by Z? input tensor; obtaining one or more modified weight matrices, wherein the modified weight matrices operate on the X? by Y? by Z? input tensor to generate a U? by V? by W? output tensor, and the U? by V? by W? output tensor comprises a transformed U by V by W output tensor; and processing the X? by Y? by Z? input tensor using the modified weight matrices to generate the U? by V? by W? output tensor, wherein the U? by V? by W? output tensor comprises the U by V by W output tensor.

Abstract: An image processing method performed by a computer, the method including: changing a rendering parameter in a three-dimensional model of a recognition target; and generating teacher data of the recognition target based on the rendering parameter changed by the changing. Thereby, sufficient amount of teacher data can be obtained, without any unfavorable redundancy.

Abstract: An otoscope speculum can include forceps, a curette, or other instruments to allow healthcare providers to treat a patient while observing thought the otoscope lens. According to some embodiments, a flexible hinge on an otoscope speculum orients forceps jaws and allows the healthcare provider to close the forceps jaws by applying a squeezing force. In other embodiments, a curette on an otoscope speculum allows the healthcare provider to perform scraping operations on a patient. Embodiments of the present disclosure may be used to examine and/or treat a variety of orifices of a patient, including the ear. The various specula instruments may allow the healthcare provider to view the treatment through the otoscope lens while the instrument is in use.

Abstract: A medical otoscope, comprises an otoscope body and an observation apparatus connected to one end of the otoscope body, the other end of the otoscope body having a tapered portion capable of inserting into an ear, the observation apparatus comprising at least one optical lens group arranged along a same optical axis, the optical lens group comprising at least one optical lens capable of moving along the optical axis, central axis of the observation apparatus being coaxial with or deviating from central axis of the otoscope body. The focal length of the medical otoscope can be adjusted by means of arranging two groups of optical lenses movable relative to one another, and the medical otoscope has a simple structure and is convenient for operation.

Abstract: Provided are a medicine audit apparatus, a medicine audit method, and a program capable of detecting a state where recognition of a medicine is impossible from a captured image obtained by imaging the medicine and urging a user to pay attention in the case of the state where the medicine recognition is impossible.

Abstract: Methods, systems, and apparatus for efficiently performing a computation of a convolutional neural network layer. One of the methods includes transforming a X by Y by Z input tensor into a X? by Y? by Z? input tensor, wherein X? is smaller than or equal to X, Y? is smaller than or equal to Y, and Z? is larger than or equal to Z; obtaining one or more modified weight matrices, wherein the modified weight matrices operate on the X? by Y? by Z? input tensor to generate a U? by V? by W? output tensor, and the U? by V? by W? output tensor comprises a transformed U by V by W output tensor; and processing the X? by Y? by Z? input tensor using the modified weight matrices to generate the U? by V? by W? output tensor.

Abstract: Mechanisms are provided to implement a neural network, a concept extractor, and a machine learning model that operate to provide automatic contour annotation of medical images based on correlations with medical reports. The neural network processes a medical image to extract image features of the medical image. The concept extractor processes a portion of text associated with the medical image to extract concepts associated with the portion of text. The machine learning model correlates the extracted image features with the extracted concepts. An annotated medical image is generated based on the correlation of the extracted image features and extracted concepts. An annotation of the annotated medical image specifies a region of interest corresponding to both an extracted image feature and an extracted concept, thereby automatically mapping the portion of text to a relevant region of the medical image.

Abstract: Light-field data is masked to identify regions of interest, before applying to deep learning models. In one approach, a light-field camera captures a light-field image of an object to be classified. The light-field image includes a plurality of views of the object taken simultaneously from different viewpoints. The light-field image is pre-processed, with the resulting data provided as input to a deep learning model. The pre-processing includes determining and then applying masks to select regions of interest within the light-field data. In this way, less relevant data can be excluded from the deep learning model. Based on the masked data, the deep learning model produces a decision classifying the object.

Abstract: This invention provides a method for obtaining ear drum standard image and the design of related otoscope and software, which includes the following steps: First, moving an otoscope with a circle sight to a target position in ear canal, and capturing an ear drum image; Then, choosing an ear drum region from the ear drum image, and calculating an area overlapping between the circle sight and the ear drum region. If the area does not satisfy a standard value, moving the otoscope to another target position, and repeating above steps; otherwise, choosing the ear drum image to be an ear drum standard image.

Abstract: In an aspect, a device-and-clip system is provided for an electronic device. The system includes an external device that cooperates with at least one electronic device feature on the rear face to perform a selected function. The system includes a clip including a first clip arm having an arm marker thereon and which is engageable with the front face of the electronic device and a second clip arm that is engageable with the rear face of the electronic device. The system further includes an application that is executable to instruct the electronic device to display a screen marker on the display screen in a selected position and in a selected orientation such that positioning and orienting of the first clip arm on the display screen of the smart phone with the arm marker aligned with the position and orientation of the screen marker positions the external device in alignment with the at least one electronic device feature.

Abstract: A thermal powered medical device generates power from a temperature differential between a living body and a differential temperature source. The power is supplied to power one or more electrical components of the medical device.

Abstract: A device to correct an image blur within a medical image is described. An image analysis application executed by the device receives the medical image from a medical image provider. Next, the image blur is detected within the medical image by analyzing the medical image. The medical image is subsequently processed with a deep learning model to correct the image blur. In response to the processing, a de-blurred medical image is generated. The de-blurred medical image is provided for a presentation or a continued analysis.

Abstract: Eardrums are automatically classified based on a feature set from a three-dimensional image of the eardrum, such as might be derived from a plenoptic image captured by a light field otoscope. In one aspect, a grid is overlaid onto the three-dimensional image of the eardrum. The grid partitions the three-dimensional image into cells. One or more descriptors are calculated for each of the cells, and the feature set includes the calculated descriptors. Examples of descriptors include various quantities relating to the depth and/or curvature of the eardrum. In another aspect, isocontour lines (of constant depth) are calculated for the three-dimensional image of the eardrum. One or more descriptors are calculated for the isocontour lines, and the feature set includes the calculated descriptors. Examples of descriptors include various quantities characterizing the isocontour lines.

Abstract: An otoscopic instrument includes an instrument housing having a distal end and an opposing proximal end, each end defining a viewing axis of the instrument. A laser light source is disposed in relation to the viewing axis. At least one optical element is configured to direct emitted light from the laser light source toward a target of interest through the distal end of the instrument housing and in which reflected laser light is directed toward the proximal end along the viewing axis. The laser light source can be contained within a releasably attachable laser module to selectively permit separate white light and laser viewing modes of the instrument.

Abstract: An otoscope comprises a handle portion and a head portion tapering along its longitudinal axis. The head portion has a proximal end adjacent the handle portion and a smaller distal end adapted to be introduced in an ear canal of a patient's outer ear. The otoscope further comprises an electronic imaging unit positioned at the distal end of the head portion, and a probe cover moving mechanism configured to move at least a portion of an at least partially transparent probe cover adapted to be put over the head portion, especially configured to move the probe cover with respect to at least one optical axis of the electronic imaging unit. The present invention further refers to a probe cover for such an otoscope and to a method of identifying objects in a subject's ear.

Abstract: This document provides vascular filtering devices and methods for their use. In some embodiments, the vascular filtering devices include an elongate member having a wall with one or more apertures and a lumen. The vascular filtering devices can also include a porous membrane bag portion with multiple elongate extensions that extend through the apertures of the elongate member and through the lumen of the elongate member, exiting the lumen at the proximal region of the elongate member.

Abstract: Applicator for delivering an occluding compound in a fallopian tube includes a lumen extending between a proximal end connectable to a dispenser for containing uncured occluding compound, and a distal end. A spiral wire with a first end is connected to the distal end of the lumen and a free second end. A disconnecting member is configured to disconnect the spiral wire from the distal end. An actuator is configured to actuate the disconnecting member. The distal end of the lumen can be inserted into the fallopian tube. The spiral wire functions as a guide wire. The curable compound embeds the spiral wire. The actuator can be actuated to disconnect the embedded spiral wire from the distal end of the lumen.

Abstract: A medical diagnostic instrument includes a housing having an interior, a distal end and an opposing proximal end. A supporting member is disposed within the interior of the housing, and supports a plurality of LEDs. A light guide made from a light transmissive material is distally disposed in relation to the LED supporting member for transmitting light emitted by the plurality of LEDs through the distal end of the housing. In at least one version, at least one end of the light guide can be provided with a patterned surface that is configured to produce a uniform illumination spot.