Abstract: A computing system for wound tracking is disclosed herein. A server computing device receives a first image of a wound of a patient captured by a first camera. Subsequently, the server computing device receives a message generated by a computing device, the message indicating that a second camera of the computing device is to capture a second image of the wound. Responsive to receiving the message, the server computing device causes data to be transmitted to the computing device, the data based in part upon the first image. The data causes the computing device to present a semi-transparent overlay to a view of the wound on a display as perceived through a lens of the second camera, the semi-transparent overlay indicative of the first image. The computing device captures the second image via the second camera and causes the second image to be received by the server computing device.

Abstract: The present solution can segment tracts by performing two-pass tractography. The system can first perform deterministic tractography and then probabilistic tractography. The system can use the result from the deterministic tractography to update and refine initial identified regions of interest. The refined regions of interest can be used to filter and select streamlines identified through the probabilistic tractography.

Abstract: A framework for anatomy-aware adaptation of a graphical user interface. Landmarks are first detected by passing one or more current images through a trained machine learning model. A body section may then be inferred based on the detected landmarks. One or more user interface elements may be determined based on the inferred body section. A graphical user interface may then be adapted with the determined one or more user interface elements.

Abstract: A method of identifying and quantifying calcified regions of a tissue including obtaining an image of a cross-section of the tissue, wherein the image distinguishes between calcified regions and non-calcified regions of the cross-section of the tissue. Also disclosed are methods of detecting a change in size of a calcified region of a tissue over time including identifying and quantifying a first size of the calcified region of the tissue at a first time, identifying and quantifying a second size of the corresponding calcified region of the tissue at a second time, and detecting a change in size between the first and second size of the calcified region of the tissue in the image of a cross-section of the tissue. Some aspects relate to computer software program configured to construct a panoramic image from partial images, quantify RGB values for each pixel in the panoramic image, and calculate the total pixels of calcified and uncalcified regions and a calcification ratio.

Abstract: The subject disclosure presents systems and methods for automatically selecting meaningful regions on a whole-slide image and performing quality control on the resulting collection of FOVs. Density maps may be generated quantifying the local density of detection results. The heat maps as well as combinations of maps (such as a local sum, ratio, etc.) may be provided as input into an automated FOV selection operation. The selection operation may select regions of each heat map that represent extreme and average representative regions, based on one or more rules. One or more rules may be defined in order to generate the list of candidate FOVs. The rules may generally be formulated such that FOVs chosen for quality control are the ones that require the most scrutiny and will benefit the most from an assessment by an expert observer.

Abstract: Systems and methods of enhancing images use a contrast limited adaptive histogram equalization (CLAHE) algorithm in a field programmable gate array (FPGA). The images may be obtained by the imaging elements of a multiple imaging elements endoscope of an endoscopy system.

Abstract: Disclosed herein are cell differentiating systems for differentiating cells. The systems comprise an input means for receiving a reconstructed image of a cell based on a holographic image of the cell in suspension, and a cell recognition means for determining cell characterization features from the reconstructed image of the cell for characterization of the cell. The cell recognition means thereby is configured for determining, as cell recognition features, image moments.

Abstract: Methods, systems, and media for segmenting images are provided. In some embodiments, the method comprises: generating an aggregate U-Net comprised of a plurality of U-Nets, wherein each U-Net in the plurality of U-Nets has a different depth, wherein each U-Net is comprised of a plurality of nodes Xi,j, wherein i indicates a down-sampling layer the U-Net, and wherein j indicates a convolution layer of the U-Net; training the aggregate U-Net by: for each training sample in a group of training samples, calculating, for each node in the plurality of nodes Xi,j, a feature map xi,j, wherein xi,j is based on a convolution operation performed on a down-sampling of an output from Xi?1,j when j=0, and wherein xi,j is based on a convolution operation performed on an up-sampling operation of an output from Xi+1,j?1 when j>0; and predicting a segmentation of a test image using the trained aggregate U-Net.

Abstract: A fingerprint sensing module including an image sensor, a microlens array and a light-shielding layer is provided. The image sensor has multiple pixels. Each of the pixels has multiple light-sensing regions physically separated. Each of the light-sensing regions is adapted to receive an image beam coming from a fingerprint of user. The microlens array is disposed above the image sensor. The microlens array includes multiple microlens. A focus region of each of the microlens covers a portion of the light-sensing regions. The light-shielding layer is disposed between the image sensor and the microlens array. The light-shielding layer has multiple openings, and the positions of the openings are corresponded to the positions of the pixels.

Abstract: A system and method for validating the accuracy of delineated contours in computerized imaging using statistical data for generating assessment criterion that define acceptable tolerances for delineated contours, with the statistical data being conditionally updated and/or refined between individual processes for validating delineated contours to thereby adjust the tolerances defined by the assessment criterion in the stored statistical data, such that the stored statistical data is more closely representative of a target population. In an alternative embodiment, a system and method for validating the accuracy of delineated contours in computerized imaging using machine learning for assessing delineated contours, with the machine learning training data being used to generate geometric attributes, and the geometric attributes used to construct intra- and interstructural geometric attribute distribution models to automatically detect contouring errors.

Abstract: A system for computer-aided triage includes and/or interfaces with a computing system. A method for computer-aided triage includes receiving a data packet including a set of images; and processing the set of images to determine a suspected condition and/or associated features. Additionally or alternatively, the method can include any or all of: preprocessing the set of images; triggering an action based on the suspected condition and/or associated features; determining a recipient based on the suspected condition; preparing a data packet for transfer; transmitting information to a device associated with the recipient; receiving an input from the recipient and triggering an action based on the input; aggregating data; and/or any other suitable processes.

Abstract: A learning model preparation method includes: acquiring a non-specific binding specimen image representing a non-specific binding specimen that allows a reagent to act on a tissue containing the endogenous protein, the reagent developing a color in a non-specific binding region in which an endogenous protein exists; and preparing a first learning model by setting the non-specific binding specimen image to first learning data, and by allowing a learning device to learn the non-specific binding region, based on the first learning data.

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: As saturation enhancement processing, first saturation enhancement processing or second saturation enhancement processing different from the first saturation enhancement processing is executed. A high saturation range Ry(rc)Ry(r2) after the second saturation enhancement processing is greater than a high saturation range Rx(rc)Rx(r2) after the first saturation enhancement processing. A value Ry(r) included in the high saturation range Ry(rc)Ry(r2) after the second saturation enhancement processing is smaller than a value Rx(r) included in the high saturation range Rx(rc)Rx(r2) after the first saturation enhancement processing.

Abstract: Presented herein are systems and methods that provide for improved 3D segmentation of nuclear medicine images using an artificial intelligence-based deep learning approach. For example, in certain embodiments, the machine learning module receives both an anatomical image (e.g., a CT image) and a functional image (e.g., a PET or SPECT image) as input, and generates, as output, a segmentation mask that identifies one or more particular target tissue regions of interest. The two images are interpreted by the machine learning module as separate channels representative of the same volume. Following segmentation, additional analysis can be performed (e.g., hotspot detection/risk assessment within the identified region of interest).

Abstract: Implementations relate to visualizations including images based on image content. In some implementations, a computer-implemented method includes obtaining a set of images, determining one or more pixel characteristics of the set of images, and determining one or more faces depicted in the plurality of images based on one or more pixel characteristics. The method selects a group of images of the set of images, where each image in the group of images depicts a different group of faces than depicted in the other images in the set of images. The method generates a visualization including the group of images, and provides the visualization to a user device in response to a user request to cause the group of images to be displayed by the user device.

Abstract: A method and system for predicting liver injury in vivo due to hepatocyte damage by a test compound are provided. The method includes acquiring images of fluorescently stained cells obtained from a cell culture in which the cells have been treated with a dose-range of at least the test compound and its vehicle. The cells may be hepatic cells including primary or immortalized hepatocytes, hepatoma cells or induced pluripotent stem cell-derived hepatocyte-like cells. The acquired images are segmented. The method further includes extracting and analyzing one or more phenotypic features from the segmented images, wherein the one or more phenotypic features are selected from the group of intensity, textural, morphological, or ratiometric features consisting of (a) features of DNA, (b) features of RELA (NF-KB p65), and (c) features of actin filaments at different subcellular regions and d) features of cellular organelles and their substructures in the segmented images.

Abstract: A lesion tracking system is operable to receive a first medical scan and second medical scan associated with a patient ID. A lesion area calculation is performed on a first subset of image slices determined to include a lesion detected in the first medical to generate a first set of lesion area measurements. The lesion area calculation is performed on a second subset of image slices determined to include the lesion in the second medical scan to generate a second set of lesion area measurements. A lesion volume calculation is performed on the first set of lesion area measurements and the second set of lesion area measurements to generate a first lesion volume measurement and a second lesion volume measurement, respectively, and the first and second lesion volume measurements are utilized to calculate a lesion volume change for transmission to a client device for display via a display device.

Abstract: In order to assess, with high accuracy, a degree of a change having occurred in a structure, the present invention includes: a Betti number calculating section (42) configured to (I) generate, with respect to a single captured image obtained by capturing an image of a structure, a plurality of binarized images having respective binarization reference values different from each other and (II) calculate, for each of the plurality of binarized images, a first characteristic numerical value indicative of the number of connected regions each of which is obtained by connecting pixels each having one of pixel values obtained by binarization; and a prediction score determining section (44) configured to determine, in accordance with a result of a comparison, information on a change having occurred in the structure, the comparison having been made between (i) a pattern indicative of a relationship between (a) the respective binarization reference values and (b) the first characteristic numerical value and (ii) a prede

Abstract: Disclosed is a computer-implemented medical data processing method for determining an orientation of an electrode, the electrode being configured for electrically stimulating an anatomical structure of a patient and comprising a rotational orientation marker, the method comprising executing, on at least one processor of at least one computer, steps of: a) acquiring (S1.1), at the at least one processor, rotational image data describing two-dimensional medical images of the anatomical structure and the electrode, the two-dimensional medical images having been taken with a two-dimensional medical imaging apparatus during rotation of the medical imaging apparatus relative to the anatomical structure, the rotational image data further describing, for each of the two-dimensional medical images, an imaging perspective relative to the anatomical structure associated with the respective two-dimensional medical image; b) determining (S1.

Abstract: An image detection method includes determining, by a terminal in a skin detection mode, a to-be-detected original image in a raw format based on a to-be-detected feature, processing the to-be-detected original image according to a preset rule corresponding to the to-be-detected feature to obtain a detection-specific image, determining a normal image that is in a Joint Photographic Experts Group (JPEG) format, detecting the detection-specific image to determine a detection result image, and determining a to-be-displayed image based on the detection result image and the normal image.

Abstract: An image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry is configured to obtain three-dimensional image data of a brain acquired by performing a magnetic resonance imaging process. The processing circuitry is configured to generate a projection image rendering a micro bleed or calcification occurring in the brain by performing a projecting process on the three-dimensional image data in a range limited on the basis of a shape of the brain. The processing circuitry is configured to output the projection image.

Abstract: In this patent disclosure, a machine-learning-based system for automatically turning on/off a light source of an endoscope camera during a surgical procedure to ensure the safety of the surgical staff is disclosed. The disclosed system can receive a real-time video image captured by the endoscope camera, wherein the real-time video image is captured either inside the patient's body or outside of the patient's body. The system next processes the real-time video image using a first statistical classifier to classify the real-time video image as either being inside the patient's body or being outside of the patient's body. If the real-time video image is classified as being outside of the patient's body, the system next determines if the light source is turned on. If so, the system generates a control signal to immediately turn off the light source. Otherwise, the system continues receiving and processing real-time video images captured by the endoscope camera.

Abstract: A method for analyzing an image, called analysis image, of a dental arch of a patient. The analysis image is submitted to a deep learning device in order to determine at least one value of a tooth attribute relating to a tooth represented on the analysis image, and/or at least one value of an image attribute relating to the analysis image.

Abstract: A method of fundus oculi image analysis includes acquiring a target fundus oculi image; analyzing the target fundus oculi image by a fundus oculi image analysis model determined by training to acquire an image analysis result of the target fundus oculi image; and the fundus oculi image analysis model includes at least one of an image overall grade prediction sub-model and an image quality factor sub-model. The method performs quality analysis on the target fundus oculi image by the fundus oculi image analysis model, and when the model includes the overall grade prediction sub-model, a prediction result of whether the target fundus oculi image as a whole is gradable can be acquired; when the model includes the image quality factor sub-model, the analysis result of the fundus oculi image quality factor can be acquired and the image analysis model is determined by extensive image training, and the reliability of the result of whether the image is gradable determined based on the above model is high.

Abstract: A framework for automatically finding an organ in image data. In accordance with one aspect, a predetermined view of the organ is approximated by transforming the original image data to generate transformed image data. A best-match region in the transformed image data that best matches a synthesized geometric shape may then be found. The best-match region may be transformed into a volume space of the original image data to generate a location of the organ.

Abstract: A system includes a structural imaging acquisition unit, a functional imaging acquisition unit, and one or more processors. The structural imaging acquisition unit is configured to perform a structural scan to acquire structural imaging information of a patient. The functional imaging acquisition unit is configured to perform a functional scan to acquire functional imaging information of a patient.

Abstract: The disclosure features methods that include exposing a biological sample to illumination light and measuring light emission from the sample to obtain N sample images, where each sample image corresponds to a different combination of a wavelength band of the illumination light and one or more wavelength bands of the light emission, where the one or more wavelength bands of the light emission define a wavelength range, and where N>1, and exposing the sample to illumination light in a background excitation band and measuring light emission from the sample in a background spectral band to obtain a background image of the sample, where the background spectral band corresponds to a wavelength within the wavelength range.

Abstract: Methods and Systems for generating a centerline for an object in an image and computer readable medium are provided. The method includes receiving an image containing the object. The method also includes generating the centerline of the object by tracing a sequence of patches with a virtual agent. For each patch other than the initial patch, the method determines a current patch based on the position and action of the virtual agent at a previous patch. The method further determines a policy function and a value function based on the current patch using a trained learning network, which includes an encoder followed by a first learning network and a second learning network. The learning network is trained by maximizing a cumulative reward. The method also determines the action of the virtual agent at the current patch. Additionally, the method displays the centerline of the object.

Abstract: Systems and methods for reducing false positive detections of malignant lesions are provided. A candidate malignant lesion is detected in one or more medical images, such as, e.g., multi-parametric magnetic resonance images. One or more patches associated with the candidate malignant lesion are extracted from the one or more medical images. The candidate malignant lesion is classified as being a true positive detection of a malignant lesion or a false positive detection of the malignant lesion based on the one or more extract patches using a trained machine learning network. The results of the classification are output.

Abstract: A system for generating a bullseye plot of a heart of a subject is provided. The system may obtain multiple slice images in a plurality of groups, wherein each group corresponds to one of a plurality of sections of the heart and includes at least one slice image of the corresponding section, and each slice image includes part of the right ventricle, part of the left ventricle, and part of the myocardium. The system may also identify at least one landmark associated with the left ventricle by applying a landmark detection network in each of the slice images. The system may further generate the bullseye plot of the heart based on the at least one landmark identified in each of the multiple slice images, wherein the bullseye plot includes a plurality of sectors, each of which represents an anatomical region of the myocardium in one of the plurality of sections.

Abstract: An information processing apparatus includes an image obtaining unit configured to obtain a first inspection image having first supplemental information and a second inspection image having second supplemental information, a difference image obtaining unit configured to obtain a difference image generated using the first and second inspection images, a difference information obtaining unit configured to obtain difference information on a difference between the first supplemental information and the second supplemental information, and an association unit configured to associate the difference information with the difference image.

Abstract: An apparatus includes: an accommodation unit capable of accommodating a cell and liquid; and a rotation unit that produces a flow in the liquid in the accommodation unit to rotate the cell. The apparatus further includes a rotation controller unit that detects a rotation amount input from an input device, and controls the flow of the liquid produced by each of the output ports on a basis of the input rotation amount to control a rotation amount of the cell.

Abstract: A machine learning model is trained to identify the texture difference between the different layers of a multilayer object. By training with data in full 3D space, the resulting model is capable of predicting the probability that each pixel in a 3D image belongs to a certain layer. With the resulting probability map, comparing probabilities allows one to determine boundaries between layers, and/or other properties and useful information such as volume data.

Abstract: Presented herein are systems and methods that allow for vertebral centrums of individual vertebrae to be identified and segmented within a 3D image of a subject (e.g., a CT or microCT image). In certain embodiments, the approaches described herein identify, within a graphical representation of an individual vertebra in a 3D image of a subject, multiple discrete and differentiable regions, one of which corresponds to a vertebral centrum of the individual vertebra. The region corresponding to the vertebral centrum may be automatically or manually (e.g., via a user interaction) classified as such. Identifying vertebral centrums in this manner facilitates streamlined quantitative analysis of 3D images for osteological research, notably, providing a basis for rapid and consistent evaluation of vertebral centrum morphometric attributes.

Abstract: A method and apparatus for performing an angiographic simulation is disclosed. A vascular structure is segmented within a 3D imaging dataset, such as a CT scan or MRI scan. The voxels corresponding to virtual contrast are placed within the segmented vascular structure. Multi-phase simulations can be performed to track contrast flow through the vascular tree. Some embodiments comprises inserting virtual contrast in conjunction with performing a deformity of the vascular structure.

Abstract: An image processing system and related method. The system comprises an input interface (IN) configured for receiving an n[?2]-dimensional input image with a set of anchor points defined in same, said set of anchor points forming an input constellation. A constellation modifier (CM) is configured to modify said input constellation into a modified constellation. A constellation evaluator (CE) configured to evaluate said input constellation based on said hyper-surface to produce a score. A comparator (COMP) is configured to compare said score against a quality criterion. Through an output interface (OUT) said constellation is output if the score meets said criterion. The constellation suitable to define a segmentation for said input image.

Abstract: An X-ray CT apparatus according to an embodiment includes processing circuitry. The processing circuitry acquires a first data set corresponding to first X-ray energy and a second data set corresponding to second X-ray energy different from the first X-ray energy, with respect to a region including a part of a subject by performing scanning using X-rays. The processing circuitry generates a scatter diagram representing a contained amount of each of reference materials at each of positions in the region on the basis of the first data set and the second data set. The processing circuitry sets weights for at least a part of the scatter diagram. The processing circuitry generates an analysis image based on the contained amounts and the weights.

Abstract: An X-ray CT device and a computing unit to use a projection-based method for image reconstruction are included. The computing unit sets a coordinate space having coordinate axes of the thicknesses of base materials and likelihood the thicknesses, and then based on X-ray attenuation responses, executes: a first search to search in a direction perpendicular to a ridge direction of likelihood contours for a first estimated thickness having the highest likelihood, starting with an estimated thickness input value set in the coordinate space; a second search to search for a second estimated thickness having the highest likelihood, starting with a shifted starting point at a position shifted from the estimated thickness input value; and a third search to search on a line connecting the first estimated thickness with the second estimated thickness for the highest likelihood estimator having the highest likelihood, to obtain an estimated thickness output value.

Abstract: A medical scan header standardization system is operable to determine a set of standard DICOM headers based on determining a standard set of fields and based on further determining a standard set of entries for each of the standard set of fields. A DICOM image is received via a network, and a header of the DICOM image is determined to be incorrect. A selected one of the set of standard DICOM headers to replace the header of the DICOM image is determined. The selected one of the set of standard DICOM headers is transmitted, via the network, to a medical scan database for storage in conjunction with the DICOM image.

Abstract: A method for handing off diagnostic test results to a telemedicine provider is provided. The method comprises receiving diagnostic test results in response to a diagnostic test, determining if the diagnostic test results include a positive result, storing the diagnostic test results on a server disposed on a network, sending the diagnostic test results from the server to the telemedicine provider, sending additional medical history information to the telemedicine provider, and initiating a telemedicine conference with the telemedicine provider.

Abstract: Disclosed herein are ratiometric fluorescence imaging reagents, and image processing methods for using fluorescence ratio and intensity thresholds to detect and visualize regions of biological activity in biological specimens with improved accuracy.

Abstract: Disclosed herein are exemplary embodiments of innovations in the area of point cloud encoding and decoding. Example embodiments can reduce the computational complexity and/or computational resource usage during 3D video encoding by selectively encoding one or more 3D-point-cloud blocks using an inter-frame coding (e.g., motion compensation) technique that allows for previously encoded/decoded frames to be used in predicting current frames being encoded. Alternatively, one or more 3D-point-cloud block can be encoded using an intra-frame encoding approach. The selection of which encoding mode to use can be based, for example, on a threshold that is evaluated relative to rate-distortion performance for both intra-frame and inter-frame encoding. Still further, embodiments of the disclosed technology can use one or more voxel-distortion-correction filters to correct distortion errors that may occur during voxel compression.

Abstract: The present disclosure provides an object detection method, an object detection device, and a storage medium. In the present disclosure, with respect to each contour existing in an image to be detected, a contour diameter is calculated; a shape of the contour is determined based on side lengths of the circumscribed rectangular frame of each contour and the contour diameter; and an object in the image to be detected and parameter information of the object is determined based on the shape of each contour, thereby quickly and accurately detecting the shape of the object and reducing the labor cost and time of detection due to the low complexity of the detection.

Abstract: Disclosed is a method and system for three-dimensional tracking of a target located within a body, the method performed using at least one processing system. A two-dimensional scanned image of the body including the target is processed to obtain a two-dimensional image of the target. A first present dataset of the target is predicted using a previous dataset of the target and a state transition model, the first present dataset includes a three-dimensional present position value of the target. A second present dataset of the target is measured by template-matching of the two-dimensional image of the target with a model of the target. A third present dataset of the target is estimated by statistical inference using the first present dataset and the second present dataset. The previous dataset of the target is updated to match the third present dataset.

Abstract: Techniques are provided for reconstructing cardiac frequency phenomena from a sequence of angiographic images, i.e., two-dimensional projection images acquired at faster than cardiac rate (greater than two-fold), and analyzed to provide a spatiotemporal reconstruction of moving vascular pulse waves according to that projection. In aspects, a cardiac frequency bandpass filter and/or a Eulerian magnification may be applied to the angiographic data to output the spatiotemporal reconstruction of cardiac frequency angiographic phenomena.

Abstract: A system for tracking single-cell movement trajectories is disclosed. The system can record, to a plurality of frames, cells (events) within a microfluidic device. Also, the system can identify an event within each frame including whether the event is a single cell or multiple cells. When the event appears differently between frames (e.g., single cell in one frame and multiple cells in another frame), the system can either segment or merge the cell(s). Then, the system can determine a trajectory for the events based on a position of the event in the frames. Further, the system can determine cell properties based on the trajectory of the events.

Abstract: A method for evaluating image quality is provided. The method may include: obtaining an image, the image including a plurality of elements, each element of the plurality of elements being a pixel or voxel, each element having a gray level; determining, based on a maximum gray level of the plurality of elements, one or more thresholds for segmenting the image; determining one or more sub-images of a region of interest by segmenting, based on the one or more thresholds, the image; and determining, based on the one or more sub-images of the region of interest, a quality index for the image.

Abstract: Introduced here are diagnostic platforms able to attribute an output produced by a neural network to its input, as well as communicate the relationship between the output and input in a comprehensible manner. Neural networks are increasingly being used for critical tasks, such as detecting the presence/progression of medical conditions. Accordingly, the importance of explaining how these neural networks produce outputs has grown in importance. By explaining how outputs are produced by a neural network, a diagnostic platform can build trust with medical professionals responsible for interpreting the outputs, identify possible modes of neural network failure, and identify the latent variable(s) responsible for producing a given output.

Abstract: A method for localization and identification of a structure in a projection image with a system having a known system geometry, includes acquiring a preoperative computer-tomography or CT image of a structure, preprocessing the CT-image to a volume image, acquiring an intraoperative two dimensional or 2D X-ray image, preprocessing the 2D X-ray image to a fix image, estimating an approximate pose of the structure, calculating a digitally reconstructed radiograph or DRR using the volume image, the estimated pose and the system geometry, and calculating a correlation between the generated DRR and the fix image, with a correlation value representing matching between the generated DRR and the fix image. The method significantly decreases the number of wrong-level surgeries and is independent of the surgeon's ability to localize and/or identify a target level in a body.