Abstract: Information representing a physique of a subject is extracted from an image obtained by imaging the subject. A group in which the subject is classified is specified, using the extracted information representing the physique of the subject. Image data representing a medical image obtained by imaging the subject is input to a learned model corresponding to a specified group among learned models obtained for each group by machine learning using learning data for each group. Information representing an area extracted from the medical image is acquired, which is output from the learned model with the input.

Abstract: Applicants have discovered a new low-cost and accessible method and apparatus that allowing for quicker and more precise state determinations based on medical images. The method and apparatus are non-intrusive and require providing a medical image of a subject and determining a state based on a comparison to a training image set comprising two or more states. There is provided, according to the present invention, a computer-implemented method for processing medical images comprising calculating non-local means patch-based weights comparing patches surrounding pixels of interest in a test image with a number of patches of pixels surrounding a corresponding number of pixels in reference images; and calculating for the pixels of interest at least one state estimation using a given state assigned to said reference images and said weights.

Abstract: A three-dimensional shape data editing apparatus includes a processor configured to set, based on three-dimensional shape data of a surface of a three-dimensional shape of an object configured by using a formation surface of at least one of plural flat surfaces or curved surfaces, for each of plural divided three-dimensional regions, a distance from a predetermined location of the region to the formation surface of the three-dimensional shape of the object configured by the formation surface.

Abstract: An image interpretation support apparatus includes an acquisition unit, an acceptance unit, and a specifying unit. The acquisition unit acquires a two-dimensional standard image having information on a breast, and a plurality of tomographic images in a plurality of tomographic planes of the breast which are obtained by tomosynthesis imaging of the breast. The acceptance unit accepts a selection instruction of a location on the two-dimensional standard image. In a case where the selection instruction is accepted in the acceptance unit, the specifying unit specifies a corresponding tomographic plane corresponding to a selected location which is the location of which the selection instruction is accepted in the acceptance unit, from among the plurality of tomographic planes on the basis of the plurality of tomographic images.

Abstract: A method of reading a medical image by a computing device operated by at least one processor is provided. The method includes obtaining an abnormality score of the input image using an abnormality prediction model, filtering the input image so as not to be subsequently analyzed when the abnormality score is less than or equal to a cut-off score based on the cut-off score which makes a specific reading sensitivity; and obtaining an analysis result of the input image using a classification model that distinguishes the input image into classification classes when the abnormality score is greater than the cut-off score.

Abstract: An intraoral scanning system comprises an intraoral scanner and a computing device. The computing device receives intraoral scans of a dental site from the intraoral scanner, the intraoral scans comprising at least a first intraoral scan and a second intraoral scan. The computing device determines, for each point in the second intraoral scan based on a first comparison of the first intraoral scan to the second intraoral scan, whether the point is a back-face point or an uncovered point. The computing device determines a region comprising a plurality of points in the second intraoral scan that are uncovered points, determines whether the region satisfies one or more removal criteria, and removes the region from the second intraoral scan responsive to determining that the region satisfies the one or more removal criteria.

Abstract: The present disclosure is directed towards systems and methods that leverage machine-learned models to decrease the rate at which abnormal sites are missed during a gastroenterological procedure. In particular, the system and methods of the present disclosure can use machine-learning techniques to determine the coverage rate achieved during a gastroenterological procedure. Measuring the coverage rate of the gastroenterological procedure can allow medical professionals to be alerted when the coverage output is deficient and thus allow an additional coverage to be achieved and as a result increase in the detection rate for abnormal sites (e.g., adenoma, polyp, lesion, tumor, etc.) during the gastroenterological procedure.

Abstract: Disclosed is method, a user interface, a computer program product and a system for predicting future development of a dental condition of a patient's set of teeth, wherein the method comprises:—obtaining two or more digital 3D representations for the teeth recorded at different points in time;—deriving based on the obtained digital 3D representations a formula expressing the development of the dental condition in terms of at least one parameter as a function of time; and—predicting the future development of the condition based on the derived formula.

Abstract: Various example embodiments are described in which an anisotropic encoder-decoder convolutional neural network architecture is employed to process multiparametric magnetic resonance images for the generation of cancer predication maps. In some example embodiments, a simplified anisotropic encoder-decoder convolutional neural network architecture may include an encoder portion that is deeper than a decoder portion. In some example embodiments, simplified network architectures may be combined with test-time-augmentation in order to facilitate training and testing with a minimal number of test subjects.

Abstract: There is provided an image processing apparatus and an image processing method that are capable of suppressing an increase in loads when a point cloud is generated from a mesh. Point cloud data is generated by positioning points at intersection points between a surface of a mesh and vectors each including, as a start origin, position coordinates corresponding to a specified resolution. For example, intersection determination is performed between the surface of the mesh and each of the vectors, and in a case where the surface and the vector are determined to intersect each other, the coordinates of the intersection point are calculated. The present disclosure can be applied to an image processing apparatus, electronic equipment, an image processing method, a program, or the like.

Abstract: A medical imaging communication system generates an automated report for a medical image corresponding to a patient. The system receives one or more medical images for a patient. The system applies a model to identify an abnormality in the received one or more medical images. The model is configured to determine a likelihood score for the presence of the abnormality in the one or more medical images. If the likelihood score is above a threshold value, the system generates an automated report indicating the type of abnormality identified in the received one or more medical images. The automated report is then provided to a viewing user (e.g., a medical professional viewing the one or more medical images).

Abstract: Ingestible devices are disclosed that provide very high localization accuracy for the devices when present in the GI tract of a body. Related systems and methods are also disclosed.

Abstract: Methods, devices, and systems are provided for quantifying an extent of various pathology patterns in scanned subject images. The detection and quantification of pathology is performed automatically and unsupervised via a trained system. The methods, devices, and systems described herein generate unique dictionaries of elements based on actual image data scans to automatically identify pathology of new image data scans of subjects. The automatic detection and quantification system can detect a number of pathologies including a usual interstitial pneumonia pattern on computed tomography images, which is subject to high inter-observer variation, in the diagnosis of idiopathic pulmonary fibrosis.

Abstract: The disclosure relates to methods, devices, systems, and computer storage medium for performing medical image segmentation. The method includes: The method includes: obtaining, by a device, a first medical image and a second medical image with a labeled region; performing, by the device, feature extraction on the first medical image and the second medical image respectively, to obtain first feature information of the first medical image and second feature information of the second medical image; obtaining, by the device, optical flow motion information from the second medical image to the first medical image according to the first feature information and the second feature information; and segmenting, by the device, the first medical image according to the optical flow motion information and the labeled region, to obtain a segmentation result of the first medical image.

Abstract: A computer-implemented method for tracking surgical textiles includes receiving a first image comprising a first textile-depicting image region, receiving a second image comprising a second textile-depicting image region, measuring a likelihood that the first and second image regions depict at least a portion of the same textile, and incrementing an index counter if the measure of likelihood does not meet a predetermined threshold. The measure of likelihood may be based on at least one classification feature at least partially based on aspects or other features of the first and second images.

Abstract: A method for classifying input data includes receiving the input data that describe an object, wherein the input data corresponds to plural classes; associating the input data with voxels that describe the object; calculating a real-number sequence X(n), which is associated with a measured parameter P that describes the object; quantizing the real-number sequence X(n) to generate a finite set sequence Q(n), where n describes a number of levels; generating a voxel-based weight matrix for each class of the input data; and calculating a score S for each class of the plural classes, based on a corresponding voxel-based weight matrix. The score S is a number that indicates a likelihood that the input data associated with a given sample belongs to a class of the plural classes.

Abstract: The outline of a bone or at least a portion thereof may be determined based on deep neural net and optionally on an active shape model approach. An algorithm may detect a fracture of the bone. An algorithm may also classify the bone fracture and provide guidance on how to treat the fracture.

Abstract: Disease detection from medical images is provided. In various embodiments, a medical image of a patient is read. The medical image is provided to a trained anatomy segmentation network. A feature map is received from the trained anatomy segmentation network. The feature map indicates the location of at least one feature within the medical image. The feature map is provided to a trained classification network. The trained classification network was pre-trained on a plurality of feature map outputs of the segmentation network. A disease detection is received from the trained classification network. The disease detection indicating the presence or absence of a predetermined disease.

Abstract: A feature information acquisition unit acquires the first feature information on the first medical image and second feature information on the second medical image having an imaging time different from an imaging time of the first medical image. A sentence creation unit compares the first feature information and the second feature information generated by the feature information acquisition unit, and creates a sentence representing a change between the first medical image and the second medical image. A display control unit causes the display unit to display a sentence representing a change.

Abstract: This disclosure relates to a medical image viewer for incorporating multi-user collaboration features, such as in-image commenting and workspace sharing. An example method includes receiving a comment location including image coordinates and comment information associated with the comment from a user device. The comment information includes a text body, identify identity information related to the user, and a comment creation date. The example method further includes determining world coordinates based on the image coordinates, and storing the world coordinates and the comment information as a subset of header attributes of the DICOM image file.

Abstract: A cortical malformation identification method includes quantitatively evaluating, using a processor of a computer that includes the processor and a memory, digital image data from a magnetic resonance imaging (MRI) scan on a cerebral cortex to produce quantified scan data. The method also includes automatically detecting a cortical malformation based on the quantified scan data. An image of the cerebral cortex may be color-coded so that the cortical malformation is shown in a different color than the remainder of the cerebral cortex in the image, based on the quantified scan data. Additionally or alternatively, a 3-dimensional representation of the cerebral cortex may be mapped to the quantified scan data to produce a mapped image of the cerebral cortex including the detected cortical malformation.

Abstract: A discrimination unit discriminates a disease region included in a medical image. The discrimination unit has a first neural network which discriminates a first medical feature in the medical image, and consists of a plurality of processing layers, and a second neural network which discriminates a second medical feature associated with the first medical feature, in the medical image, and consists of a plurality of processing layers. A feature quantity output from the processing layer in the middle of the second neural network or an output result of the second neural network is input to the first neural network.

Abstract: An image processing method is provided that automatically calculates Body Surface Area (BSA) score using machine learning techniques. A Felzenszwalb image segmentation algorithm is used to define proposed regions in each of a plurality of training set images. The training set images are oversegmented, and then each of the proposed regions in each of the plurality of oversegmented training set images are manually classified as being a lesion or a non-lesion. A Convolutional Neural Network (CNN) is then trained using the manually classified proposed regions in each of the plurality of training set images. The trained CNN is then used on test images to calculate BSA scores.

Abstract: A method for initiating a telemedicine conference on a mobile device 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, presenting, if the diagnostic test results are positive, a telemedicine initiation option on a screen of the mobile device, determining whether the telemedicine initiation option is selected, 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. Some of these aspects also provide healthcare providers the ability to electronically send prescriptions and provide users the ability to use a mobile application to send prescriptions to pharmacies to be filled.

Abstract: Provided are a medical image processing apparatus, a medical image processing method, a program, a diagnosis supporting apparatus, and an endoscope system that emphasize a region of interest in a medical image at an appropriate emphasis degree. The above problem is solved by a medical image processing apparatus including: an emphasis processing unit that emphasizes a region of interest included in a time-series medical image at a set emphasis degree; a total-time measuring unit that measures a total time during which the region of interest is emphasized; and an emphasis-degree setting unit that sets the emphasis degree to a relatively larger value as the total time is relatively longer.

Abstract: A method for blood flow imaging can include receiving, by a processor coupled to a first memory device comprising a first type of media and a second memory device comprising a second type of media, an indication corresponding to initiation of an application and data captured by an imaging device coupled to the processor. The method can include determining characteristics of a workload corresponding to execution of the application to process the data captured by the imaging device for the first memory device and the second memory device and writing the data captured by the imaging device to the first memory device or the second memory device based on determined characteristics for the first memory device and the second memory device in executing the workload.

Abstract: An image of a sample collection device is captured. The image of the sample collection device is analyzed to determine whether the sample collection device includes a sufficient amount of fluid sample. The image of the sample collection device is validated based on a result of the image analysis.

Abstract: An information processing system includes a storage device that stores therein a trained model, and a processor. The trained model is trained to output a position and shape of an object in a training image based on training data. The training data is data in which the training image is provided with an annotation indicating the position and shape of the object. The training image is an image captured with an angle of view including the object whose position and shape are not clearly displayed in an image. The processor executes detection processing on a detection image to output detected information indicating the position and shape of the object. The processor then causes a display device to display the detected information superimposed on the detection image.

Abstract: The system obtains a first digital image and a hash associated with the first digital image, where the hash associated with the first digital image is a hash of analog values recorded by a sensor involved in generating the first digital image. Based on the hash, the system retrieves the analog values from a database. Based on the analog values, the system reconstructs a second digital image. The system determines whether the first digital image and the second digital image are substantially the same. Upon determining that the first digital image and the second digital image are substantially the same, the system provides a first notification that the first digital image is the same as the second digital image, otherwise the system provides a second notification that the first digital image is different from the second digital image.

Abstract: Digital pathology is a promising alternative to manual slide analysis, but improvements in imaging and analysis methods are needed to provide an analysis data set of images that can easily be handled, stored, and importantly, delivered from one data location to another. Methods and software are described herein to improve image collection and analysis.

Abstract: A system comprises a dental tray comprising an array of cameras, wherein each camera of the first array of cameras has a fixed position and orientation relative to one or more other camera of the array of cameras. The system further comprises a processing device to receive a plurality of images generated by the array of cameras, stitch the plurality of images together based on calibration data specifying predetermined image stitching parameters for combining the plurality of images, wherein the predetermined image stitching parameters are based on predetermined fixed relative positions and orientations of cameras from the array of cameras, and generate a three-dimensional model of a plurality of teeth based on the stitched plurality of images.

Abstract: A method and bot assistance system (101) for identifying ideal virtual assistant bots for providing response to user queries is disclosed. The bot assistance system receives user query. The user query is processed to identify context and intent using Natural Language Processing (NLP). The bot assistance system identifies at least one virtual assistant bot for responding to user query based on confidence score of each virtual assistant bot associated with intent of user query, using pretrained model. The identification of at least one virtual assistant bot includes either determining ideal virtual assistant bot based on context of user query, using predefined governance rules. Otherwise, initiating polling between plurality of predefined virtual assistant bots when context of user query is unidentified. The plurality of predefined virtual assistance bots is provided to user associated with user query if each of predefined virtual assistance bots are selected during polling.

Abstract: Digital image object anchor point techniques are described that increase user efficiency in interacting with a user interface to create digital images. This is achieved through use of anchor points by the digital image editing system that are defined with respect to an actual geometry of the object. Further, filtering and prioritization techniques are also leveraged to promote real world utility and efficiency of these techniques as a balance between having too many and two few anchor points.

Abstract: An ophthalmic imaging system comprises a first imaging subsystem, a sensor array and a second imaging subsystem. The first imaging subsystem forms a primary image of the interior of an eye through the diameter of the eye pupil. The second imaging subsystem comprises a lens array to form an array of secondary images on the sensor array. The lens array is composed of a plurality of types of lenses, each type having a different optical power.

Abstract: In various embodiments, a gradient modeling application automatically generates designs of three-dimensional (3D) objects. The gradient modeling application generates a set of points based on a resolution and a perimeter. The gradient modeling application computes a set of displacement values based on the set of points, a first two-dimensional (2D) border, and a first displacement parameter that is associated with the first 2D border. Based on the set of displacement values, the gradient modeling application generates a 3D object design.

Abstract: The method includes receiving digital images of tissue samples of patients, the images having assigned a label indicating a patient-related attribute value; splitting each received image into a set of image tiles; computing a feature vector for each tile; training a Multiple-Instance-Learning program on all the tiles and respective feature vectors for computing for each of the tiles a numerical value being indicative of the predictive power of the feature vector associated with the tile in respect to the label of the tile's respective image; and outputting a report gallery including tiles sorted in accordance with their respectively computed numerical value and/or including a graphical representation of the numerical value.

Abstract: A method includes receiving anatomic image data comprising a plurality of graphical units; generating an initial segmented set of the plurality of graphical units associated with an anatomic tree structure; receiving an indication of a first user selected graphical unit, the first user selected graphical unit being outside the initial segmented set of the plurality of graphical units; applying a cost function to determine a first sequence of graphical units from the first user selected graphical unit to the initial segmented set of graphical units; receiving an indication of a second user selected graphical unit, the second user selected graphical unit being selected from the first sequence of the plurality of graphical units; and applying the cost function to determine a second sequence of the plurality of graphical units from the second user selected graphical unit to the initial segmented set of the plurality of graphical units.

Abstract: Methods and systems are provided for detecting focal lesions in multi-phase or multi-sequence medical imaging studies of medical images. One system includes memory for storing medical images and an electronic processor. The electronic processor is configured to: detect native candidate lesions for first phase computer tomography (CT) scans, detect candidate lesions for second phase CT scans, and project the candidate lesions detected for the first phase CT scans and/or the second phase CT scans on a same common domain. Once the candidate lesions are registered together, the electronic processor performs a matching algorithm for each of the native candidate lesions of the first phase CT scans with the registered candidate lesions from the second phase CT scans to determine presence and contours of valid lesions for the medical images, and to discard candidate lesions that are not acceptable.

Abstract: A system and method to analyze image data. The image data may be used to assist in determine the presence of a feature in the image. The feature may include a bubble.

Abstract: Digital imaging systems and methods are described for analyzing pixel data of an image of a shaving stroke for determining pressure being applied to a user's skin. A plurality of training images of a plurality of individuals are aggregated, each of the training images comprising pixel data of a respective individual when shaving with a shaving razor. A pressure model, trained with the pixel data, is operable to determine pressure being applied to the respective individual's skin. An image of a user when shaving with the shaving razor is received and analyzed, by the pressure model, to determine a user-specific pressure being applied to the user's skin by the shaving razor when a user shaving stroke is taken. A user-specific electronic recommendation to address at least one feature identifiable within the pixel data is generated and rendered, on a display screen of a user computing device.

Abstract: A non-transitory computer-readable storage medium storing a set of program instructions for an image processing apparatus is disclosed. The set of program instructions, when executed by a controller of the image processing apparatus, causes the image processing apparatus to: acquire input image data indicating an input image; and input the input image data to a trained machine learning model configured to perform calculation processing on the input image data and to generate output image data corresponding to the input image data. The machine learning model is trained to generate the output image data indicating a first area and a second area. The first area is an area in the input image in which it is preferable to perform first image processing. The second area is an area in the input image in which it is preferable to perform second image processing different from the first image processing.

Abstract: A system, method and non-transient computer readable medium for tracking hypoglycemia risk in patients with diabetes exercise. A system may include a digital processor configured to execute instructions to receive an input from each available data source of a plurality of intermittently available data sources; determine a plurality of probability signals for impending hypoglycemia, wherein each probability signal is based on one or more of the inputs from the available data sources or a lack of input from an unavailable data source; wherein a probability signal for each unavailable data source is assigned a value corresponding to a zone of uncertainty; and determine an aggregate risk of hypoglycemia based on the plurality of intermittently data sources by aggregating the plurality of probability signals.

Abstract: The present disclosure provides a computer-implemented method, a device, and a storage medium. The method includes inputting an image into an attention-enhanced high-resolution network (AHRNet) to extract feature maps for generating a first feature map; generating a first probability map which is concatenated with the first feature map to form a concatenated first feature map, and updating the AHRNet using the first segmentation loss; generating a second feature map, and scaling the second feature map to form a third feature map; generating a second probability map which is concatenated with the third feature map to form a concatenated third feature map, and updating the AHRNet using the second segmentation loss; generating a fourth feature map, and scaling the fourth feature map to form a fifth feature map; updating the AHRNet using the third segmentation loss and the regional level set loss; and outputting the third probability map.

Abstract: Methods for generating a deep neural net and for localizing an object in an input image, the deep neural net, a corresponding computer program product, and a corresponding computer-readable storage medium are provided. A discriminative counting model is trained to classify images according to a number of objects of a predetermined type depicted in each of the images, and a segmentation model is trained to segment images by classifying each pixel according to what image part the pixel belongs to. Parts and/or features of both models are combined to form the deep neural net. The deep neural net is adapted to generate, in a single forward pass, a map indicating locations of any objects for each input image.

Abstract: During operation, a computer system may apply a pretrained predictive model to information for at least a subset of a plurality of individuals, and may determine levels of uncertainty in results of the pretrained predictive model for at least the subset of the plurality of individuals. Then, the computer system may dynamically adapt a at least one threshold range based at least in part on the determined levels of uncertainty and a predefined target performance of the pretrained predictive model for the plurality of individuals. Next, the computer system may perform different remedial actions for a first group of individuals in the plurality of individuals having the results where the levels of uncertainty are within the at least one threshold range and a second group of individuals in the plurality of individuals having the results where the levels of uncertainty are outside of the at least one threshold range.

Abstract: The present invention relates biometric authentication using an optical biometric arrangement comprising an image sensor comprising a photodetector pixel array configured to capture an image of an object, the image sensor being arranged under a color controllable light source comprising light source units, the method comprising: providing a light pattern comprising portions of different light intensity for illuminating the object; acquiring an image of the object, the image comprising image portions corresponding to the portions of different light intensity of the light pattern illuminating the object, at least one image portion being captured by pixels in the photodetector pixel array arranged directly under a light source being active during image acquisition, and at least one image portion being captured by pixels in the photodetector pixel array arranged under an at least partly in-active illumination area of the color controllable light source during image acquisition, and performing biometric authentica

Abstract: Described herein is a platform and supported graphical user interface (GUI) decision-making tools for use by medical practitioners and/or their patients, e.g., to aide in the process of making decisions about a course of cancer treatment and/or to track treatment and/or the progress of a disease.

Abstract: A deep learning-based digital staining method and system are disclosed that enables the creation of digitally/virtually-stained microscopic images from label or stain-free samples based on autofluorescence images acquired using a fluorescent microscope. The system and method have particular applicability for the creation of digitally/virtually-stained whole slide images (WSIs) of unlabeled/unstained tissue samples that are analyzes by a histopathologist. The methods bypass the standard histochemical staining process, saving time and cost. This method is based on deep learning, and uses, in one embodiment, a convolutional neural network trained using a generative adversarial network model to transform fluorescence images of an unlabeled sample into an image that is equivalent to the brightfield image of the chemically stained-version of the same sample.

Abstract: A finding classification unit classifies each pixel of a first medical image into at least one finding. A feature amount calculation unit calculates a first feature amount for each finding. A weighting coefficient setting unit sets a weighting coefficient indicating a degree of weighting, which varies depending on a size of each finding, for each finding. A similarity derivation unit performs a weighting operation for the first feature amount for each finding calculated in the first medical image and a second feature amount for each finding calculated in advance in a second medical image on the basis of the weighting coefficient to derive a similarity between the first medical image and the second medical image.

Abstract: A computer apparatus and method for identifying and visualizing tumors in a histological image and measuring a tumor margin are provided. A CNN is used to classify pixels in the image according to whether they are determined to relate to non-tumorous tissue, or one or more classes for tumorous tissue. Segmentation is carried out based on the CNN results to generate a mask that marks areas occupied by individual tumors. Summary statistics for each tumor are computed and supplied to a filter which edits the segmentation mask by filtering out tumors deemed to be insignificant. Optionally, the tumors that pass the filter may be ranked according to the summary statistics, for example in order of clinical relevance or by a sensible order of review for a pathologist. A visualization application can then display the histological image having regard to the segmentation mask, summary statistics and/or ranking. Tumor masses extracted by resection are painted with an ink to highlight its surface region.