Abstract: Mechanisms are provided to implement an automated echocardiograph measurement extraction system. The automated echocardiograph measurement extraction system receives medical imaging data comprising one or more medical images and inputs the one or more medical images into a deep learning network. The deep learning network automatically processes the one or more medical images to generate an extracted echocardiograph measurement vector output comprising one or more values for echocardiograph measurements extracted from the one or more medical images. The deep learning network outputs the extracted echocardiograph measurement vector output to a medical image viewer.

Abstract: A method for processing medical images includes analyzing a medical image to detect a medical condition from a list of medical conditions, wherein the list of medical conditions includes aortic dissection, pulmonary embolism, and coronary stenosis. Responsive to determining the medical image includes a first medical condition, the method generates a first report that includes information on a detection of the first medical condition. The method identifies, a medical specialist based on availability and medical expertise and sends to the identified medical specialist, the medical image and the first report for a decision on the detection of the first medical condition. Responsive to receiving the decision from the medical specialist, the method sends to a second electronic device, the decision, the medical image, and the first report.

Abstract: A method and system for automatically inferring a subject's body position in a two-dimensional image produced by a medical-imaging system are disclosed. The image is labeled with a body position selected from a semantically meaningful set of candidate positions sequenced in order of their relative locations in a subject's body. A processor performs procedures that each identify a class of image features related to pixel intensity, such as a histogram of gradients, local binary patterns, or Haar-like features. A second set of procedures employs applications of a pretrained convolutional neural network that has learned to recognize features of a specific class of medical images. The results of both types of procedures are then mapped by a pretrained support-vector machine onto candidate image labels, which are mathematically combined into a single, semantically meaningful, label most likely to identify a body position of the subject shown by the image.

Abstract: According to one or more embodiments, a method, a computer program product, and a computer system for detecting and characterizing aortic pathologies are provided. The method may include receiving, by a computer, one or more tomograph scan images corresponding to a patient's aorta. The one or more received tomograph scan images may be analyzed by the computer for one or more image features associated with one or more aortic pathologies, such as aortic dissection or an aortic aneurysm. One or more image features associated with the one or more aortic pathologies may be identified in the one or more analyzed tomograph scan images, which may allow the determination of an aortic pathology associated with the patient's aorta based on the identification of the image features. A portion of the aorta and one or more branch arteries corresponding to the determined aortic pathology may then be identified.

Abstract: A method and system for automatically inferring a subject's body position in a two-dimensional image produced by a medical-imaging system are disclosed. The image is labeled with a body position selected from a semantically meaningful set of candidate positions sequenced in order of their relative locations in a subject's body. A processor performs procedures that each identify a class of image features related to pixel intensity, such as a histogram of gradients, local binary patterns, or Haar-like features. A second set of procedures employs applications of a pretrained convolutional neural network that has learned to recognize features of a specific class of medical images. The results of both types of procedures are then mapped by a pretrained support-vector machine onto candidate image labels, which are mathematically combined into a single, semantically meaningful, label most likely to identify a body position of the subject shown by the image.

Abstract: In many medical image classification problems, distinctive image features are often localized in certain anatomical regions. The key to efficient and accurate classification in such problems is the localization of the region of interest (ROI). To address this problem, a multi-atlas label fusion technique was developed for automatic ROI detection. Given training images with class labels, the present method infers voxel-wise scores for each image showing how distinctive each voxel is for categorizing the image. The present method for ROI segmentation and for class specific ROI patch extraction in a 2D cardiac CT body part classification application was applied and shows the effectiveness of the detected ROIs.

Abstract: In many medical image classification problems, distinctive image features are often localized in certain anatomical regions. The key to efficient and accurate classification in such problems is the localization of the region of interest (ROI). To address this problem, a multi-atlas label fusion technique was developed for automatic ROI detection. Given training images with class labels, the present method infers voxel-wise scores for each image showing how distinctive each voxel is for categorizing the image. The present method for ROI segmentation and for class specific ROI patch extraction in a 2D cardiac CT body part classification application was applied and shows the effectiveness of the detected ROIs.

Abstract: Ranking of data and retrieval of data or relationships of the data responsive to the ranking. A data model is represented as a graph, with edges in the graph linking related concepts, and an assertion represented in the graph as a reified n-ary relation. The graph is ingested though traversal and storage of the node paths. The traversal includes concepts and categories. In addition, neighborhood of one or more adjacent concepts are followed and stored in relation to the node paths. The ingested graph is converted into a set of flat document structures supported by information ranking and a retrieval framework.

Abstract: Embodiments relate to associating coronary angiography image annotations with SYNTAX score for assessment of coronary artery disease. Aspects include receiving and processing a plurality of angiogram videos from a coronary angiography study into a plurality of frames, selecting and displaying a key frame from the plurality of frames for each angiogram video in a browsing interface, and receiving a selection of one of the key frame from a user. Aspects further include displaying the angiogram video associated with the selected key frame in a video viewer interface, receiving a lesion annotation from the user for a frame of the angiogram video, and displaying a SYNTAX score questionnaire in the video viewer interface. Aspects further include annotating the frame of the angiogram video with the answers to the SYNTAX score questionnaire from the user and saving the answers to the SYNTAX score questionnaire with the annotated frame in a database.

Abstract: An automatic extraction of disease-specific features from Doppler images to help diagnose valvular diseases is provided. The method includes the steps of obtaining a raw Doppler image from a series of images of an echocardiogram, isolating a region of interest from the raw Doppler image, the region of interest including a Doppler image and an ECG signal, and depicting at least one heart cycle, determining a velocity envelope of the Doppler image in the region of interest, extracting the ECG signal to synchronize the ECG signal with the Doppler age over the at least one heart cycle, within the region of interest, calculating a value of a clinical feature based on the extracted ECG signal synchronized with the velocity envelope, and comparing the value of the clinical feature with clinical guidelines associated with the clinical feature to determine a diagnosis of a disease.

Abstract: Embodiments relate to detecting coronary stenosis through spatio-temporal tracking. Aspects include extracting a coronary artery tree from each of a sequence of angiogram images, creating a mean artery tree from the extracted coronary artery trees, and projecting the mean artery tree back onto each of the sequence of angiogram images to recover a complete coronary artery tree for each of the sequence of angiogram images. Aspects also include extracting one or more tubular sections from each of the sequence of angiogram images, estimating an arterial width for each of the one or more tubular sections from each of the sequence of angiogram images, and creating a spatio-temporal surface from the arterial widths of the one or more tubular sections over a time spanned by the sequence of angiogram images. Aspects further include detecting a minimum in the spatio-temporal surface and determining if the minimum is indicative of stenosis.

Abstract: A method and system for automatically inferring a subject's body position in a two-dimensional image produced by a medical-imaging system are disclosed. The image is labeled with a body position selected from a semantically meaningful set of candidate positions sequenced in order of their relative locations in a subject's body. A processor performs procedures that each identify a class of image features related to pixel intensity, such as a histogram of gradients, local binary patterns, or Haar-like features. A second set of procedures employs applications of a pretrained convolutional neural network that has learned to recognize features of a specific class of medical images. The results of both types of procedures are then mapped by a pretrained support-vector machine onto candidate image labels, which are mathematically combined into a single, semantically meaningful, label most likely to identify a body position of the subject shown by the image.

Abstract: Methods and arrangements for automatic ground truth generation of medical image collections. Aspects include receiving a plurality of imaging studies, wherein each imaging study includes one or more images and a textual report associated with the one or more images. Aspects also include selecting a key image from each of the one or more images from each of the plurality of imaging studies and extracting one or more discriminating image features from a region of interest within the key image. Aspects further include processing the textual report associated with the one or more images to detect one or more concept labels, assigning an initial label from the one or more concept labels to the one or more discriminating image features, and learning an association between each of the one or more discriminating image features and the one or more concept labels.

Abstract: A method for extracting information from electronic documents, including: learning terms and term variants from a training corpus, wherein the terms and the term variants correspond to a specialized dictionary related to the training corpus; generating a list of negative indicators found in the training corpus; performing a partial match of the terms and the term variants in a set of electronic documents to create initial match results; and performing a negation test using the negative indicators and a positive terms test using the terms and the term variants on the initial match results to remove matches from the initial match results that fail either the negation test or the positive terms test, resulting in final match results.

Abstract: Embodiments of the invention relate to ranking of data and retrieval of data or relationships of the data responsive to the ranking. A data model is represented as a graph, with edges in the graph linking related concepts, and an assertion represented in the graph as a reified n-ary relation. The graph is ingested though traversal and storage of the node paths. The traversal includes concepts and categories. In addition, neighborhood of one or more adjacent concepts are followed and stored in relation to the node paths. The ingested graph is converted into a set of flat document structures supported by information ranking and a retrieval framework.

Abstract: Embodiments of the present invention relate to discriminating between normal and abnormal left ventricles in echocardiography. In one embodiment, a method of and computer program product for discriminating between normal and abnormal left ventricles in echocardiography are provided. A first region of a first image of a heart is located. The first region depicts a chamber of the heart. A boundary of the first region is determined. A predetermined shape is compared to the boundary. A first plurality of parameters is determined that, when applied to the predetermined shape, conforms the predetermined shape to the boundary. The first plurality of parameters is provided to a classifier. An indication of normality or abnormality is received from the classifier.

Abstract: Methods and arrangements for automatic ground truth generation of medical image collections. Aspects include receiving a plurality of imaging studies, wherein each imaging study includes one or more images and a textual report associated with the one or more images. Aspects also include selecting a key image from each of the one or more images from each of the plurality of imaging studies and extracting one or more discriminating image features from a region of interest within the key image. Aspects further include processing the textual report associated with the one or more images to detect one or more concept labels, assigning an initial label from the one or more concept labels to the one or more discriminating image features, and learning an association between each of the one or more discriminating image features and the one or more concept labels.

Abstract: Machine learning solutions compensate for data missing from input (training) data and thereby arrive at a predictive model that is based upon, and consistent with, the training data. The predictive model can be generated within a learning algorithm framework by transforming the training data to generate modality or similarity kernels. Similarity values can be generated for these missing similarity values.

Abstract: Embodiments relate to detecting coronary stenosis through spatio-temporal tracking. Aspects include extracting a coronary artery tree from each of a sequence of angiogram images, creating a mean artery tree from the extracted coronary artery trees, and projecting the mean artery tree back onto each of the sequence of angiogram images to recover a complete coronary artery tree for each of the sequence of angiogram images. Aspects also include extracting one or more tubular sections from each of the sequence of angiogram images, estimating an arterial width for each of the one or more tubular sections from each of the sequence of angiogram images, and creating a spatio-temporal surface from the arterial widths of the one or more tubular sections over a time spanned by the sequence of angiogram images. Aspects further include detecting a minimum in the spatio-temporal surface and determining if the minimum is indicative of stenosis.

Abstract: Embodiments relate to selection systems and methods for identifying patient cohorts. One aspect is a computer-implemented method including receiving one or more cohort criteria for a clinical study. The cohort criteria indicate at least one of inclusion criteria for inclusion in the clinical study and exclusion criteria for exclusion from the clinical study. The cohort criteria are transformed into a constraint tree. The constraint tree is traversed, by a computer processor, to apply the cohort criteria to the plurality of patient records. As a result of the traversing, a patient cohort of one or more patients is identified from among a plurality of patient records.