Abstract: Automatic detection of valve disease from analysis of Doppler waveforms exploiting the echocardiography annotations is provided. In various embodiments, a frame is selected from a medical video. The selected frame depicts a valve of interest. A Doppler envelope is extracted from the selected frame. Based on the frame and the Doppler envelope, one or more measurements indicative of a disease condition are extracted.

Abstract: Automatic discrepancy detection in medical data is provided. In various embodiments, a disease label for a present study is determined, indicative of a disease condition. Retrospective review of a plurality of electronic medical records is performed. The retrospective review comprises searching for electronic medical records relevant to the disease condition. The earliest electronic medical record reflecting the disease condition is identified. Based on the earliest electronic medical record reflecting the disease condition, one or more of the electronic medical records having an omission or inconsistency is identified. The one or more of the electronic medical records having an omission or inconsistency are flagged for supplemental review in a worklist.

Abstract: Automatic detection of disease presence from combining disease-specific measurements with textual descriptions of disease and its severity in unstructured textual reports is provided. In various embodiments, a knowledge graph of clinical concepts is read. Based on the knowledge graph, a plurality of associations are determined between disease names, symptoms, anatomical abnormalities, and qualifiers. A corpus of clinical reports is read. Based on the plurality of associations, a plurality of portions indicative of a disease condition are located within the corpus of clinical reports. Within each of the plurality of portions, name/value pairs are detected corresponding to measurements indicative of the disease condition. The measurements indicative of the disease condition are extracted.

Abstract: Sequential learning techniques, such as auto-context, that apply the output of an intermediate classifier as contextual features for its subsequent classifier have shown impressive performance for semantic segmentation. It is shown that these methods can be interpreted as an approximation technique derived from a Bayesian formulation. To improve the effectiveness of applying this approximation technique, a new sequential learning approach is proposed for semantic segmentation that solves a segmentation problem by breaking it into a series of simplified segmentation problems. Sequentially solving each of the simplified problems along the path leads to a more effective way for solving the original segmentation problem. To achieve this goal, a learning-based method is proposed to generate simplified segmentation problems by explicitly controlling the complexities of the modeling classifiers. Promising results were reported on the 2013 SATA canine leg muscle segmentation dataset.

Abstract: A solution is presented for cardiac CT viewpoint recognition to identify the desired images for a specific view and subsequent processing and anatomy recognition. A new set of features is presented to describe the global binary pattern of cardiac CT images characterized by the highly attenuating components of the anatomy in the image. Five classic image texture and edge feature sets are used to devise a classification approach based on SVM classification, class likelihood estimation, and majority voting, to classify 2D cardiac CT images into one of six viewpoint categories that include axial, sagittal, coronal, two chamber, four chamber, and short axis views. Such an approach results in an accuracy of 99.4% in correct labeling of the viewpoints.

Abstract: A solution is presented for cardiac CT viewpoint recognition to identify the desired images for a specific view and subsequent processing and anatomy recognition. A new set of features is presented to describe the global binary pattern of cardiac CT images characterized by the highly attenuating components of the anatomy in the image. Five classic image texture and edge feature sets are used to devise a classification approach based on SVM classification, class likelihood estimation, and majority voting, to classify 2D cardiac CT images into one of six viewpoint categories that include axial, sagittal, coronal, two chamber, four chamber, and short axis views. Such an approach results in an accuracy of 99.4% in correct labeling of the viewpoints.

Abstract: Embodiments of the present invention relate to discriminating between normal and abnormal left ventricles in echocardiography. In some embodiments, a first region of a first image of a heart is located by clustering. The first region depicts a chamber of the heart. The chamber has a chamber shape. A boundary of the first region is determined by contour tracing a retaining the traced contour overlapping the first region. A predetermined shape is compared to the boundary. The predetermined shape had been determined without reference to the first image. A first plurality of parameters is determined that, when applied to the predetermined shape, conforms the predetermined shape to the boundary and minimizes at least one error between the predetermined shape and the boundary. An indication of normality or abnormality is determine from the first plurality of parameters.

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: Embodiments of the invention relate to arrangements for ascertaining time-dependent associations between inputted comparative effectiveness research (CER) variables from patient data are. Each CER variable is represented via at least one unit time series, and a similarity metric with respect to pairs of CER variables is determined. The determining includes comparing at least one unit time series from each of at least two CER variables.

Abstract: Embodiments relate to creating a classification rule by combining classifiers. Aspects include receiving N training samples d, wherein each of the N training samples d includes a label l, receiving T classifiers C, and initializing a first random weight vector ? for the N training samples d. Aspects also include initializing a second random weight vector ? for the T classifiers C and creating, by a processor, the classification rule by identifying a combination of one or more of the T classifiers C that best approximates the label l for each of the N training samples d based on the first random weight vector and the second random weight vector ?.

Abstract: Embodiments of the invention relate to a method, system, and computer program product to automate image classification with respect to coronary vessels in an angiography sequence. Two primary elements are employed, including training and recognition. Training pertains to the pre-processing images and extracting salient features that characterize the appearance of coronary arteries under different viewpoints. Recognition pertains to extraction of features from a new image sequence and determining a classification boundary for the new image from previously classified and labeled image sequences.

Abstract: Embodiments of the invention relate to automating image classification with respect to coronary vessels in an angiography sequence. Two primary elements are employed, including training and recognition. Training pertains to the pre-processing images and extracting salient features that characterize the appearance of coronary arteries under different viewpoints. Recognition pertains to extraction of features from a new image sequence and determining a classification boundary for the new image from previously classified and labeled image sequences.

Abstract: A method for estimating a heart period is disclosed. The heart period is detected from an ECG recording. ECG data is acquired, and converted into electronic ECG images. The data is processed to prepare for estimation of a heart period. The heart period is estimated based upon an average of intervals between a plurality of detected peaks of electronic electrocardiogram waveforms. The peaks are determined by taking a product of a filtered electronic ECG signal with a wandering baseline removed, a difference between the upper and lower ECG envelopes of the electronic ECG images, and a first order derivative of a derived ECG waveform.

Abstract: Embodiments of the invention relate to arrangements for ascertaining time-dependent associations between inputted comparative effectiveness research (CER) variables from patient data are. Each CER variable is represented via at least one unit time series, and a similarity metric with respect to pairs of CER variables is determined. The determining includes comparing at least one unit time series from each of at least two CER variables.

Abstract: Embodiments of the invention relate to automating image classification with respect to coronary vessels in an angiography sequence. Two primary elements are employed, including training and recognition. Training pertains to the pre-processing images and extracting salient features that characterize the appearance of coronary arteries under different viewpoints. Recognition pertains to extraction of features from a new image sequence and determining a classification boundary for the new image from previously classified and labeled image sequences.

Abstract: Embodiments of the invention relate to a method, system, and computer program product to automate image classification with respect to coronary vessels in an angiography sequence. Two primary elements are employed, including training and recognition. Training pertains to the pre-processing images and extracting salient features that characterize the appearance of coronary arteries under different viewpoints. Recognition pertains to extraction of features from a new image sequence and determining a classification boundary for the new image from previously classified and labeled image sequences.

Abstract: A method for estimating a heart period is disclosed. The heart period is detected from an ECG recording. ECG data is acquired, and converted into electronic ECG images. The data is processed to prepare for estimation of a heart period. The heart period is estimated based upon an average of intervals between a plurality of detected peaks of electronic electrocardiogram waveforms. The peaks are determined by taking a product of a filtered electronic ECG signal with a wandering baseline removed, a difference between the upper and lower ECG envelopes of the electronic ECG images, and a first order derivative of a derived ECG waveform.

Abstract: A method of automatically matching schemas begins by extracting schemas from sources and targets. Then, source and target attributes are extracted from the schemas. Each source schema will have multiple source attributes and each target schema will also have multiple target attributes. The source attributes and the target attributes are presented as nodes in a bipartite graph. This bipartite graph has edges between nodes that are related to each other. A plurality of similarity scores are defined between each set of related nodes. Each of the similarity scores is based on a different context-specific cue of the attributes that the nodes represent. These context-specific cues can comprise lexical name, semantic name, type, structure, functional mappings, etc. An overall weight is computed for each edge in the bipartite graph by combining the similarity scores of each set of nodes that form an edge.

Abstract: A method and system and computer program product for estimating a heart period is disclosed. The heart period is detected from an ECG recording. ECG data is acquired, and converted into electronic ECG images. The data is processed to prepare for estimation of a heart period. The heart period is estimated based upon an average of intervals between a plurality of detected peaks of electronic electrocardiogram waveforms. The peaks are determined by taking a product of a filtered electronic ECG signal with a wandering baseline removed, a difference between the upper and lower ECG envelopes of the electronic ECG images, and a first order derivative of a derived ECG waveform.

Abstract: A data processing system is provided that comprises a processor, a random access memory for storing data and programs for execution by the processor, and computer readable instructions stored in the random access memory for execution by the processor to perform a method for clustering data points in a multidimensional dataset in a multidimensional image space. The method comprises generating a multidimensional image from the multidimensional dataset; generating a pyramid of multidimensional images having varying resolution levels by successively performing a pyramidal sub-sampling of the multidimensional image; identifying data clusters at each resolution level of the pyramid by applying a set of perceptual grouping constraints; and determining levels of a clustering hierarchy by identifying each salient bend in a variation curve of a magnitude of identified data clusters as a function of pyramid resolution level.