Abstract: Methods are herein provided for decision support in diagnosis of a disease in a subject, and for extracting features from a multi-slice data set. Systems for computer-aided diagnosis are provided. The systems take as input a plurality of medical data and produces as output a diagnosis based upon this data. The inputs may consist of a combination of image data and clinical data. Diagnosis is performed through feature selection and the use of one or more classifier algorithms.

Abstract: A method includes determining, with a computer implemented classifier, a health state of tissue interest of a subject in at least one pair of images of the subject based on a predetermined set of longitudinal features of the tissue of interest of the subject in the at least one pair of images of the subject. The at least one pair of images of the subject includes a first image of the tissue of interest acquired at a first moment in time and a second image of the tissue of interest acquired at a second moment in time. The first and second moments in time are different moments in time. The method further includes visually displaying indicia indicative of the determined health state.

Abstract: An ultrasound system for performing cancer grade mapping includes an ultrasound imaging device (10) that acquires ultrasound imaging data. An electronic data processing device (30) is programmed to generate an ultrasound image (34) from the ultrasound imaging data, and to generate a cancer grade map (42) by (i) extracting sets of local features from the ultrasound imaging data that represent map pixels of the cancer grade map and (ii) classifying the sets of local features using a cancer grading classifier (46) to generate cancer grades for the map pixels of the cancer grade map. A display component (20) displays the cancer grade map, for example overlaid on the ultrasound image as a color-coded cancer grade map overlay. The cancer grading classifier is learned from a training data set (64) comprising sets of local features extracted from ultrasound imaging data at biopsy locations and labeled with histopathology cancer grades.

Abstract: A system and method for context-dependent data filtering for clinical decision support are disclosed. The system and method comprise determining values for characteristics of a present case, determining whether the present case is a special case based on the determined values, receiving input from a user verifying that the present case is the special case and saving the present case to a database containing a compilation of cases if the user verifies that the present case is the special case.

Abstract: This invention relates to a method and device for case-based decision support. It proposes that a case-based decision support system is trained on inputs from several radiologists in order to have a “baseline” system, and then the system provides an option to a radiologist to refine the baseline system based on his/her inputs which either refine weights of features for similarity distance computation directly or provide new similarity ground truth clusters. By enabling modifying the similarity distance computation based on user inputs, this invention adapts similarity ground truth to different users with different experience and/or different opinions.

Abstract: When evaluating patient cases to determine complexity thereof, a computer-aided stratification technique is applied to analyze historical patient case diagnoses and correctness thereof in order to calculate a stratification score (20) for each of a plurality of abnormality types and/or anatomical locations. When a new patient case is received, the computer-aided stratification technique is applied to evaluate the patient case in view of historical data and assign a stratification score thereto. A ranked list (21) of current patient cases can be generated according to stratification scores, and physician workload can be adjusted as a function thereof so that workload is balanced across physicians and/or according to physician experience level.

Abstract: A method includes obtaining, in electronic format, an image (102) including a medical image display region (104) and an information display region (106). The at least one of the medical image display region or the information display region includes graphical indicia representing at least one of an annotation (110, 112, 114, 116) or alphanumeric information (118, 120, 122, 124, 126, 128, 130, 132, 134, 136, 138, 140). The method further includes evaluating pixels of the image to identify pixels including the graphical indicia representing an annotation or alphanumeric information of interest in the image. The method further includes extracting the annotation or alphanumeric information of interest from the identified graphical indicia from the image. The method further includes inserting the extracted annotation or alphanumeric information of interest in an electronically formatted clinical report for the image.

Abstract: A method generates images based on context-aware imaging. The method includes acquiring a first image of a patient using first image acquisition parameters. The method includes determining, within the first image, an area as a function of first data associated with the patient. The method includes determining modification data as a function of at least one of (a) second data corresponding to the determined area and (b) the first data. The method includes determining second image acquisition parameters as a function of the modification data and the first image acquisition parameters. The method includes acquiring a second image of the patient using the second image acquisition parameters.

Abstract: Described herein are a system(s) and/or a method(s) that associate results of medical procedures for a particular medical finding over a lifetime of the finding. A method includes tagging, with a same finding unique identifier tag (FUID), electronic formatted medical results from different events for a same finding of a patient, storing the electronic formatted medical results along with the FUID, wherein the stored tagged different electronic formatted medical results provide a longitudinal record for the finding from discovery of the finding through a last event for the finding. A system includes a FUID repository that stores a single FUID for each different finding for each different patient, and a new FUID generator that generates a new FUID for a new finding. The FUIDs in the FUID repository are accessible to a plurality of medical facilities which tag electronic data for a same finding with a same FUID.

Abstract: A classifier (20) is trained by a feature matrix (18, 18?) made up of feature vectors (F11, . . . , Fkm). The feature vectors are generated by operating on each of a plurality (k) of training image data sets with each of a plurality (m) of image processing algorithms (121, . . . , 12m) to generate processed and segmented images. Features of the segmented regions are extracted (14) to generate the feature vectors. In this manner, the classifier is trained with data generated with a variety of image processing algorithms.

Abstract: A non-transitory computer-readable storage medium storing a set of instructions executable by a processor. The set of instructions is operable to receive a current patient medical image of a current patient, compare the current patient medical image to a plurality of previous patient medical images, each of the previous patient medical images corresponding to a previous patient, select one of the previous patients based on a geometric similarity between the previous patient medical image of the selected one of the previous patients and the current patient medical image, and determine an initial radiation treatment plan based on a radiation treatment plan of the selected one of the previous patients.

Abstract: A method includes receiving a signal indicative of an experience level of a clinician evaluating patient data, and, in response to determining whether the experience level satisfies a predetermined experience level threshold, prompting, via a graphical user interface, for an input indicating a first impression based on the evaluation of the patient data, automatically populating a first sub-set of the fields in the electronically formatted structured medical report based on the first impression, populating a second different sub-set of the fields in the electronically formatted structured medical report based on an input indicative of clinician selected entries, finalizing the electronically formatted structured medical report in response to clinician confirmation of the populated electronically formatted structured medical report, and storing the finalized electronically formatted structured medical report in a data repository.

Abstract: Methods for performing genetic algorithm-based feature selection are provided herein. In certain embodiments, the methods include steps of applying multiple data splitting patterns to a learning data set to build multiple classifiers to obtain at least one classification result; integrating the at least one classification result from the multiple classifiers to obtain an integrated accuracy result; and outputting the integrated accuracy result to a genetic algorithm as a fitness value for a candidate feature subset, in which genetic algorithm-based feature selection is performed.

Abstract: A non-transitory computer-readable storage medium storing a set of instructions executable by a processor. The set of instructions is operable to receive a current patient medical image of a current patient, compare the current patient medical image to a plurality of previous patient medical images, each of the previous patient medical images corresponding to a previous patient, select one of the previous patients based on a geometric similarity between the previous patient medical image of the selected one of the previous patients and the current patient medical image, and determine an initial radiation treatment plan based on a radiation treatment plan of the selected one of the previous patients.

Abstract: A non-transitory computer-readable storage medium storing a set of instructions executable by a processor. The set of instructions is operable to receive a current patient set of data relating to a current patient; compare the current patient set of data to a plurality of previous patient sets of data, each of the previous patient sets of data corresponding to a previous patient; select one of the previous patient sets of data based on a level of similarity between the selected previous patient set of data and the current patient set of data; and provide the selected previous patient set of data to a user.

Abstract: A system and method for context-dependent data filtering for clinical decision support are disclosed. The system and method comprise determining values for characteristics of a present case, determining whether the present case is a special case based on the determined values, receiving input from a user verifying that the present case is the special case and saving the present case to a database containing a compilation of cases if the user verifies that the present case is the special case.

Abstract: Methods and apparatus for training a system for developing a process of data mining, false positive reduction, computer-aided detection, computer-aided diagnosis and artificial intelligence are provided. A method includes choosing a training set from a set of training cases using systematic data scaling and creating a classifier based on the training set using a classification method. The classifier yields fewer false positives. The method is suitable for use with a variety of data mining techniques including support vector machines, neural networks and decision trees.

Abstract: Optimizing example-based computer-aided diagnosis (CADx) is accomplished by clustering volumes-of-interest (VOIs) (116) in a database (120) into respective clusters according to subjective assessment of similarity (S220). An optimal set of volume-of-interest (VOI) features is then selected for fetching examples such that objective assessment of similarity, based on the selected features, clusters, in a feature space, the database VOIs so as to conform to the subjectively-based clustering (S230). The fetched examples are displayed alongside the VOI to be diagnosed for comparison by the clinician. Preferably, the displayed example is user-selectable for further display of prognosis, therapy information, follow up information, current status, and/or clinical information retrieved from an electronic medical record (S260).

Abstract: An oncology monitoring system comprises: an image analysis module (42, 44) configured to perform an oncological monitoring operation based on images of a subject, for example acquired by positron emission tomography (PET) and computed tomography (CT); and a clinical guideline support module (10). The clinical guideline support module is configured to: display a graphical flow diagram (GFD) of a clinical therapy protocol for treating the subject comprising graphical blocks (B0, B1 B2, B3, B4, B5, B21, B211, B22, B221, B222, B223, B23, B231, B232) representing therapeutic or monitoring operations of the clinical therapy protocol including at least one monitoring operation performed by the image analysis module; annotate a graphical block of the graphical flow diagram with subject-specific information pertaining to a therapeutic or monitoring operation represented by the graphical block; and display an annotation (POP) of a graphical block (B211) responsive to selection of the graphical block by a user.

Abstract: A clinical decision support (CDS) system comprises a patient treatment histories database (10, 32) and a patient case navigation tool (10, 30) operative to select a patient treatment history from the patient treatment histories database and to display a flowchart representation (50) of at least a portion of the selected patient treatment history. Optionally, the navigation tool (10, 30) is further operative to selectively display a flowchart representation (64, 66) of a portion or all of a patient nonspecific treatment guideline not coinciding with the selected patient treatment history. Optionally, the CDS system further comprises a patient records query engine (10, 40) operative to receive a query and apply same against the patient treatment histories database to retrieve query results, the navigation tool (10, 30) being further operative to generate a query responsive to user input and to display query results retrieved for the query.