Abstract: Systems and methods for selecting a prior comparison study. One system includes an electronic processor configured to, for a medical image study associated with a patient, select a prior comparison image study. The electronic processor is also configured to automatically determine, based on monitored user interaction with the selected prior comparison image study, a usefulness of the selected prior comparison image study. The electronic processor is also configured to automatically update a selection model based on the usefulness of the prior comparison image study to a user.

Abstract: Methods and systems for rending medical images within a web browser application. The web browser application retrieves a worklist and automatically determines an image study from the worklist to be cached. The web browser application retrieves at least one medical image included in the image study. The web browser application creates a web database for storing the at least one medical image within the browser application. When a user selects a medical image for display within the web browser, the web browser application determines whether the medical image is stored in the web database. When the medical image is stored in the web database, the web browser application retrieves the medical image from the web database. When the medical image is not stored in the web database, the web browser application retrieves the medical image from a remote image repository.

Abstract: Systems and computer-implemented methods of performing image registration. One method includes receiving a first image and a second image acquired from a patient at different times and, in each of the first image and the second image, detecting an upper boundary of an imaged object in an image coordinate system and detecting a lower boundary of the imaged object in the image coordinate system. The method further includes, based on the upper boundary and the lower boundary of each of the first image and the second image, cropping and padding at least one of the first image and the second image to create an aligned first image and an aligned second image and executing a registration model on the aligned first image and the aligned second image to compute a deformation field between the aligned first image and the aligned second image.

Abstract: Systems and methods for selectively processing image studies with an artificial intelligence system. One system includes an electronic processor configured to select an image study awaiting review and update a workflow status of the image study to a first status indicating that the image study has been claimed for review by the artificial intelligence system. The electronic processor is also configured to apply at least one of the plurality of rules to the image study to determine whether the image study is applicable for processing by the artificial intelligence system, and, in response to determining the image study is not applicable for processing by the artificial intelligence system based on the at least one of the plurality of rules, update the workflow status associated with the image study to a second status to make the image study available for claiming by a manual reviewer or another artificial intelligence system.

Abstract: Methods and systems of summarizing medical data. One system includes an electronic processor configured to analyze medical data to extract a medical concept and a plurality of additional attributes of the medical concept and store the medical concept and the plurality of additional attributes. The electronic processor is configured to generate a first medical summary associated with the patient, where the first medical summary is based on the stored medical concept and at least a first additional attribute included in the stored plurality of additional attributes. The electronic processor is configured to receive a user interaction with the first medical summary. The electronic processor is configured to generate a second medical summary associated with the patient based on the user interaction, the second medical summary is based on the stored medical concept and at least a second additional attribute included in the stored plurality of additional attributes.

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: Methods and systems for processing medical images. One method includes, in response to startup of an application using an algorithm, creating a server process supporting a programming language associated with the algorithm and loading a plurality of deep learning models used by the algorithm into a memory of the server process to create in-memory models. The method also includes processing a first set of one or more medical images with the server process using the algorithm and at least one model selected from the in-memory models, maintaining the in-memory models in the memory of the server process after processing the first set of one or more medical images, and, in response to a request to process a second set of one or more medical images, processing the second set of one or more medical images using the algorithm and at least one of the in-memory models.

Abstract: A conversation management system provides a conversational computing interface that manages verbal exchanges between a computer (e.g., artificial intelligence) and a human operator. In a medical embodiment, conversational input from the computing system is generated based on medical knowledge, uses deep learning algorithms, and/or intelligently tracks the state of a conversation so as to the most relevant data to the user.

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 conversation management system provides a conversational computing interface that manages verbal exchanges between a computer (e.g., artificial intelligence) and a human operator. In a medical embodiment, conversational input from the computing system is generated based on medical knowledge, uses deep learning algorithms, and/or intelligently tracks the state of a conversation so as to the most relevant data to the user.

Abstract: Methods and systems for training computer-aided condition detection systems. One method includes receiving a plurality of images for a plurality of patients, some of the images including an annotation associated with a condition; iteratively applying a first deep learning network to each of the images to produce an attention map, a feature map, and an image-level probability of the condition for each of the images; iteratively applying a second deep learning network to each feature map produced by the first network to produce a plurality of outputs; training the first network based on the attention map produced for each image; and training the second network based on the output produced for each of the patients. The second network includes a plurality of convolution layers and a plurality of convolutional long short-term memory (LSTM) layers. Each of the outputs includes a patient-level probability of the condition for one of the patients.

Abstract: A computer system identifies a medical condition in a patient. A trained machine learning image generator is used to generate a set of training images based on three-dimensional patient imaging data, wherein each training image is labeled with a projection angle of the corresponding two-dimensional projection. Using the set of training images, a machine learning image classifier model is trained to identify patient rotation angles in x-ray images. X-ray images are processed with the machine learning image classifier model to identify patient rotation angles. A machine learning medical condition classifier model is trained to identify a medical condition using the labeled x-ray images. The machine learning medical condition classifier model determines an indication of the medical condition in a patient's x-ray image. Embodiments of the present invention further include a method and program product for identifying a medical condition in a patient in substantially the same manner described above.

Abstract: Methods and systems for clinical report generation. One system includes an electronic processor configured to receive a query image and determine a similarity metric for a plurality of medical images, where the similarity metric represents a similarity between the query image and each of the plurality of medical images. The electronic processor is also configured to determine a predetermined number of medical images from the plurality of medical images based on the similarity metric for each of the plurality of medical images. The electronic processor is also configured to rank a plurality of reports, where each of the plurality of reports correspond to one of the predetermined number of medical images. The electronic processor is also configured to generate a clinical report including information extracted from at least one of the plurality of reports based on the ranking of the plurality of reports.

Abstract: Methods and systems are directed to training an artificial intelligence engine. One system includes an electronic processor configured obtain a set of reports corresponding to a set of medical images, determine a label for a finding of interest, and identify one or more ambiguous reports in the set of repots. Ambiguous reports do not include a positive label or a negative label for the finding of interest. The electronic processor is also configured to generate an annotation for each of the one or more ambiguous reports in the set of reports, and train the artificial intelligence engine using a training set including the annotation for each of the one or more ambiguous reports and non-ambiguous reports in the set of reports. A result of the training is generation of a classification model for the label for the finding of interest.

Abstract: Methods and systems for detecting a vertebral fracture within an x-ray. One method includes receiving a chest x-ray image and identifying a plurality of vertebrae represented in the chest x-ray image. The method further includes extracting a plurality of image patches from the chest x-ray image, each image patch of the plurality of image patches including a portion of the chest x-ray image representing one of the plurality of vertebrae identified in the chest x-ray image. The method further includes sequencing the plurality of image patches into an ordered sequence of image patches, and assigning, with a deep learning model applied to the ordered sequence of image patches, a classification to each of the plurality of image patches indicating whether the image patch represents a fractured vertebra or an unfractured vertebra.

Abstract: Techniques for dynamic visualization of data are provided. A plurality of therapies is received, where each of the plurality of therapies is associated with a respective plurality of guidelines. A guideline tree is generated based on the plurality of therapies, where each leaf node in the guideline tree represents a respective therapy, and where each edge in the guideline tree represents a respective guideline. A visual depiction of the guideline tree is generated. Further, a first plurality of attributes associated with a first patient is received, and a first modified visual depiction of the guideline tree is generated based on the first plurality of attributes.

Abstract: Computer based methods, systems, and computer readable media for intelligently accessing various types of pharmaceutical information in a content repository and ranking drugs at the variant level, gene level, and pathway level. In some cases, drugs that target the same gene, gene variant, or biological pathway may be ranked based upon in vitro, pre-clinical, clinical, or post-clinical evidence. To determine ranking of a plurality of drugs, information pertaining to drug administration is analyzed for the drugs. For a plurality of drugs, attributes corresponding to the drug are determined, wherein the attributes include a variant or a gene targeted by the drug, and a biological pathway comprising the targeted variant or gene. The plurality of drugs are ranked according to a drug effectiveness score based on one or more of a determined efficacy, potency, or toxicity.

Abstract: Systems and methods for developing a classification model for classifying medical reports, such as radiology reports. One method includes selecting, from a corpus of reports, a training set and a testing set, assigning labels of a modality and an anatomical focus to the reports in both sets, and extracting a sparse representation matrix for each set based on features in the training set. The method also includes learning, with one or more electronic processors, a correlation between the features of the training set and the corresponding labels using a machine learning classifier, thereby building a classification model and testing the classification model on the reports in the testing set for accuracy using the sparse representation matrix of the testing set. The method further includes predicting, with the classification model, labels of an anatomical focus and a modality for remaining reports in the corpus not included in the sets.

Abstract: A method, computing platform, and computer program product are provided for evaluating data quality during a clinical trial. A computing platform receives, for a clinical trial, study design information including a set of parameters and corresponding parameter values related to data quality of the clinical trial. During the clinical trial, the computing platform receives query-related information associated with queries from at least some of a plurality of participants of the clinical trial. The computing platform applies the study design information and the query-related information to at least one trained machine learning model to calculate a predicted data quality score indicating data quality for the clinical trial. At least one suggestion for improving the data quality is determined and the predicted data quality score and the at least one suggestion for improving the data quality are output.

Abstract: A plurality of attributes are extracted from a plurality of electronic health records, where each electronic health record is associated with a patient in a plurality of patients. Additionally, a training data set and a scoring data set are generated based on the plurality of attributes, and a patient similarity model is trained based on the training data set. A precision cohort is identified, where the precision cohort includes patients in the plurality of patients from the scoring data set that are similar to a first patient based on an electronic health record of the first patient and the similarity model. At least one result statistic for each of a plurality of treatments given to patients in the precision cohort is determined, and a first treatment of the plurality of treatments is selected for the first patient based at least in part on the determined result statistics.