Abstract: There is provided a method of training a machine learning model, comprising: for each set of sample medical images depicting calcification within a target anatomical structure wherein each set includes non-contrast medical image(s) and contrast enhanced medical image(s), correlating between calcifications depicted in the target anatomical structure of the contrast enhanced image(s) with corresponding calcifications depicted in the target anatomical structure of the non-contrast medical image(s), computing calcification parameter(s) for calcification depicted in the respective target anatomical structure, labelling each contrast enhanced medical image with the calcification parameter(s), and training the machine learning model on a training dataset that includes the contrast enhanced medical images of the sets, each labelled with ground truth label of a respective calcification parameter(s), for generating an outcome indicative of a target calcification parameter(s) for calcification depicted in the target ana

Abstract: There is provided a method of training a machine learning model, comprising: for each set of sample medical images depicting calcification within a target anatomical structure wherein each set includes non-contrast medical image(s) and contrast enhanced medical image(s), correlating between calcifications depicted in the target anatomical structure of the contrast enhanced image(s) with corresponding calcifications depicted in the target anatomical structure of the non-contrast medical image(s), computing calcification parameter(s) for calcification depicted in the respective target anatomical structure, labelling each contrast enhanced medical image with the calcification parameter(s), and training the machine learning model on a training dataset that includes the contrast enhanced medical images of the sets, each labelled with ground truth label of a respective calcification parameter(s), for generating an outcome indicative of a target calcification parameter(s) for calcification depicted in the target ana

Abstract: Systems and techniques are disclosed for improvement of machine learning systems based on enhanced training data. An example method includes accessing a database storing associations between objects included in medical images and classifications of the objects. A risk assessment model adapted to determine a risk condition for an object is accessed, the assessment based on features of the object. Risk conditions associated with respective objects are determined based on the risk assessment model. A group of objects associated with a first risk condition is identified. An interactive user interface is generated for display, the user interface concurrently displaying images of the group of objects. The interactive user interface enables a user to select subsets of images to be concurrently assigned a user-selected classification. User selected classifications are provided to a machine learning system adapted to update the risk assessment model based on the classifications to increase accuracy of the model.

Abstract: There is provided a method for training a deep convolutional neural network (CNN) for detecting an indication of likelihood of abnormality, comprising: receiving anatomical training images, each including an associated annotation indicative of abnormality for the whole image without an indication of location of the abnormality, executing, for each anatomical training image: decomposing the anatomical training image into patches, computing a feature representation of each patch, computing for each patch, according to the feature representation of the patch, a probability that the patch includes an indication of abnormality, setting a probability indicative of likelihood of abnormality in the anatomical image according to the maximal probability value computed for one patch, and training a deep CNN for detecting an indication of likelihood of abnormality in a target anatomical image according to the patches of the anatomical training images, the one patch, and the probability set for each respective anatomical

Abstract: There is provided, a method of selecting patients for treatment, comprising: feeding anatomical image(s) of a patient depicting a target tissue, and non-imaging clinical parameters of the patient into neural network component(s) of a model, outputting by the neural network component(s), an intermediate vector storing a plurality of embedding values computed for the anatomical image(s), a plurality of values outputted by a dense layer of the neural network component(s) in response to an input of at least some of the non-imaging clinical parameters, and an intermediate value indicative of likelihood of malignancy for the target tissue, feeding into a classifier component of the model, a feature vector created from the intermediate vector and the plurality of non-imaging clinical parameters, and selecting patients for treatment according to an indication of likelihood of malignancy in the target tissue outputted by the model.

Abstract: There is provided a method for training a deep convolutional neural network (CNN) for detecting an indication of likelihood of abnormality, comprising: receiving anatomical training images, each including an associated annotation indicative of abnormality for the whole image without an indication of location of the abnormality, executing, for each anatomical training image: decomposing the anatomical training image into patches, computing a feature representation of each patch, computing for each patch, according to the feature representation of the patch, a probability that the patch includes an indication of abnormality, setting a probability indicative of likelihood of abnormality in the anatomical image according to the maximal probability value computed for one patch, and training a deep CNN for detecting an indication of likelihood of abnormality in a target anatomical image according to the patches of the anatomical training images, the one patch, and the probability set for each respective anatomical

Abstract: Systems and techniques are disclosed for improvement of machine learning systems based on enhanced training data. An example method includes accessing a database storing associations between objects included in medical images and classifications of the objects. A risk assessment model adapted to determine a risk condition for an object is accessed, the assessment based on features of the object. Risk conditions associated with respective objects are determined based on the risk assessment model. A group of objects associated with a first risk condition is identified. An interactive user interface is generated for display, the user interface concurrently displaying images of the group of objects. The interactive user interface enables a user to select subsets of images to be concurrently assigned a user-selected classification. User selected classifications are provided to a machine learning system adapted to update the risk assessment model based on the classifications to increase accuracy of the model.

Abstract: A system for detection and classification of findings in an image, comprising at least one hardware processor configured to: receive the image; process the image by a plurality of convolutional and pooling layers of a neural network to produce a plurality of feature maps; process one of the feature maps by some of the layers and another plurality of layers to produce a plurality of region proposals; produce a plurality of region of interest (ROI) pools by using a plurality of pooling layers to downsample the plurality of region proposals with each one of the plurality of feature maps; process the plurality of ROI pools by at least one concatenation layer to produce a combined ROI pool; process the combined ROI pool by a classification network comprising some other of the convolutional and pooling layers to produce one or more classifications; and output the one or more classifications.

Abstract: According to some aspects, a computer-implemented method of registering a first image and a second image is provided. The method comprises computer-implemented acts of logically dividing the first image into a first plurality of regions, logically dividing the second image into a second plurality of regions, projecting the first plurality of regions and the second plurality of regions into a lower dimensional space using random projections, determining, for each of the projected first plurality of regions, at least one of the projected second plurality of regions that is closest according to first criteria, and determining a transform that brings each of the projected first plurality of regions into a closest correspondence with the respective at least one of the projected second plurality of regions according to second criteria, the transform indicating the registration of the first image and the second image.

Abstract: According to some aspects, a computer-implemented method of registering a first image and a second image is provided. The method comprises computer-implemented acts of logically dividing the first image into a first plurality of regions, logically dividing the second image into a second plurality of regions, projecting the first plurality of regions and the second plurality of regions into a lower dimensional space using random projections, determining, for each of the projected first plurality of regions, at least one of the projected second plurality of regions that is closest according to first criteria, and determining a transform that brings each of the projected first plurality of regions into a closest correspondence with the respective at least one of the projected second plurality of regions according to second criteria, the transform indicating the registration of the first image and the second image.

Abstract: A novel multiscale approach that combines segmentation with classification to detect abnormal brain structures in medical imagery, and demonstrate its utility in detecting multiple sclerosis lesions in 3D MRI data. The method uses segmentation to obtain a hierarchical decomposition of a multi-channel, anisotropic MRI scan. It then produces a rich set of features describing the segments in terms of intensity, shape, location, and neighborhood relations. These features are then fed into a decision tree-based classifier, trained with data labeled by experts, enabling the detection of lesions in all scales. Unlike common approaches that use voxel-by-voxel analysis, our system can utilize regional properties that are often important for characterizing abnormal brain structures. Experiments show successful detections of lesions in both simulated and real MR images.