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, comprising: accessing medical images of subjects, depicting contrast phases of contrast administered to the respective subject, accessing for a first subset of the medical images, metadata indicating a respective contrast phase, wherein a second subset of the medical images are unassociated with metadata, mapping each respective contrast phase of the contrast phases to a respective time interval indicating estimated amount of time from a start of contrast administration to time of capture of the respective medical image, creating a training dataset, by labelling images of the first subset with a label indicating the respective time interval, and including the second subset as non-labelled images, and training the ML model using the training dataset for generating an outcome of a target time interval indicating estimated amount of time from the start of contrast administration, in response to an input of a target medical image.

Abstract: There is provided a method, comprising feeding a medical image into a detector component trained on a first training dataset of medical images annotated with ground truth boxes depicting a visual finding, obtaining boxes each associated with a respective box score indicative of likelihood of the visual finding, converting each respective box into a respective patch, feeding patches into a patch classifier trained on a second training dataset that includes patches extracted from the ground truth box labels of the first training dataset, wherein a patch score for a patch corresponds to a box score obtained from a box corresponding to the patch, obtaining patch scores indicative of likelihood of the visual finding being depicted, and computing a dot product of the box scores and the patch scores, and providing the dot product as an image-level indication of likelihood of the visual finding being depicted in the medical image.

Abstract: There is provided a method, comprising: providing a training dataset including, medical images and corresponding text based reports, and concurrently training a natural language processing (NLP) machine learning (ML) model for generating a NLP category for a target text based report and a visual ML model for generating a visual finding for a target image, by: training the NLP ML model using the text based reports of the training dataset and a ground truth comprising the visual finding generated by the visual ML model in response to an input of the images corresponding to the text based reports of the training dataset, and training the visual ML model using the images of the training dataset and a ground truth comprising the NLP category generated by the NLP ML model in response to an input of the text based reports corresponding to the images of the training dataset.

Abstract: There is provided a computer implemented method for identification of an indication of visual object(s) in anatomical image(s) of a target individual, comprising: providing anatomical image(s) of a body portion of a target individual, inputting the anatomical image(s) into a classification component of a neural network (NN) and into a segmentation component of the NN, feeding a size feature into the classification component of the NN, wherein the size feature comprises an indication of a respective size of each segmented visual object identified in the anatomical image(s), the size feature computed according to segmentation data outputted by the segmentation component for each pixel element of the anatomical image(s), and computing, by the classification component of the NN, an indication of visual object(s) in the anatomical image(s).

Abstract: There is provided a method of computing a likelihood of malignancy in a mammographic image, comprising: receiving a single channel 2D mammographic image including a single pixel intensity value for each pixel thereof, converting the single channel 2D mammographic image into a multi channel 2D mammographic image including multiple pixel intensity value channels for each pixel thereof, computing by a first sub-classifier according to the whole multi channel image, a first score indicative of likelihood of malignancy within the whole multi channel image, computing by a second sub-classifier according to each respective patch extracted from the multi channel image, a respective second score indicative of likelihood of malignancy within each respective patch, and computing by a gating sub-classifier according to the first score and the second scores, an indication of likelihood of malignancy and a location of the malignancy.

Abstract: There is provided a system for computing a single-label neural network for detection of an indication of an acute medical condition, comprising: hardware processor(s) executing a code for: providing a multi-label training dataset including anatomical images each associated with a label indicative of visual finding type(s), or indicative of no visual finding types, training a multi-label neural network for detection of the visual finding types(s) in a target anatomical image according to the multi-label training dataset, creating a single-label training dataset including anatomical images each associated with a label indicative of the selected single visual finding type, or indicative of an absence of the single visual finding type, and training a single-label neural network for detection of the single visual finding type, by setting the trained multi-label neural network as an initial baseline of the single-label neural network, and fine-tuning and/or re-training the baseline according to the single-label tra

Abstract: A system for prioritizing patients for treatment, comprising: at least one hardware processor executing a code for: feeding anatomical images into a visual filter neural network for outputting a category indicative of a target body region depicted at a target sensor orientation and a rotation relative to a baseline, rejecting a sub-set of anatomical images classified into another category, rotating to the baseline images classified as rotated, identifying pixels for each image having outlier pixel intensity values denoting an injection of content, adjusting the outlier pixel intensity values to values computed as a function of non-outlier pixel intensity values, feeding each the remaining sub-set of images with adjusted outlier pixel intensity values into a classification neural network for detecting the visual finding type, generating instructions for creating a triage list for which the classification neural network detected the indication, wherein patients are selected for treatment based on the triage lis

Abstract: There is provided a computer implemented method for localizing target anatomical regions of interest (ROI) of a target individual, comprising: uniformly sub-sampling a plurality of 2D images having sequential index numbers within a 3D anatomical volume, feeding the plurality of sampled 2D images into a classifier for outputting a plurality of values on a normalized anatomical scale, fitting a linear model to the plurality of values and corresponding sequential index numbers, mapping by the linear model, the plurality of 2D images to the normalized anatomical scale, receiving an indication of at least one target anatomical ROI of a target individual, wherein each target anatomical ROI is mapped to the normalized anatomical scale, and providing a sub-set of the plurality of 2D images having values of the normalized anatomical scale corresponding to the received at least one target anatomical ROI.

Abstract: There is provided a method of training a neural network for reconstructing of a 3D point cloud from 2D image(s), comprising: extracting point clouds each represented by an ordered list of coordinates, from 3D anatomical images depicting a target anatomical structure, selecting one of the plurality of point clouds as a template, non-rigidly registering the template with each of the point clouds to compute a respective warped template having a shape of the respective point cloud and retaining the coordinate order of the template, wherein the warped templates are consistent in terms of coordinate order, receiving 2D anatomical images depicting the target anatomical structure depicted in corresponding 3D anatomical images, and training a neural network, according to a training dataset of the warped templates and corresponding 2D images, for mapping 2D anatomical image(s) into a 3D point cloud.

Abstract: There is provided a method of training a neural network for reconstructing of a 3D point cloud from 2D image(s), comprising: extracting point clouds each represented by an ordered list of coordinates, from 3D anatomical images depicting a target anatomical structure, selecting one of the plurality of point clouds as a template, non-rigidly registering the template with each of the point clouds to compute a respective warped template having a shape of the respective point cloud and retaining the coordinate order of the template, wherein the warped templates are consistent in terms of coordinate order, receiving 2D anatomical images depicting the target anatomical structure depicted in corresponding 3D anatomical images, and training a neural network, according to a training dataset of the warped templates and corresponding 2D images, for mapping 2D anatomical image(s) into a 3D point cloud.

Abstract: There is provided a computer implemented method for localizing target anatomical regions of interest (ROI) of a target individual, comprising: uniformly sub-sampling a plurality of 2D images having sequential index numbers within a 3D anatomical volume, feeding the plurality of sampled 2D images into a classifier for outputting a plurality of values on a normalized anatomical scale, fitting a linear model to the plurality of values and corresponding sequential index numbers, mapping by the linear model, the plurality of 2D images to the normalized anatomical scale, receiving an indication of at least one target anatomical ROI of a target individual, wherein each target anatomical ROI is mapped to the normalized anatomical scale, and providing a sub-set of the plurality of 2D images having values of the normalized anatomical scale corresponding to the received at least one target anatomical ROI.

Abstract: There is provided a method for predicting risk of osteoporotic fracture, comprising: receiving imaging data of a computed tomography (CT) scan of a body of a patient containing at least a bone portion, the CT scan being performed with settings selected for imaging of non-osteoporosis related pathology; processing the imaging data to identify the bone portion; automatically extracting features based on the imaging data denoting the identified bone portion; computing an osteoporotic fracture predictive factor indicative of the risk of developing at least one osteoporotic fracture in the patient, or the risk of the patient having at least one severe osteoporotic fracture, based on the extracted features, the predictive factor calculated by applying a trained osteoporotic fracture classifier to the extracted features, the osteoporotic fracture classifier trained from data from a plurality of CT scans performed with settings selected for imaging non-osteoporosis related pathology; and providing the predictive fact

Abstract: There is provided a method comprising: providing two anatomical images of a target individual, each captured at a unique orientation of the target individual, inputting first and second anatomical images respectively into a first and second convolutional neural network (CNN) of a classifier to respectively output first and second feature vectors, inputting a concatenation of the first and second feature vectors into a fully connected layer of the classifier, and computing an indication of distinct visual finding(s) present in the anatomical images by the fully connected layer, wherein the statistical classifier is trained on a training dataset including two anatomical images of each respective sample individual, each image captured at a respective unique orientation of the target individual, and a tag created based on an analysis that maps respective individual sentences of a text based radiology report to one of multiple indications of visual findings.

Abstract: There is provided a method of computing a likelihood of malignancy in a mammographic image, comprising: receiving a single channel 2D mammographic image including a single pixel intensity value for each pixel thereof, converting the single channel 2D mammographic image into a multi channel 2D mammographic image including multiple pixel intensity value channels for each pixel thereof, computing by a first sub-classifier according to the whole multi channel image, a first score indicative of likelihood of malignancy within the whole multi channel image, computing by a second sub-classifier according to each respective patch extracted from the multi channel image, a respective second score indicative of likelihood of malignancy within each respective patch, and computing by a gating sub-classifier according to the first score and the second scores, an indication of likelihood of malignancy and a location of the malignancy.

Abstract: There is provided a method for predicting risk of osteoporotic fracture, comprising: receiving imaging data of a computed tomography (CT) scan of a body of a patient containing at least a bone portion, the CT scan being performed with settings selected for imaging of non-osteoporosis related pathology; processing the imaging data to identify the bone portion; automatically extracting features based on the imaging data denoting the identified bone portion; computing an osteoporotic fracture predictive factor indicative of the risk of developing at least one osteoporotic fracture in the patient, or the risk of the patient having at least one severe osteoporotic fracture, based on the extracted features, the predictive factor calculated by applying a trained osteoporotic fracture classifier to the extracted features, the osteoporotic fracture classifier trained from data from a plurality of CT scans performed with settings selected for imaging non-osteoporosis related pathology; and providing the predictive fact

Abstract: There is provided a method for segmentation of an image of a target patient, comprising: providing a target 2D slice and nearest neighbor 2D slice(s) of a 3D anatomical image, and computing, by a trained multi-slice fully convolutional neural network (multi-slice FCN), a segmentation region including a defined intra-body anatomical feature that extends spatially across the target 2D slice and the nearest neighbor 2D slice(s), wherein the target 2D slice and each of the nearest neighbor 2D slice(s) are processed by a corresponding contracting component of sequential contracting components of the multi-slice FCN according to the order of the target 2D slice and the nearest neighbor 2D slice(s) based on the sequence of 2D slices extracted from the 3D anatomical image, wherein outputs of the sequential contracting components are combined and processed by a single expanding component that outputs a segmentation mask for the target 2D slice.

Abstract: There is provided a method of computing a likelihood of malignancy in a mammographic image, comprising: receiving a single channel 2D mammographic image including a single pixel intensity value for each pixel thereof, converting the single channel 2D mammographic image into a multi channel 2D mammographic image including multiple pixel intensity value channels for each pixel thereof, computing by a first sub-classifier according to the whole multi channel image, a first score indicative of likelihood of malignancy within the whole multi channel image, computing by a second sub-classifier according to each respective patch extracted from the multi channel image, a respective second score indicative of likelihood of malignancy within each respective patch, and computing by a gating sub-classifier according to the first score and the second scores, an indication of likelihood of malignancy and a location of the malignancy.

Abstract: A system for prioritizing patients for treatment, comprising: at least one hardware processor executing a code for: feeding anatomical images into a visual filter neural network for outputting a category indicative of a target body region depicted at a target sensor orientation and a rotation relative to a baseline, rejecting a sub-set of anatomical images classified into another category, rotating to the baseline images classified as rotated, identifying pixels for each image having outlier pixel intensity values denoting an injection of content, adjusting the outlier pixel intensity values to values computed as a function of non-outlier pixel intensity values, feeding each the remaining sub-set of images with adjusted outlier pixel intensity values into a classification neural network for detecting the visual finding type, generating instructions for creating a triage list for which the classification neural network detected the indication, wherein patients are selected for treatment based on the triage lis

Abstract: There is provided a method for predicting risk of osteoporotic fracture, comprising: receiving imaging data of a computed tomography (CT) scan of a body of a patient containing at least a bone portion, the CT scan being performed with settings selected for imaging of non-osteoporosis related pathology; processing the imaging data to identify the bone portion; automatically extracting features based on the imaging data denoting the identified bone portion; computing an osteoporotic fracture predictive factor indicative of the risk of developing at least one osteoporotic fracture in the patient, or the risk of the patient having at least one severe osteoporotic fracture, based on the extracted features, the predictive factor calculated by applying a trained osteoporotic fracture classifier to the extracted features, the osteoporotic fracture classifier trained from data from a plurality of CT scans performed with settings selected for imaging non-osteoporosis related pathology; and providing the predictive fact