Abstract: Embodiments discussed herein facilitate generation of a prognosis for a medical condition based on determination of one or more histomorphometric features for tiles of a whole slide image (WSI) that have been identified as the most prognostically significant tiles of the WSI. A first set of embodiments discussed herein relates to training of a fully convolutional network (FCN) to determine the prognostic significance of pixels of a WSI. A second set of embodiments discussed herein relates to determination of a prognosis based on analysis of regions identified as the most prognostically significant by a trained FCN.

Abstract: Embodiments discussed herein facilitate determination of risk of relapse of AML post-transplant. One example embodiment is a method, comprising: accessing a digital whole slide image (WSI) comprising a post-transplant bone marrow aspirate from a patient that has acute myeloid leukemia (AML); segmenting one or more myeloblasts on the digital WSI; extracting one or more features from the segmented one or more myeloblasts; providing the one or more features extracted from the segmented one or more myeloblasts to a trained machine learning model; and receiving, from the trained machine learning model, an indication of a risk of relapse of the AML.

Abstract: Embodiments access a digitized image of tissue demonstrating non-small cell lung cancer (NSCLC), the tissue including a plurality of cellular nuclei; segment the plurality of cellular nuclei represented in the digitized image; extract a set of nuclear radiomic features from the plurality of segmented cellular nuclei; generate at least one nuclear cell graph (CG) based on the plurality of segmented nuclei; compute a set of CG features based on the nuclear CG; provide the set of nuclear radiomic features and the set of CG features to a machine learning classifier; receive, from the machine learning classifier, a probability that the tissue will respond to immunotherapy, based, at least in part, on the set of nuclear radiomic features and the set of CG features; generate a classification of the tissue as a responder or non-responder based on the probability; and display the classification.

Abstract: Embodiments discussed herein facilitate determination of a response to treatment and/or a prognosis for a tumor based at least in part on features of tumor-associated vasculature (TAV). One example embodiment is a method, comprising: accessing a medical imaging scan of a tumor, wherein the tumor is segmented on the medical imaging scan; segmenting tumor-associated vasculature (TAV) associated with the tumor based on the medical imaging scan; extracting one or more features from the TAV; providing the one or more features extracted from the TAV to a trained machine learning model; and receiving, from the machine learning model, one of a predicted response to a treatment for the tumor or a prognosis for the tumor.

Abstract: Embodiments discussed herein facilitate determination of whether lesions are benign or malignant. One example embodiment is a method, comprising: accessing medical imaging scan(s) that are each associated with distinct angle(s) and each comprise a segmented region of interest (ROI) of that medical imaging scan comprising a lesion associated with a first region and a second region; providing the first region(s) of the medical imaging scan(s) to trained first deep learning (DL) model(s) of an ensemble and the second region(s) of the medical imaging scan(s) to trained second DL model(s) of the ensemble; and receiving, from the ensemble of DL models, an indication of whether the lesion is a benign architectural distortion (AD) or a malignant AD.

Abstract: Embodiments discussed herein facilitate segmentation of histological primitives from stained histology of renal biopsies via deep learning and/or training deep learning model(s) to perform such segmentation. One example embodiment is configured to access a first histological image of a renal biopsy comprising a first type of histological primitives, wherein the first histological image is stained with a first type of stain; provide the first histological image to a first deep learning model trained based on the first type of histological primitive and the first type of stain; and receive a first output image from the first deep learning model, wherein the first type of histological primitives is segmented in the first output image.

Abstract: Embodiments facilitate predicting a patient prostate cancer (PCa) DECIPHER risk group. A first set of embodiments relates to training of a machine learning classifier to compute a probability that a patient is a member of a DECIPHER low/intermediate risk group based on radiomic features extracted from bi-parametric magnetic resonance imaging (bpMRI) images. A second set of embodiments relates to classifying a patient as a member of DECIPHER low/intermediate risk group, or DECIPHER high-risk group, based on radiomic features extracted from bpMRI imagery of the patient.

Abstract: Embodiments facilitate stratification of a patient according to prostate cancer (PCa) risk. A first set of embodiments relates to training of a machine learning classifier to compute a probability that a patient has a low-risk of PCa progression based on intratumoral radiomic features and peritumoral radiomic features extracted from multi-parametric magnetic resonance imaging (mpMRI) images. A second set of embodiments relates to classifying a patient as low-risk of PCa progression, or high-risk of PCa progression, based on radiomic features extracted from mpMRI imagery of the patient.

Abstract: Embodiments discussed herein facilitate training and/or employing a machine learning model trained on radiomic features, quantitative histomorphometric features, and molecular expression to generate prognoses for treatment of tumors. One example embodiment can access a medical imaging scan of a tumor; segment a peri-tumoral region around the tumor; extract one or more radiomic features from the one or more of the tumor or the peri-tumoral region; provide the one or more radiomic features to a machine learning model trained based on the one or more radiomic features of a training set, one or more quantitative histomorphometric (QH) features of the training set, and a molecular expression of the training set; and receive a prognosis associated with the tumor from the machine learning model.

Abstract: Embodiments discussed herein facilitate building and/or employing a clinical-radiomics score for determining tumor prognoses based on a combination of a radiomics risk score generated by a machine learning model and clinico-pathological factors. One example embodiment can perform actions comprising: accessing a medical imaging scan of a tumor; segmenting a peri-tumoral region around the tumor; extracting one or more intra-tumoral radiomic features from the tumor and one or more peri-tumoral radiomic features from the peri-tumoral region; providing the one or more intra-tumoral radiomic features and the one or more peri-tumoral radiomic features to a trained machine learning model; receiving a radiomic risk score (RRS) associated with the tumor from the machine learning model; determining a clinical-radiomics score based on the RRS and one or more clinico-pathological factors; and generating a prognosis for the tumor based on the clinical-radiomics score.

Abstract: Embodiments discussed herein facilitate building and/or employing model(s) for determining tumor prognoses based on a combination of radiomic features and pathomic features. One example embodiment can perform actions comprising: providing, to a first machine learning model, at least one of: one or more intra-tumoral radiomic features associated with a tumor or one or more peri-tumoral radiomic features associated with a peri-tumoral region around the tumor; receiving a first predicted prognosis associated with the tumor from the first machine learning model; providing, to a second machine learning model, one or more pathomic features associated with the tumor; receiving a second predicted prognosis associated with the tumor from the second machine learning model; and generating a combined prognosis associated with the tumor based on the first predicted prognosis and the second predicted prognosis.

Abstract: Embodiments facilitate prediction of anti-vascular endothelial growth (anti-VEGF) therapy response in DME or RVO patients. A first set of embodiments discussed herein relates to training of a machine learning classifier to determine a prediction for response to anti-VEGF therapy based on a vascular network organization via Hough transform (VaNgOGH) descriptor generated based on FA images of tissue demonstrating DME or RVO. A second set of embodiments discussed herein relates to determination of a prediction of response to anti-VEGF therapy for a DME or RVO patient (e.g., non-rebounder vs. rebounder, response vs. non-response) based on a VaNgOGH descriptor generated based on FA imagery of the patient.

Abstract: Embodiments discussed herein facilitate determination of risk of recurrence of atrial fibrillation (AF) after ablation based on fractal features. One example embodiment is configured to generate a binary mask of at least a portion of a CT scan of a heart of a patient with AF; compute one or more radiomic fractal-based features from at least one of the binary mask or the portion of the CT scan; provide the one or more radiomic fractal-based features to a trained machine learning (ML) classifier; and receive a prediction from the trained ML classifier of whether or not the AF will recur after AF ablation, wherein the prediction is based at least in part on the one or more radiomic fractal-based features.

Abstract: Embodiments discussed herein facilitate training and/or employing a combined model employing machine learning and deep learning outputs to generate prognoses for treatment of tumors. One example embodiment can extract radiomic features from a tumor and a peri-tumoral region; provide the intra-tumoral and peri-tumoral features to two separate machine learning models; provide the segmented tumor and peri-tumoral region to two separate deep learning models; receive predicted prognoses from each of the machine learning models and each of the deep learning models; provide the predicted prognoses to a combined machine learning model; and receive a combined predicted prognosis for the tumor from the combined machine learning model.

Abstract: Embodiments discussed herein facilitate training deep learning models to generate synthetic versions of histological texture features and employing such deep learning models. One example embodiment is an apparatus configured to convert a stained histological image to grayscale; extract patches from the grayscale image; for each patch of the plurality of patches: provide that patch to a deep learning model trained to generate a synthetic version of a texture feature; and obtain an associated patch from the deep learning model that indicates an associated value of the synthetic version of the histology texture feature for each pixel of that patch; and merge the associated patches for each patch of the plurality of patches to generate an associated feature map for the stained histological image, wherein the associated feature map indicates the associated value of the synthetic version of the histology texture feature for each pixel of the plurality of pixels.

Abstract: Embodiments predict early stage NSCLC recurrence, and include an image acquisition circuit configured to access an image of a region of tissue demonstrating early-stage NSCLC including a plurality of cellular nuclei; a nuclei detecting and segmentation circuit configured to detect a member of the plurality; and classify the member as a tumor infiltrating lymphocyte (TIL) nucleus or non-TIL nucleus; a spatial TIL feature circuit configured to extract spatial TIL features from the plurality, the spatial TIL features including a first subset of features based on the spatial arrangement of TIL nuclei, and a second subset of features based on the spatial relationship between TIL nuclei and non-TIL nuclei; and an NSCLC recurrence classification circuit configured to compute a probability that region will experience recurrence based on the spatial TIL features; and generate a classification of the region as likely or unlikely to experience recurrence based on the probability.

Abstract: Methods, apparatus, and other embodiments predict response to immunotherapy from computed tomography (CT) images of a region of tissue demonstrating non-small cell lung cancer (NSCLC). One example apparatus includes a set of circuits that includes an image acquisition circuit that accesses a CT image of a region of tissue demonstrating cancerous pathology, a tumoral definition circuit that generates a tumoral surface boundary that defines a tumoral volume, a peritumoral segmentation circuit that generates a peritumoral region based on the tumoral surface boundary, and that segments the peritumoral region into a plurality of annular bands, a radiomics circuit that extracts a set of discriminative features from the tumoral volume and at least one of the plurality of annular bands, and a classification circuit that classifies the ROI as a responder or a non-responder, based, at least in part, on the set of discriminative features.

Abstract: Embodiments facilitate prediction of anti-vascular endothelial growth (anti-VEGF) therapy response in DME patients. A first set of embodiments discussed herein relates to training of a machine learning classifier to determine a prediction for response to anti-VEGF therapy based on a set of graph-network features and a set of morphological features generated based on FA images of tissue demonstrating DME. A second set of embodiments discussed herein relates to determination of a prediction of response to anti-VEGF therapy for a DME patient (e.g., non-rebounder vs. rebounder, response vs. non-response) based on a set of graph-network features and a set of morphological features generated based on FA imagery of the patient.

Abstract: Embodiments discussed herein relate to accessing a digitized image associated with a patient of tissue demonstrating breast cancer pathology; segmenting a tumor region represented in the digitized image; segmenting collagen fibers represented in the tumor region; computing collagen vectors based on the segmented collagen fibers; generating an orientation co-occurrence matrix based on the collagen vectors; computing a collagen fiber orientation disorder feature based on the co-occurrence matrix; upon determining that the collagen fiber orientation feature exceeds a threshold value: generating a prognosis of the region of tissue as unlikely to experience breast cancer recurrence; upon determining that the collagen fiber orientation feature is less than or equal to the threshold value: generating a prognosis of the region of tissue as likely to experience breast cancer recurrence; classifying the patient as high-risk of recurrence or low-risk of recurrence based, at least in part, on the prognosis; and displayin

Abstract: Embodiments discussed herein facilitate determining a diagnosis and/or prognosis for prostate cancer based at least in part on three-dimensional (3D) pathomic feature(s). One example embodiment comprises a computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations, comprising: accessing a three-dimensional (3D) optical image volume comprising a prostate gland of a patient; segmenting the prostate gland of the 3D optical image volume; extracting one or more features from the segmented prostate gland, wherein the one or more features comprise at least one 3D pathomic feature; and generating, via a model based at least on the one or more features, one or more of the following based at least on the extracted one or more features: a classification of the prostate gland as one of benign or malignant, a Gleason score associated with the prostate gland, or a prognosis for the patient.