Abstract: The present disclosure, in some embodiments, relates to a non-transitory computer-readable medium storing computer-executable instructions. The computer readable medium is configured to cause a processor to access an image volume of a rectum comprising a rectal tumor. A forward mapping is generated based on non-rigidly registering a healthy rectal atlas to the image volume. The forward mapping is inverted to generate an inverse mapping from the image volume to the healthy rectal atlas. Based on the inverse mapping, a plurality of deformation vectors, associated with a deformation within a rectal wall of the rectum, are determined. Magnitude based deformation features and orientation based deformation features are computed from the plurality of deformation vectors. One or more of the magnitude based deformation features and one or more of the orientation based deformation features are utilized to determine a response of a patient to a chemoradiation treatment.

Abstract: In some embodiments, the present disclosure relates to a method for generating a prognosis. The method may be performed by providing one or more digitized biopsy images of a patient having a glioma. One or more necrotic regions and one or more non-necrotic regions are identified within the one or more digitized biopsy images using a first deep learning algorithm. A second deep learning algorithm is applied to the one or more non-necrotic regions to identify glioblastoma multiforme (GBM) histopathological indicators within the one or more non-necrotic regions.

Abstract: In some embodiments, the present disclosure relates to a non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations, that include obtaining an imaging data set having one or more digitized images from one or more patients with glioblastoma (GBM). A machine learning pipeline is utilized to generate a prognosis using one or more machine learning features that describe a morphology of the one or more digitized images. Utilizing the machine learning pipeline includes utilizing a first machine learning stage to segment the one or more digitized images to identify one or more cellular tumor (CT) regions; and utilizing a second machine learning stage to generate one or more machine learning features that describe a morphology of the one or more CT regions and to further determine the prognosis from one or more machine learning features.

Abstract: Embodiments facilitate generation of a prediction of long-term survival (LTS) or short-term survival (STS) of Glioblastoma (GBM) patients. A first set of embodiments discussed herein relates to training of a machine learning classifier to determine a prediction for LTS or STS based on a radiographic-deformation and textural heterogeneity (r-DepTH) descriptor generated based on radiographic images of tissue demonstrating GBM. A second set of embodiments discussed herein relates to determination of a prediction of disease outcome for a GBM patient of LTS or STS based on an r-DepTH descriptor generated based on radiographic imagery of the patient.

Abstract: Embodiments discussed herein facilitate determination of tumor mutation status based on context and spatial information. One example embodiment can access a MRI scan of a tumor comprising voxels; extract radiomic feature(s) from the voxels; generate a spatial feature descriptor indicating probabilities the tumor has a first mutation status and a second mutation status, based on the MRI scan, a first population atlas for the first mutation status, and a second population atlas for the second mutation status; provide the radiomic feature(s) and the spatial feature descriptor to a machine learning model; and receive, via the machine learning model, a map indicating, for each voxel of the voxels, a probability of the first mutation status for that voxel and a probability of the second mutation status for that voxel, wherein the map is based at least on the one or more radiomic features and the spatial feature descriptor.

Abstract: Embodiments discussed herein facilitate determination of tumor mutation status based on context and spatial information. One example embodiment can access a MRI scan of a tumor comprising voxels; extract radiomic feature(s) from the voxels; generate a spatial feature descriptor indicating probabilities the tumor has a first mutation status and a second mutation status, based on the MRI scan, a first population atlas for the first mutation status, and a second population atlas for the second mutation status; provide the radiomic feature(s) and the spatial feature descriptor to a machine learning model; and receive, via the machine learning model, a map indicating, for each voxel of the voxels, a probability of the first mutation status for that voxel and a probability of the second mutation status for that voxel, wherein the map is based at least on the one or more radiomic features and the spatial feature descriptor.

Abstract: The present disclosure, in some embodiments, relates to a non-transitory computer-readable medium storing computer-executable instructions. The computer readable medium is configured to cause a processor to access an image volume of a rectum comprising a rectal tumor. A forward mapping is generated based on non-rigidly registering a healthy rectal atlas to the image volume. The forward mapping is inverted to generate an inverse mapping from the image volume to the healthy rectal atlas. Based on the inverse mapping, a plurality of deformation vectors, associated with a deformation within a rectal wall of the rectum, are determined. Magnitude based deformation features and orientation based deformation features are computed from the plurality of deformation vectors. One or more of the magnitude based deformation features and one or more of the orientation based deformation features are utilized to determine a response of a patient to a chemoradiation treatment.

Abstract: Embodiments discussed herein facilitate determination of responsiveness to chemoradiation treatment in rectal cancer patients based on structural deformation features obtained from a pre- or post-treatment medical imaging. One example embodiment can perform operations comprising: accessing an image volume of a rectum comprising a rectal tumor; generating a forward mapping based on non-rigidly registering a healthy rectal atlas to the image volume; inverting the forward mapping to generate an inverse mapping from the image volume to the healthy rectal atlas; determining, based on the inverse mapping, an associated deformation magnitude for each voxel of a plurality of voxels associated with the rectum; computing one or more structural deformation features based on the associated deformation magnitudes for the plurality of voxels; and predicting via a classifier whether or not the rectal tumor will respond to the chemoradiation treatment based at least in part on the one or more structural deformation features.

Abstract: Embodiments discussed herein facilitate generating a quantitative population atlas of tumor progression (TP) versus pseudo-progression (PsP) in Glioblastoma (GBM). A first set of embodiments discussed herein relates to generating a quantitative population atlas of TP versus PsP based on a plurality of multi-parametric (mpMRI) studies of a population of patients demonstrating GBM. A second set of embodiments discussed herein relates to computing a probability that a patient will experience PsP or TP based on a DICE analysis of a mapping of a diagnostic mpMRI study associated with the patient into the quantitative population atlas space.

Abstract: Embodiments discussed herein facilitate determination of responsiveness to chemoradiation treatment in rectal cancer patients based on structural deformation features obtained from a pre- or post-treatment medical imaging. One example embodiment can perform operations comprising: accessing an image volume of a rectum comprising a rectal tumor; generating a forward mapping based on non-rigidly registering a healthy rectal atlas to the image volume; inverting the forward mapping to generate an inverse mapping from the image volume to the healthy rectal atlas; determining, based on the inverse mapping, an associated deformation magnitude for each voxel of a plurality of voxels associated with the rectum; computing one or more structural deformation features based on the associated deformation magnitudes for the plurality of voxels; and predicting via a classifier whether or not the rectal tumor will respond to the chemoradiation treatment based at least in part on the one or more structural deformation features.

Abstract: Embodiments access an image of a region of interest (ROI) demonstrating cancerous pathology; extract radiomic features from the ROI; define a radiomic feature expression scene based on the ROI and radiomic features; generate a cluster map by superpixel clustering the expression scene; generate an expression map by repartitioning the cluster map into expression levels; compute a textural and spatial phenotypes for the expression map based on the expression levels; construct a radiomic spatial textural (RADISTAT) descriptor by concatenating the textural and spatial phenotypes; provide the RADISTAT descriptor to a machine learning classifier; receive, from the machine learning classifier, a first probability that the ROI is a responder or non-responder, or a second probability that the ROI will experience long-term survival or short-term survival, based, at least in part, on the RADISTAT descriptor; and generate a classification of the ROI as a responder or non-responder, or long-term survivor or short-term surv

Abstract: Methods and apparatus quantify mass effect deformation in diagnostic images of patients demonstrating glioblastoma multiforme (GBM). One example apparatus includes an image acquisition circuit that acquires an image of a region of tissue demonstrating GBM pathology, a delineation circuit that segments a tumor region from the image, a pre-processing circuit that generates a pre-processed image by pre-processing the segmented image, a registration circuit that registers the pre-processed image with a template image of a healthy brain, a deformation quantification circuit that computes a set of differences between a position of a brain sub-structure represented in the registered image relative to the position of the brain sub-structure represented in the template image. Embodiments may include a classification circuit that classifies the region of tissue as a long or short-term survivor based, at least in part, on the set of differences.

Abstract: Embodiments discussed herein facilitate generating a quantitative population atlas of tumor progression (TP) versus pseudo-progression (PsP) in Glioblastoma (GBM). A first set of embodiments discussed herein relates to generating a quantitative population atlas of TP versus PsP based on a plurality of multi-parametric (mpMRI) studies of a population of patients demonstrating GBM. A second set of embodiments discussed herein relates to computing a probability that a patient will experience PsP or TP based on a DICE analysis of a mapping of a diagnostic mpMRI study associated with the patient into the quantitative population atlas space.

Abstract: Embodiments facilitate generation of a prediction of long-term survival (LTS) or short-term survival (STS) of Glioblastoma (GBM) patients. A first set of embodiments discussed herein relates to training of a machine learning classifier to determine a prediction for LTS or STS based on a radiographic-deformation and textural heterogeneity (r-DepTH) descriptor generated based on radiographic images of tissue demonstrating GBM. A second set of embodiments discussed herein relates to determination of a prediction of disease outcome for a GBM patient of LTS or STS based on an r-DepTH descriptor generated based on radiographic imagery of the patient.

Abstract: Embodiments access an image of a region of interest (ROI) demonstrating cancerous pathology; extract radiomic features from the ROI; define a radiomic feature expression scene based on the ROI and radiomic features; generate a cluster map by superpixel clustering the expression scene; generate an expression map by repartitioning the cluster map into expression levels; compute a textural and spatial phenotypes for the expression map based on the expression levels; construct a radiomic spatial textural (RADISTAT) descriptor by concatenating the textural and spatial phenotypes; provide the RADISTAT descriptor to a machine learning classifier; receive, from the machine learning classifier, a first probability that the ROI is a responder or non-responder, or a second probability that the ROI will experience long-term survival or short-term survival, based, at least in part, on the RADISTAT descriptor; and generate a classification of the ROI as a responder or non-responder, or long-term survivor or short-term surv

Abstract: Methods and apparatus quantify mass effect deformation in diagnostic images of patients demonstrating glioblastoma multiforme (GBM). One example apparatus includes an image acquisition circuit that acquires an image of a region of tissue demonstrating GBM pathology, a delineation circuit that segments a tumor region from the image, a pre-processing circuit that generates a pre-processed image by pre-processing the segmented image, a registration circuit that registers the pre-processed image with a template image of a healthy brain, a deformation quantification circuit that computes a set of differences between a position of a brain sub-structure represented in the registered image relative to the position of the brain sub-structure represented in the template image. Embodiments may include a classification circuit that classifies the region of tissue as a long or short-term survivor based, at least in part, on the set of differences.

Abstract: Methods, apparatus, and other embodiments associated with distinguishing disease phenotypes using co-occurrence of local anisotropic gradient orientations (CoLIAGe) are described. One example apparatus includes a set of logics that acquires a radiologic image (e.g., MRI image) of a region of tissue demonstrating disease pathology (e.g., cancer), computes a gradient orientation for a pixel in the MRI image, computes a significant orientation for the pixel based on the gradient orientation, constructs a feature vector that captures a discretized entropy distribution for the image based on the significant orientation, and classifies the phenotype of the disease pathology based on the feature vector. Embodiments of example apparatus may generate and display a heatmap of entropy values for the image. Example methods and apparatus may operate substantially in real-time. Example methods and apparatus may operate in two or three dimensions.

Abstract: Methods, apparatus, and other embodiments associated with distinguishing disease phenotypes using co-occurrence of local anisotropic gradient orientations (CoLIAGe) are described. One example apparatus includes a set of logics that acquires a radiologic image (e.g., MRI image) of a region of tissue demonstrating disease pathology (e.g., cancer), computes a gradient orientation for a pixel in the MRI image, computes a significant orientation for the pixel based on the gradient orientation, constructs a feature vector that captures a discretized entropy distribution for the image based on the significant orientation, and classifies the phenotype of the disease pathology based on the feature vector. Embodiments of example apparatus may generate and display a heatmap of entropy values for the image. Example methods and apparatus may operate substantially in real-time. Example methods and apparatus may operate in two or three dimensions.

Abstract: This invention relates to computer-assisted diagnostics and classification of prostate cancer. Specifically, the invention relates to segmentation of the prostate boundary on MRI images, cancer detection using multimodal multi-protocol MR data; and their integration for a computer-aided diagnosis and classification system for prostate cancer.

Abstract: This invention relates to computer-assisted diagnostics and classification of prostate cancer. Specifically, the invention relates to segmentation of the prostate boundary on MRI images, cancer detection using multimodal multi-protocol MR data; and their integration for a computer-aided diagnosis and classification system for prostate cancer.