Case Western Reserve University

Rutgers, the State University of New Jersey

The Cleveland Clinic Foundation

University of Pennsylvania

Other

The United States Government As Represented by the Department of Veterans Affairs

University of Pittsburgh

Boston University

Elucid Bioimaging Inc.

University of Pa.

Uh Cleveland Medical Center

Apsam Imaging Corp.

The United States Government As Represente

Anant Madabhushi

Vamsidhar Velcheti

Nathaniel Braman

Andrew Janowczyk

Pallavi Tiwari

Mirabela Rusu

Cheng Lu

Mehdi Alilou

Prateek Prasanna

Mahdi Orooji

Satish E Viswanath

Kaustav Bera

Xiangxue Wang

Pranjal Vaidya

Michael D Feldman

Ajay Basavanhally

Sahirzeeshan Ali

George C Lee

Robert Gilkeson

John Tomaszewski

Mark Rosen

Jacob Antunes

Niha Beig

Philip Linden

Soumya Ghose

Haibo Wang

Patrick Leo

Cristian Barrera

Fabio Gonzalez

Rakesh Shiradkar

Shannon C Agner

Sunil K Srivastava

Justis P Ehlers

Robert Toth

Rachel Sparks

Thomas Atta-Fosu

Kavya Ravichandran

Zhouping Wei

Yuanqi Xie

Mina Chung

Marwa Ismail

Sagar Rakshit

Angel Alfonso Cruz Roa

Yijiang Chen

Jun Xu

Andrew J Buckler

Joseph Willis

Dimitris Metaxas

Jianbo Shi

James P Monaco

Kazuaki Nakane

Sanjay Gupta

Hersh Bhargava

Nicholas P Reder

Yao Fu

Lyndsay Harris

Vinay Varadan

James Hamilton

Sharat Chandran

Shridar Ganesan

Anna Gawlik

Jonathan Chappelow

John Tomaszeweski

Scott Doyle

Can Koyuncu

German Corredor

Eduardo Romero

Michael LaBarbera

Marjan Firouznia

Gavin Hanson

Laura Barisoni

John Sedor

Catherine Jayapandian

Charlems Alvarez Jimenez

Tristan Maidment

Eliot G Peyster

Haoda Lu

Albert Feeny

Jhimli Mitra

Chaoyang Yan

Xiangshan Fan

Andrei S Purysko

Kenneth B Margulies

Jeffrey Eben

Jeffrey John Nirschl

Lin Li

Priti Lal

Afshin Dowlati

Mohammadhadi Khorrami

Ahmad Algohary

Prantesh Jain

Jonathan Teng-Chieh Liu

German Corredor Prada

Khoi Le

Salendra Singh

Haojia Li

Angel Cruz-Roa

The present disclosure relates to a non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations. The operations include extracting one or more image characterization metrics from respective ones of a plurality of digitized images within an imaging data set. The plurality of digitized images have batch effects. The operations further include identifying a plurality of batch effect groups of the digitized images using the one or more image characterization metrics, and dividing the plurality of batch effect groups between a training set and/or a validation set. The training set and/or the validation set include some of the plurality of digitized images associated with respective ones of the plurality of batch effect groups.

Batch effect mitigation in digitized images

The present disclosure relates to a method. The method may be performed by accessing data derived from one or more routine clinical medical imaging scans including a lesion in which the lesion and associated vasculature are segmented in a three-dimensional segmentation. At least two features are extracted from the three-dimensional segmentation of the associated vasculature. The at least two features include at least one feature indicative of a morphology of the associated vasculature or a portion thereof, and at least one feature indicative of a function of the associated vasculature or a portion thereof. The at least two features, and/or one or more statistics of the at least two features, are provided to a machine learning model trained to make a prediction concerning the lesion. The prediction concerning the lesion is received from the machine learning model.

Tumor characterization and outcome prediction through quantitative measurements of tumor-associated vasculature

Embodiments include accessing a set of digital pathology (DP) images having an imaging parameter; applying a low-computational cost histology quality control (HistoQC) pipeline to the DP images, where the low-computational cost HistoQC pipeline computes a first set of image metrics associated with a DP image, and assigns the DP image to a first or a second, different cohort based on the imaging parameter and the first set of image metrics; applying a first, higher-computational-cost HistoQC pipeline to a member of the first cohort; applying a second, different higher-computation-cost HistoQC pipeline to a member of the second cohort; where the first or second, higher-computational-cost HistoQC pipeline determines an artifact-free region of the member of the first or second cohort, respectively, and classifies the member of the first or second cohort, respectively, as suitable or unsuitable for downstream computation or diagnostic analysis based, at least in part, on the artifact free region.

Quality control for digital pathology slides

Embodiments classify lung nodules by accessing a 3D radiological image of a region of tissue, the 3D image including a plurality of voxels and slices, a slice having a thickness; segmenting the nodule represented in the 3D image across contiguous slices, the nodule having a 3D volume and 3D interface, where the 3D interface includes an interface voxel; partitioning the 3D interface into a plurality of nested shells, a nested shell including a plurality of 2D slices, a 2D slice including a boundary pixel; extracting a set of intra-perinodular textural transition (Ipris) features from the 2D slices based on a normal of a boundary pixel of the 2D slices; providing the Ipris features to a machine learning classifier which computes a probability that the nodule is malignant, based, at least in part, on the set of Ipris features; and generating a classification of the nodule based on the probability.

Intra-perinodular textural transition (ipris): a three dimenisonal (3D) descriptor for nodule diagnosis on lung computed tomography (CT) images

The present disclosure relates to a non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations, including generating an imaging data set having both scan data and digitized biopsy data from a patient with small cell lung cancer (SCLC). Scan derived features are extracted from the scan data and biopsy derived features are extracted from the digitized biopsy data. A radiomic-pathomic risk score (RPRS) is calculated from one or more of the scan derived features and one or more of the biopsy derived features. The RPRS is indicative of a prognosis of the patient.

Combination of features from biopsies and scans to predict prognosis in SCLC

Various embodiments of the present disclosure are directed towards a method for generating a risk group classification for an African American (AA) patient. The method includes extracting a first plurality of architectural features from a digitized H&E slide image of the AA patient. A risk score for the AA patient is generated based on the first plurality of architectural features, where the risk score is prognostic of overall survival (OS) of the AA patient. The risk group classification is generated for the AA patient, where generating the risk group classification includes classifying the AA patient into either a high risk group or a low risk group based on the risk score, where the high risk group indicates the AA patient will die before a threshold date and the low risk group indicates the AA patient will die after or on the threshold date.

Computational features of tumor-infiltrating lymphocyte (TIL) architecture

Embodiments discussed herein facilitate determination of cancer stages based at least in part on shape, size, and/or texture features of cancer nuclei. One example embodiment is a method, comprising: accessing at least a portion of a digital whole slide image (WSI) comprising a tumor; segmenting (e.g., via a first deep learning model) the tumor on the at least the portion of the digital WSI; segmenting (e.g., via a second deep learning model) cancer nuclei in the segmented tumor; extracting one or more features from the segmented cancer nuclei; providing the one or more features extracted from the segmented cancer nuclei to a trained machine learning model; and receiving, from the machine learning model, an indication of a cancer stage of the tumor.

Distinguishing colon cancer stages based on computationally derived morphological features of cancer nuclei

Embodiments discussed herein facilitate determination of one of a probability of prostate cancer recurrence-free survival or a risk factor associated with prostate cancer based on intra-tumor stromal morphology. Example embodiments can perform operations comprising: accessing a digitized histological image of a prostate of a patient, wherein the histological image comprises a region of interest associated with prostate cancer; identifying nuclei of intra-tumoral stromal cells within the region of interest; extracting, for the region of interest of the digitized histological image, one or more features describing the structure of the intra-tumoral stromal cells; and generating, via a model based at least on the one or more features, one of a probability of prostate cancer recurrence-free survival or a risk score associated with prostate cancer for the patient based at least on the extracted one or more features.

Population-specific prediction of prostate cancer recurrence based on stromal morphology features

Embodiments predict response to neoadjuvant chemotherapy (NAC) in breast cancer (BCa) from pre-treatment dynamic contrast enhanced magnetic resonance imaging (DCE-MRI). Embodiments compute, using a machine learning (ML) classifier, a first probability of response based on a set of radiomic features extracted from a tumoral region represented in a pre-treatment DCE-MRI image of a region of tissue (ROT) demonstrating BCa; extract patches from the tumoral region; provide the patches to a convolutional neural network (CNN); receive, from the CNN, a pixel-level localized patch probability of response; compute a second probability of response based on the pixel-level localized patch probability; compute a combined ML probability from the first and second probabilities; compute a final probability of response based on the combined ML probability and clinical information associated with the ROT; classify the ROT as a responder or non-responder based on the final probability of response; and display the classification.

Predicting neo-adjuvant chemotherapy response from pre-treatment breast magnetic resonance imaging using artificial intelligence and HER2 status

Embodiments include accessing an image of a region of tissue demonstrating cancerous pathology; detecting a plurality of cells represented in the image; segmenting a cellular nucleus of a first member of the plurality of cells and a cellular nucleus of at least one second, different member of the plurality of cells; extracting a set of nuclear morphology features from the plurality of cells; constructing a feature driven local cell graph (FeDeG) based on the set of nuclear morphology features and a spatial relationship between the cellular nuclei using a mean-shift clustering approach; computing a set of FeDeG features based on the FeDeG; providing the FeDeG features to a machine learning classifier; receiving, from the machine learning classifier, a classification of the region of tissue as a long-term or a short-term survivor, based, at least in part, on the set of FeDeG features; and displaying the classification.

Predicting overall survival in early stage lung cancer with feature driven local cell graphs (FeDeG)

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.

The degree of differentiation of a cell in tissue is precisely determined. An estimating device () includes: a binarizing section () configured to generate binarized images from an image obtained by capturing an image of tissue; a Betti number calculating section () configured to calculate, for each binarized image, (i) the number of hole-shaped regions (b) each surrounded by pixels of a first pixel value and each composed of pixels of a second pixel value, (ii) the number of connected regions each composed of the pixels of the first pixel value connected together, and (iii) a ratio (R) between (i) and (ii); a statistic calculating section () configured to calculate statistics of the calculated numbers (b, b) and ratio (R); and an estimating section () configured to feed input data including the calculated statistics to a trained estimating model to output the degree of differentiation of the cell in tissue.

Image analysis method, estimating device, estimating system, and storage medium

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.

Specialized computer-aided diagnosis and disease characterization with a multi-focal ensemble of convolutional neural networks

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.

Disease characterization and response estimation through spatially-invoked radiomics and deep learning fusion

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.

Structural rectal atlas deformation features for characterizing intra-wall and peri-wall chemoradiation response on magnetic resonance imaging (MRI)

Growing community of inventors

Shaker Heights, OH, United States of America

Anant Madabhushi