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

Patent metadata

Field	Value
Publication number	US-2021169349-A1
Application number	US-202017116319-A
Country	US
Kind code	A1
Filing date	Dec 9, 2020
Priority date	Dec 9, 2019
Publication date	Jun 10, 2021
Grant date	—

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.

First claim

What is claimed is:

1 . A non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations, comprising:
accessing one or more medical imaging scans of a tumor, wherein the tumor is segmented on the one or more medical imaging scans; segmenting tumor-associated vasculature (TAV) associated with the tumor based on the one or more medical imaging scans; 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.

2 . The non-transitory computer-readable medium of claim 1 , wherein the machine learning model is one of, or an ensemble of two or more of, a logistic regression model, a Cox regression model, a Least Absolute Shrinkage and Selection Operator (LASSO) regression model, a naïve Bayes classifier, a support vector machine (SVM) with a linear kernel, a SVM with a radial basis function (RBF) kernel, a linear discriminant analysis (LDA) classifier, a quadratic discriminant analysis (QDA) classifier, a logistic regression classifier, a decision tree, a random forest, a diagonal LDA, a diagonal QDA, a neural network, an AdaBoost algorithm, an elastic net, a Gaussian process classification, or a nearest neighbors classification.

3 . The non-transitory computer-readable medium of claim 1 , wherein the at least one feature comprises one or more of at least one TAV morphology feature, a statistic of the at least one TAV morphology feature, at least one TAV spatial organization feature, or the statistic of the at least one TAV spatial organization feature.

4 . The non-transitory computer-readable medium of claim 3 , wherein the statistic is one of a mean, a median, a standard deviation, a skewness, a kurtosis, a range, a minimum, a maximum, a percentile, or histogram frequencies.

5 . The non-transitory computer-readable medium of claim 3 , wherein the at least one feature comprises one or more of the at least one TAV morphology feature or the statistic of the at least one TAV morphology feature, wherein the at least one TAV morphology feature comprises one or more of a torsion per branch of a plurality of branches of the TAV, a curvature standard deviation per branch of the plurality of branches, a mean curvature per branch, a maximum curvature per branch per branch of the plurality of branches, a curvature skewness per branch of the plurality of branches, a curvature kurtosis per branch of the plurality of branches, a global vascular curvature, the torsion across the plurality of branches, a vessel volume, a vessel volume normalized to a volume of a region of interest comprising the tumor, a vessel volume normalized to a volume of the tumor, a total vessel length, a number of branches of the plurality of branches that enter the tumor, or a percentage of branches of the plurality of branches that enter the tumor.

6 . The non-transitory computer-readable medium of claim 3 , wherein the at least one feature comprises one or more of the at least one TAV spatial orientation feature or the statistic of the at least one TAV spatial orientation feature, wherein the at least one TAV spatial orientation feature comprises one or more of a vessel orientation along a XY projection image, a vessel orientation along a XZ projection image, a vessel orientation along a YZ projection image, a vessel orientation along a rotation-elevation projection image, a vessel orientation along a distance-rotation projection image, or a vessel orientation along a distance-elevation projection image.

7 . The non-transitory computer-readable medium of claim 1 , wherein the one or more features comprise at least one TAV function feature that measures a dynamics of a contrast agent in one or more of the tumor or the TAV, wherein the at least one TAV function feature is one or more of a signal enhancement ratio, a time to peak enhancement, a rate of uptake, or a rate of washout.

8 . The non-transitory computer-readable medium of claim 1 , wherein the one or more medical imaging scans comprise at least one of one or more computed tomography (CT) scans, one or more magnetic resonance imaging (MRI) scans without an addition of a contrast agent, or one or more MRI scans with the addition of the contrast agent.

9 . The non-transitory computer-readable medium of claim 1 , wherein the tumor is one a breast cancer tumor or a non-small cell lung cancer (NSCLC) tumor.

10 . The non-transitory computer-readable medium of claim 1 , wherein the predicted response to the treatment comprises a response score indicating a likelihood of pathologic complete response (pCR), major pathological response (MPR), or Response Evaluation Criteria In Solid Tumors (RECIST).

11 . The non-transitory computer-readable medium of claim 1 , wherein the prognosis for the tumor comprises one or more of a prognostic risk score or a risk group that indicates a likelihood of one or more of recurrence free survival (RFS) or progression free survival (PFS).

12 . A non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause a processor to perform operations, comprising:
accessing a training set comprising a plurality of medical imaging scans, wherein each medical imaging scan of the training set comprises an associated tumor segmented on that medical imaging scan, wherein the associated tumor of that medical imaging scan is associated with at least one of a known response to a treatment or a known prognosis; and for each medical imaging scan of the training set:
segmenting associated tumor-associated vasculature (TAV) for the associated tumor of that medical imaging scan;
extracting associated values for a set of features from the associated TAV for the associated tumor of that medical imaging scan; and
training a machine learning model based on the associated values extracted from the associated TAV for the associated tumor of that medical imaging scan and on the at least one of the known response to the treatment or the known prognosis.

13 . The non-transitory computer-readable medium of claim 12 , wherein the operations comprise:
for each medical imaging scan of the training set, extracting associated values for a plurality of features from the associated TAV for the associated tumor of that medical imaging scan; and selecting the set of features from the plurality of features, wherein the set of features are identified as the best features for predicting the known response or the known prognosis.

14 . The non-transitory computer-readable medium of claim 12 , wherein the machine learning model is one of, or an ensemble of two or more of, a logistic regression model, a Cox regression model, a Least Absolute Shrinkage and Selection Operator (LASSO) regression model, a naïve Bayes classifier, a support vector machine (SVM) with a linear kernel, a SVM with a radial basis function (RBF) kernel, a linear discriminant analysis (LDA) classifier, a quadratic discriminant analysis (QDA) classifier, a logistic regression classifier, a decision tree, a random forest, a diagonal LDA, a diagonal QDA, a neural network, an AdaBoost algorithm, an elastic net, a Gaussian process classification, or a nearest neighbors classification.

15 . The non-transitory computer-readable medium of claim 12 , wherein the set of features comprises one or more of at least one TAV morphology feature, a statistic of the at least one TAV morphology feature, at least one TAV

Assignees

• Univ Case Western Reserve
• Louis Stokes Cleveland Veterans Administration Medical Center

Inventors

• Madabhushi Anant
• Braman Nathaniel

Classifications

• A61B6/504

  for diagnosis of blood vessels, e.g. by angiography · CPC title

• A61B6/5217

  extracting a diagnostic or physiological parameter from medical diagnostic data · CPC title

• G06T7/0012

  Biomedical image inspection · CPC title

• G06T2207/30096

  Tumor; Lesion · CPC title

• A61B6/502 Primary

  for diagnosis of breast, i.e. mammography · CPC title