Radiomic heterogeneity as prognostic predictor for treatment with CDK 4/6 inhibitors in hormone receptor-positive metastatic breast cancer
Inventors
Madabhushi, Anant • Braman, Nathaniel • Kunte, Siddharth • Montero, Alberto
Assignees
Uh Cleveland Medical Center • Cleveland Clinic Foundation • Case Western Reserve University • United States Department of Veterans Affairs
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12578338-B2
Publication Date
2026-03-17
Expiration Date
Abstract
The present disclosure relates to a method of determining a prognostic outlook for patients having metastatic breast cancer. The method includes receiving imaging data from an image of a patient that is receiving or that is to receive cycline dependent kinase 4 and 6 (CDK 4/6) inhibitor therapy for hormone receptor-positive (HR+) metastatic breast cancer. Radiomic heterogeneity features are extracted from imaging data associated with a metastasis within the imaging. A prognostic marker is determined from the radiomic heterogeneity features. The prognostic marker is indicative of a response of the patient to CDK 4/6 inhibitor therapy for HR+ metastatic breast cancer.
Core Innovation
A method determines a prognosis for a patient having metastatic breast cancer by receiving imaging data from an image of a patient receiving or to receive cycline dependent kinase 4 and 6 (CDK 4/6) inhibitor therapy for hormone receptor-positive (HR+) metastatic breast cancer. The method identifies a lesional region and a perilesional region of a metastasis within the image, where the metastasis is located in tissue external to the breast, and extracts lesional and perilesional radiomic heterogeneity features from the imaging data associated with the metastasis.
The method defines the lesional radiomic heterogeneity features as a median value of gray level co-occurrence matrix (GLCM) entropy within a lesional mask, and defines the perilesional radiomic heterogeneity features as a standard deviation of GLCM contrast within a perilesional mask. A radiomic risk score is determined from both the lesional radiomic heterogeneity features and the perilesional radiomic heterogeneity features, and the radiomic risk score is indicative of a response of the patient to CDK 4/6 inhibitor therapy for HR+ metastatic breast cancer.
An apparatus and a non-transitory computer-readable medium are configured to perform the same overall radiomics-based prognosis workflow. The apparatus includes an identification circuit configured to generate a lesional mask and a perilesional mask of the metastasis, a heterogeneity measurement circuit configured to extract lesional and perilesional radiomic heterogeneity features based on the specified GLCM-derived statistics, and a prognostic marker calculation circuit configured to calculate the radiomic risk score indicative of a response.
Claims Coverage
The independent claims are clm-00001, clm-00008, and clm-00013. Across these independent claims, the coverage centers on extracting lesional and perilesional radiomic heterogeneity features from metastasis imaging, computing a radiomic risk score indicative of response to CDK 4/6 inhibitor therapy, and implementing the workflow as an apparatus or computer-readable medium. The independent claims explicitly define key inventive elements comprising lesional/perilesional mask generation, specific GLCM-derived feature statistics, and risk-score determination indicative of response.
Radiomic prognosis from lesional and perilesional heterogeneity features in external-to-breast metastasis
receiving imaging data from an image of a patient who is receiving or who is to receive cycline dependent kinase 4 and 6 (CDK 4/6) inhibitor therapy for hormone receptor-positive (HR+) metastatic breast cancer; identifying a lesional region and a perilesional region of a metastasis within the image, the metastasis located in tissue external to the breast; extracting lesional radiomic heterogeneity features corresponding to the lesional region and perilesional radiomic heterogeneity features corresponding to the perilesional region from the imaging data associated with the metastasis; and determining a radiomic risk score indicative of a response of the patient to CDK 4/6 inhibitor therapy for HR+ metastatic breast cancer.
GLCM entropy and GLCM contrast-based radiomic risk score
extracting lesional radiomic heterogeneity features identified using a median value of gray level co-occurrence matrix (GLCM) entropy and perilesional radiomic heterogeneity features identified using a standard deviation of GLCM contrast; determining a radiomic risk score from the lesional radiomic heterogeneity features and the perilesional radiomic heterogeneity features; and indicating that the radiomic risk score is indicative of a response to CDK 4/6 inhibitor therapy for HR+ metastatic breast cancer.
Apparatus with mask generation, heterogeneity measurement, and prognostic marker calculation for CDK 4/6 therapy response
a memory configured to store imaging data of a metastasis located in tissue external to the breast from a patient that is receiving or that is to receive CDK 4/6 inhibitor therapy for HR+ metastatic breast cancer; an identification circuit configured to generate a lesional mask and a perilesional mask of the metastasis; a heterogeneity measurement circuit configured to extract, from the imaging data, lesional radiomic heterogeneity features based on a median value of gray level co-occurrence matrix (GLCM) entropy within the lesional mask and perilesional radiomic heterogeneity features based on a standard deviation of GLCM contrast within the perilesional mask; and a prognostic marker calculation circuit configured to calculate a radiomic risk score from the lesional radiomic heterogeneity features and the perilesional radiomic heterogeneity features, wherein the radiomic risk score is indicative of a response of the patient to CDK 4/6 inhibitor therapy for HR+ metastatic breast cancer.
Taken together, the independent claims require metastasis radiomics that separate lesional and perilesional regions, extract radiomic heterogeneity features defined by median GLCM entropy and standard deviation of GLCM contrast, and determine a radiomic risk score indicative of response to CDK 4/6 inhibitor therapy for HR+ metastatic breast cancer, optionally including risk-group arrangement and implementing the workflow as a specific apparatus.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?