Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12217429-B2
Publication Date
2025-02-04
Expiration Date
Abstract
A platform is provided for generating 3D models of a tumor segmented from a series of 2D medical images and for identifying from these 3D models, radiomic features that may be used for diagnostic, prognostic, and treatment response assessment of the tumor. The radiomic features may be shape-based features, intensity-based features, textural features, and filter-based features. The radiomic features are compared to remove sufficiently redundant features, thereby producing a reduced set of radiomic features, which is then compared to separate genomic data and/or outcome data to identify clinically and biologically significant radiomic features for diagnostic, prognostic, and treatment response assessment, other applications.
Core Innovation
The invention relates to a computer-implemented method for analyzing medical image data by obtaining a three-dimensional (3D) model and detecting target tissue in the 3D model, where the target tissue comprises tumor tissue and surrounding tissue. From the 3D model, a master set of three-dimensional (3D) radiomic features is identified for the target tissue and linked to clinical outcome data. The disclosed approach produces objective 3D radiomic change outputs by assessing imaging before and after therapy and characterizing each radiomic feature in the master set.
The method associates the master set of 3D radiomic features with one or more of clinical data and molecular data, and produces one or more integrated radiomic-based indicators. Each integrated radiomic-based indicator is generated by characterizing each radiomic feature in the master set based on a machine learning-derived relevance score that quantitatively assesses the feature's predictive accuracy for patient-specific therapeutic outcomes. The integrated radiomic-based indicators are stored for assessing subsequent target tissue in subsequent medical image data.
In a comparative workflow, the method obtains a first 3D model corresponding to a first time period before therapy and a second 3D model corresponding to a second time period after the first time period and associated with the therapy. The comparing generates data indicating changes in 3D radiomic features and determines changes in one or more integrated radiomic-based indicators, where the integrated radiomic-based indicators include associations between the 3D radiomic features and one or more of clinical data and molecular data. By comparing the subject associations to associations of a cohort of different subjects, the method generates at least one of treatment response data, diagnostic data, or prognostic data.
Claims Coverage
The partial content provides two independent claims, each centered on integrated 3D radiomic feature modeling and subsequent use for predictive and comparative clinical analysis. Across the two independent claims, the inventive features include five merged features: constructing or using a 3D model with tumor and surrounding tissue, deriving a master set of 3D radiomic features and associating them with clinical and molecular data, producing integrated radiomic-based indicators using machine learning-derived relevance scores, and using pre- vs post-therapy 3D model comparisons to generate treatment response, diagnostic, or prognostic data via cohort comparison.
Three-dimensional model for target tissue radiomics
Obtaining a three-dimensional (3D) model of medical image data; detecting target tissue in the 3D model, the target tissue comprising tumor tissue and surrounding tissue.
Master set of three-dimensional radiomic features linked to outcomes
Identifying a master set of three-dimensional (3D) radiomic features from the 3D model, the master set corresponding to the target tissue and clinical outcome data.
Integrated radiomic-based indicators from machine learning relevance scores
Associating the master set of 3D radiomic features with one or more of clinical data and molecular data; producing one or more integrated radiomic-based indicators by characterizing each radiomic feature in the master set based on a machine learning-derived relevance score that quantitatively assesses the feature's predictive accuracy for patient-specific therapeutic outcomes; storing the one or more integrated radiomic-based indicators for assessing subsequent target tissue in subsequent medical image data.
Pre-therapy versus post-therapy 3D comparison
Obtaining a first 3D model corresponding to a first time period before a therapy; obtaining a second 3D model corresponding to a second time period after the first time period and associated with the therapy; comparing the first 3D model to the second 3D model, where comparing includes generating data indicating changes in 3D radiomic features and determining changes in one or more integrated radiomic-based indicators between the first time period and the second time period.
Cohort-based generation of treatment, diagnostic, or prognostic data
Generating, by comparing the associations of the new subject to a plurality of associations of a cohort of different subjects, at least one of treatment response data, diagnostic data or prognostic data.
Overall claim coverage centers on deriving a master set of 3D radiomic features from a 3D model containing tumor tissue and surrounding tissue, associating these features with clinical and molecular data, and producing machine learning-derived integrated radiomic-based indicators with quantitative predictive relevance; a second independent claim extends this by comparing pre- and post-therapy 3D models, tracking radiomic and indicator changes, and generating treatment response, diagnostic, or prognostic outputs via cohort comparison.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?