Back to results
US 12,653,404 B2Granted
Optoacoustic image analysis method and system for automatically estimating lesion traits
AssigneeSeno Medical Instruments, Inc.
InventorsBryan Clingman, Sandra G. Dykes
Life of this patent
Estimating the term…
Abstract
A system and method for performing optoacoustic classification prediction is provided. The method utilizes one or more processors in connection with receiving OA feature scores in connection with OA images collected from a patient examination for a volume of interest. The volume of interest includes a lesion. The method applies the OA feature scores to a classification model to obtain a predictive result indicative of a trait of the lesion.
Claims14
A method, comprising:
- utilizing one or more processors for, receiving a labeled data set for multiple patients, the labeled data set including optoacoustic (OA) feature scores for lesions in OA images of volumes of interest from examinations for the multiple patients, the labeled data set including class designators indicating a trait of the lesion;
- and
- building an ensemble of classification models, associated with OA classification prediction, based on the OA feature scores and the class designators in the labeled data set, wherein each of the classification models include predictive results indicative of the trait of the lesion, each of the classification models built utilizing a predictive machine learning (PML) classifier.
A system, comprising:
- memory configured to store program instructions;
- one or more processors that, when executing the program instructions, are configured to:
- receive a labeled data set for multiple patients, the labeled data set including OA feature scores for lesions in OA images of volumes of interest from examinations for the multiple patients, the labeled data set including class designators indicating whether the lesions are in a benign class or malignant class;
- and
- build an ensemble of classification models, associated with OA classification prediction, based on the OA feature scores and the class designators in the labeled data set, wherein each of the classification models include predictive results indicative of the trait of the lesion, each of the classification models built utilizing a predictive machine learning (PML) classifier.
2 more elements
Dependencies are inferred from the claim text.