Extracting radiomic features from MR images helps with breast lesion classification

November 7, 2018 | Article

Extracting radiomic features from MR images can help radiologists distinguish between benign breast lesions and luminal A breast cancers, according to a new study published by Academic Radiology. The authors tested the effectiveness of machine learning by studying data from breast lesions imaged with MRI at a single medical center. The lesions were classified by using maximum linear size alone and by extracting 39 radiomic features from the MR images.

The full article can be found here.

The future of medicine is going to be changed greatly by the addition of radiomic signatures that have amazing predictive capabilities from images alone. This will save pain and suffering, costs, and possibilities of complications from not having to do invasive procedures. The HealthMyne QIDS Platform is the first FDA cleared software that extracts radiomic features at the point-of-read and uses Clinical Decision Support (CDS) to inform clinicians at the point-of-care when a lesion matches a radiomic signature.* Learn more here.


*Works in progress