Using Machine Vision of Glycolytic Elements to Predict Breast Cancer Recurrences: Design and Implementation

Abstract

A major goal of biomedical research has been the early and quantitative identification of patients who will subsequently experience a cancer recurrence. In this review, I discuss the ability of glycolytic enzyme and transporter patterns within tissues to detect sub-populations of cells within ductal carcinoma in situ (DCIS) lesions that specifically precede cancer recurrences. The test uses conventional formalin fixed paraffin embedded tissue samples. The accuracy of this machine vision test rests on the identification of relevant glycolytic components that promote enhanced glycolysis (phospho-Ser226-glucose transporter type 1 (phospho-Ser226-GLUT1) and phosphofructokinase type L (PFKL)), their trafficking in tumor cells and tissues as judged by computer vision, and their high signal-to-noise levels. For each patient, machine vision stratifies micrographs from each lesion as the probability that the lesion originated from a recurrent sample. This stratification method removes overlap between the predicted recurrent and non-recurrent patients, which eliminates distribution-dependent false positives and false negatives. The method identifies computationally negative samples as non-recurrent and computationally positive samples are recurrent; computationally positive non-recurrent samples are likely due to mastectomies. The early phosphorylation and isoform switching events, spatial locations and clustering constitute important steps in metabolic reprogramming. This work also illuminates mechanistic steps occurring prior to a recurrence, which may contribute to the development of new drugs.