New machine learning method improves testing of stem-like tumor cells for breast cancer research

(Illustration of growing cancer tumor.) — Illustration of growing cancer tumor.
(Courtesy of U-M’s Electrical And Computer Engineering Division.)

Prof. Euisik Yoon’s research group has developed a new, faster method to identify cancer stem-like cells (CSCs), which could help improve the effectiveness of cancer treatments.

CSCs can develop tumors and cause a cancer relapse after a patient’s treatment. CSCs are generally resistant to chemotherapy and radiotherapy, so therapeutics that directly target CSCs may improve the success of cancer treatments greatly. Because CSCs vary widely among and within patients, it can be difficult to develop these treatments.

To address various issues that come with identifying CSCs, Yoon’s group developed and trained a convolutional neural network (CNN), a machine learning method for image classification, to predict single-cell derived tumorsphere formation.The paper, “Early Prediction of Single-cell Derived Sphere Formation Rate Using Convolutional Neural Network Image Analysis,” is published in Analytical Chemistry.