Assessing residual cancer burden in breast cancer patients undergoing neoadjuvant chemotherapy using the OptiScan probe and machine learning

Abstract

Breast cancer patients undergoing neoadjuvant chemotherapy (NAC) require precise and accurate evaluation of treatment response. Residual cancer burden (RCB) estimation is a critical prognostic tool used in breast cancer outcomes assessment. In this pioneering study, we introduce the OptiScan probe, an innovative machine-learning-based optical biosensor, to assess residual cancer burden in patients undergoing NAC. The study enrolled 32 patients (mean age: 61.8 years), with comprehensive data collected pre-and post-each NAC cycle. Using the Modified Diffusion Equation (MDE) algorithm and advanced regression analysis, we meticulously calculated the optical properties and generated functional images of both healthy and affected breast tissues. Leveraging these insights, a robust machine learning model was developed, harnessing optical parameter values and breast cancer imaging features to predict RCB values. The predictive model showcased exceptional performance, achieving an impressive accuracy of 96.875% and 96.88% sensitivity in predicting RCB based on optical property alterations. These findings underscore the potency of the OptiScan probe as a pivotal tool for assessing breast cancer response post-NAC. This innovative approach holds promise as a noninvasive and accurate method for monitoring patient responses, contributing to improved treatment decisions and patient outcomes. By combining the power of machine learning with cutting-edge optical imaging, this study marks a significant stride toward personalized and effective breast cancer management.