Segmentation, classification and interpretation of breast cancer medical images using human-in-the-loop machine learning

This paper explores the application of Human-in-the-Loop (HITL) strategies in the training of machine learning models in the medical domain. In this case, a doctor-in-the-loop approach is proposed to leverage human expertise in dealing with large and complex data. Specifically, the paper deals with the use of Whole Slide Imaging (WSI) for the analysis and prediction of the genomic subtype of breast cancer. Three different tasks were developed: segmentation of histopathological images, classification of these images regarding the genomic subtype of the cancer, and finally, interpretation of the machine learning results. The involvement of a pathologist helped us to develop a better segmentation model trying to group areas to make it more useful for further diagnosis. Because the classification models underperformed due to the complexity of the problem and insufficient data for certain cancer types, we focus our efforts in using the feedback from the pathologist to enhance model interpretability through a HITL hyperparameter optimization process.