TopOC: Topological Deep Learning for Ovarian and Breast Cancer Diagnosis
This work addresses the challenge of developing effective clinical decision support systems for pathologists by improving diagnostic accuracy in cancer detection, though it appears incremental as it builds on existing histopathological image analysis models.
The paper tackled the problem of limited labeled data for training deep learning models in histopathological cancer diagnosis by integrating topological deep learning to enhance accuracy and robustness. The result showed that including topological features significantly improved tumor type differentiation in ovarian and breast cancers, as demonstrated on publicly available datasets.
Microscopic examination of slides prepared from tissue samples is the primary tool for detecting and classifying cancerous lesions, a process that is time-consuming and requires the expertise of experienced pathologists. Recent advances in deep learning methods hold significant potential to enhance medical diagnostics and treatment planning by improving accuracy, reproducibility, and speed, thereby reducing clinicians' workloads and turnaround times. However, the necessity for vast amounts of labeled data to train these models remains a major obstacle to the development of effective clinical decision support systems. In this paper, we propose the integration of topological deep learning methods to enhance the accuracy and robustness of existing histopathological image analysis models. Topological data analysis (TDA) offers a unique approach by extracting essential information through the evaluation of topological patterns across different color channels. While deep learning methods capture local information from images, TDA features provide complementary global features. Our experiments on publicly available histopathological datasets demonstrate that the inclusion of topological features significantly improves the differentiation of tumor types in ovarian and breast cancers.