KNOWLEDGE-GUIDED MULTI-TASK LEARNING FOR BREAST CANCER DIAGNOSIS USING LONGITUDINAL MAMMOGRAM IMAGES

In clinical detection and diagnosis of breast cancer, temporal analysis of mammogram images plays a crucial role. This study introduces a knowledge-guided multi-task learning approach that aims to elevate the accuracy of breast cancer diagnosis by incorporating the analysis of breast density changes over time. While breast cancer diagnosis is our main task, we construct the classification of breast density evolution over time as an auxiliary task that leverages crucial longitudinal tissue changes to enhance breast cancer diagnosis. Specifically, we propose a novel architecture that employs cross-view mechanisms and context-guided triplet loss to capture temporal changes and facilitate more effective learning. Our contributions include a customized multi-task model that integrates breast density categorization to capture temporal feature changes, and the application of context-guided triplet loss for faster convergence. We performed experiments on a cohort of 580 breast cancer patients (each has two sequential mammogram exams) in a case-control setting, and the proposed method achieved an AUC of 0.745, outperforming the several compared methods.