Domain Generalization for Mammographic Image Analysis with Contrastive Learning
This addresses the challenge of limited data diversity in medical imaging for clinicians and researchers, though it is incremental as it builds on existing contrastive learning techniques.
The paper tackled the problem of training deep learning models for mammographic image analysis without sufficient diverse data by developing a novel contrastive learning method for domain generalization, which improved performance on four tasks (e.g., mass detection) and outperformed state-of-the-art methods on both seen and unseen domains.
The deep learning technique has been shown to be effectively addressed several image analysis tasks in the computer-aided diagnosis scheme for mammography. The training of an efficacious deep learning model requires large data with diverse styles and qualities. The diversity of data often comes from the use of various scanners of vendors. But, in practice, it is impractical to collect a sufficient amount of diverse data for training. To this end, a novel contrastive learning is developed to equip the deep learning models with better style generalization capability. Specifically, the multi-style and multi-view unsupervised self-learning scheme is carried out to seek robust feature embedding against style diversity as a pretrained model. Afterward, the pretrained network is further fine-tuned to the downstream tasks, e.g., mass detection, matching, BI-RADS rating, and breast density classification. The proposed method has been evaluated extensively and rigorously with mammograms from various vendor style domains and several public datasets. The experimental results suggest that the proposed domain generalization method can effectively improve performance of four mammographic image tasks on the data from both seen and unseen domains, and outperform many state-of-the-art (SOTA) generalization methods.