Domain Generalization for Mammographic Image Analysis with Contrastive Learning
Authors:
- Zaiyi LiuZLZaiyi Liu
- Dinggang ShenDSDinggang Shen
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Domain generalization in deep learning based mass detection in mammography: A large-scale multi-center studyArtificial Intelligence in Medicine, 2022
- MommiNet-v2: Mammographic multi-view mass identification networksMedical Image Analysis, 2021
- Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning2021
- BASCNet: Bilateral adaptive spatial and channel attention network for breast density classification in the mammogramBiomedical Signal Processing and Control, 2021
- Towards improved breast mass detection using dual-view mammogram matchingMedical Image Analysis, 2021
- Convolutional neural networks for breast cancer detection in mammography: A surveyComputers in Biology and Medicine, 2021
- Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization2020
- External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening MammogramsJAMA Oncology, 2020
- Domain generalization in rotating machinery fault diagnostics using deep neural networksNeurocomputing, 2020
- Unsupervised domain adaptation with adversarial learning for mass detection in mammogramNeurocomputing, 2020