Memory-aware curriculum federated learning for breast cancer classification

• Published in: Computer methods and programs in biomedicine 2023-02, Vol.229, p.107318-107318, Article 107318
• Main Authors: Jiménez-Sánchez, Amelia, Tardy, Mickael, González Ballester, Miguel A., Mateus, Diana, Piella, Gemma
• Format: Article
• Language: English
• Subjects: Awareness; Cognition; Computer Science; Curriculum; Curriculum learning; Data scheduling; Data sharing; Domain adaptation; Federated learning; Learning; Malignancy classification; Mammography; Neoplasms
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2022.107318

•Curriculum learning improves breast cancer classification on high-resolution mammograms in a federated setting.•Curriculum is implemented as a data scheduler, which penalizes inconsistent predictions, to improve the consistency of local models in a federated setting.•We track the predictions before and after the deployment of the global model, thus we refer to our method as memory-aware curriculum federated learning.•Memory-aware curriculum federated learning improves the classification and alignment between domain pairs.•Effective for the multi-site breast cancer classification on clinical datasets from different vendors. [Display omitted] Background and Objective: For early breast cancer detection, regular screening with mammography imaging is recommended. Routine examinations result in datasets with a predominant amount of negative samples. The limited representativeness of positive cases can be problematic for learning Computer-Aided Diagnosis (CAD) systems. Collecting data from multiple institutions is a potential solution to mitigate this problem. Recently, federated learning has emerged as an effective tool for collaborative learning. In this setting, local models perform computation on their private data to update the global model. The order and the frequency of local updates influence the final global model. In the context of federated adversarial learning to improve multi-site breast cancer classification, we investigate the role of the order in which samples are locally presented to the optimizers. Methods: We define a novel memory-aware curriculum learning method for the federated setting. We aim to improve the consistency of the local models penalizing inconsistent predictions, i.e., forgotten samples. Our curriculum controls the order of the training samples prioritizing those that are forgotten after the deployment of the global model. Our approach is combined with unsupervised domain adaptation to deal with domain shift while preserving data privacy. Results: Two classification metrics: area under the receiver operating characteristic curve (ROC-AUC) and area under the curve for the precision-recall curve (PR-AUC) are used to evaluate the performance of the proposed method. Our method is evaluated with three clinical datasets from different vendors. An ablation study showed the improvement of each component of our method. The AUC and PR-AUC are improved on average by 5% and 6%, respectively, compared to the conventional federated setting.