Continual Deep Active Learning for Medical Imaging: Replay-Base Architecture for Context Adaptation

2025-01-14

AI Summary

Medical imaging faces challenges in cross-scenario adaptation and high annotation costs due to the disconnection between continual learning (CL) and active learning (AL). Method: This paper proposes RBACA, a replay-based continual learning framework, and IL-Score, a novel integrated evaluation metric. RBACA unifies context-aware recognition, memory-efficient replay, and informativeness-driven annotation via buffer-based CL, uncertainty-diversity joint active sampling, automatic distribution shift detection, and joint segmentation-diagnosis modeling under domain- and class-incremental settings. Contribution/Results: On cardiac imaging tasks, RBACA significantly outperforms state-of-the-art methods, achieving up to a 23.6% improvement in IL-Score. It maintains robust performance under stringent constraints—≤500-sample memory budget and ≤10% annotation budget—demonstrating strong scalability and efficiency. The framework establishes a lifelong-evolving paradigm for low-resource medical AI, enabling adaptive, annotation-efficient, and clinically deployable intelligent diagnosis.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Computer Vision: Medical and Biological Imaging
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Deep Learning for medical imaging faces challenges in adapting and generalizing to new contexts. Additionally, it often lacks sufficient labeled data for specific tasks requiring significant annotation effort. Continual Learning (CL) tackles adaptability and generalizability by enabling lifelong learning from a data stream while mitigating forgetting of previously learned knowledge. Active Learning (AL) reduces the number of required annotations for effective training. This work explores both approaches (CAL) to develop a novel framework for robust medical image analysis. Based on the automatic recognition of shifts in image characteristics, Replay-Base Architecture for Context Adaptation (RBACA) employs a CL rehearsal method to continually learn from diverse contexts, and an AL component to select the most informative instances for annotation. A novel approach to evaluate CAL methods is established using a defined metric denominated IL-Score, which allows for the simultaneous assessment of transfer learning, forgetting, and final model performance. We show that RBACA works in domain and class-incremental learning scenarios, by assessing its IL-Score on the segmentation and diagnosis of cardiac images. The results show that RBACA outperforms a baseline framework without CAL, and a state-of-the-art CAL method across various memory sizes and annotation budgets. Our code is available in https://github.com/RuiDaniel/RBACA .

Problem

• Continual Learning
• Medical Imaging
• Limited Annotated Data

Innovation

• Continuous Learning
• Active Learning
• RBACA System