EndoCIL: A Class-Incremental Learning Framework for Endoscopic Image Classification

TL;DR

EndoCIL is a specialized class-incremental learning framework for endoscopic image classification that effectively mitigates catastrophic forgetting and handles class imbalance, improving continual diagnosis performance.

Contribution

The paper introduces EndoCIL, a unified CIL framework with novel components tailored for endoscopic imaging, addressing domain discrepancies and class imbalance challenges.

Findings

Outperforms state-of-the-art CIL methods on four datasets

Effectively balances stability and plasticity in incremental learning

Demonstrates potential for clinical deployment

Abstract

Class-incremental learning (CIL) for endoscopic image analysis is crucial for real-world clinical applications, where diagnostic models should continuously adapt to evolving clinical data while retaining performance on previously learned ones. However, existing replay-based CIL methods fail to effectively mitigate catastrophic forgetting due to severe domain discrepancies and class imbalance inherent in endoscopic imaging. To tackle these challenges, we propose EndoCIL, a novel and unified CIL framework specifically tailored for endoscopic image diagnosis. EndoCIL incorporates three key components: Maximum Mean Discrepancy Based Replay (MDBR), employing a distribution-aligned greedy strategy to select diverse and representative exemplars, Prior Regularized Class Balanced Loss (PRCBL), designed to alleviate both inter-phase and intra-phase class imbalance by integrating prior class distributions and balance weights into the loss function, and Calibration of Fully-Connected Gradients (CFG), which adjusts the classifier gradients to mitigate bias toward new classes. Extensive experiments conducted on four public endoscopic datasets demonstrate that EndoCIL generally outperforms state-of-the-art CIL methods across varying buffer sizes and evaluation metrics. The proposed framework effectively balances stability and plasticity in lifelong endoscopic diagnosis, showing promising potential for clinical scalability and deployment.