CAMEL: Confidence-Aware Multi-Task Ensemble Learning with Spatial Information for Retina OCT Image Classification and Segmentation

Juho Jung, Migyeong Yang, Hyunseon Won, Jiwon Kim, Jeong Mo Han, Joon Seo Hwang, Daniel Duck-Jin Hwang, Jinyoung Han; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 8929-8939

Precise retina Optical Coherence Tomography (OCT) image classification and segmentation are important for diagnosing various retinal diseases and identifying specific regions. Alongside comprehensive lesion identification reducing the predictive uncertainty of models is crucial for improving reliability in clinical retinal practice. However existing methods have primarily focused on a limited set of regions identified in OCT images and have often faced challenges due to aleatoric and epistemic uncertainty. To address these issues we propose CAMEL (Confidence-Aware Multi-task Ensemble Learning) a novel framework designed to reduce task-specific uncertainty in multi-task learning. CAMEL achieves this by estimating model confidence at both pixel and image levels and leveraging confidence-aware ensemble learning to minimize the uncertainty inherent in single-model predictions. CAMEL demonstrates state-of-the-art performance on a comprehensive retinal OCT image dataset containing annotations for nine distinct retinal regions and nine retinal diseases. Furthermore extensive experiments highlight the clinical utility of CAMEL especially in scenarios with minimal regions significant class imbalances and diverse regions and diseases. Our code is publicly available at: https://github.com/DSAIL-SKKU/CAMEL.