Ensemble learning for retinal disease recognition under limited resources.

Abstract

Retinal optical coherence tomography (OCT) images provide crucial insights into the health of the posterior ocular segment. Therefore, the advancement of automated image analysis methods is imperative to equip clinicians and researchers with quantitative data, thereby facilitating informed decision-making. The application of deep learning (DL)-based approaches has gained extensive traction for executing these analysis tasks, demonstrating remarkable performance compared to labor-intensive manual analyses. However, the acquisition of retinal OCT images often presents challenges stemming from privacy concerns and the resource-intensive labeling procedures, which contradicts the prevailing notion that DL models necessitate substantial data volumes for achieving superior performance. Moreover, limitations in available computational resources constrain the progress of high-performance medical artificial intelligence, particularly in less developed regions and countries. This paper introduces a novel ensemble learning mechanism designed for recognizing retinal diseases under limited resources (e.g., data, computation). The mechanism leverages insights from multiple pre-trained models, facilitating the transfer and adaptation of their knowledge to retinal OCT images. This approach establishes a robust model even when confronted with limited labeled data, eliminating the need for an extensive array of parameters, as required in learning from scratch. Comprehensive experimentation on real-world datasets demonstrates that the ensemble models constructed by the proposed ensemble method show superior performance over the baseline models under sparse labeled data, especially the triple ensemble model, which achieves the accuracy of 92.06%, which is 8.27%, 7.99%, and 11.14% better than the three baseline models, respectively. In addition, compared with the three baseline models learned from scratch, the triple ensemble model has fewer trainable parameters, only 3.677M, which is lower than the three baseline models of 8.013M, 4.302M, and 20.158M, respectively.