Multi-Disease Detection in Retinal Imaging based on Ensembling Heterogeneous Deep Learning Models

TL;DR

This paper presents an ensemble-based deep learning pipeline for multi-disease detection in retinal images, combining heterogeneous models and advanced training strategies to improve accuracy and reliability in clinical diagnosis.

Contribution

It introduces a novel ensemble learning approach integrating diverse deep models and techniques like transfer learning and Focal loss for retinal disease detection.

Findings

High accuracy demonstrated through internal and external validation.

Comparable performance with state-of-the-art retinal disease prediction models.

Effective integration of heterogeneous models enhances diagnostic reliability.

Abstract

Preventable or undiagnosed visual impairment and blindness affect billion of people worldwide. Automated multi-disease detection models offer great potential to address this problem via clinical decision support in diagnosis. In this work, we proposed an innovative multi-disease detection pipeline for retinal imaging which utilizes ensemble learning to combine the predictive capabilities of several heterogeneous deep convolutional neural network models. Our pipeline includes state-of-the-art strategies like transfer learning, class weighting, real-time image augmentation and Focal loss utilization. Furthermore, we integrated ensemble learning techniques like heterogeneous deep learning models, bagging via 5-fold cross-validation and stacked logistic regression models. Through internal and external evaluation, we were able to validate and demonstrate high accuracy and reliability of our pipeline, as well as the comparability with other state-of-the-art pipelines for retinal disease prediction.