SynthEnsemble: A Fusion of CNN, Vision Transformer, and Hybrid Models for Multi-Label Chest X-Ray Classification

TL;DR

SynthEnsemble introduces an ensemble deep learning approach combining CNNs, transformers, and hybrid models to enhance multi-label chest X-ray classification accuracy, outperforming existing methods.

Contribution

The paper presents a novel ensemble method that fuses CNN, transformer, and hybrid models with differential evolution for weighting, achieving state-of-the-art results on ChestX-ray14.

Findings

Ensemble improved AUROC from 84.2% to 85.4%.

Best individual model was CoAtNet with 84.2% AUROC.

Method outperforms previous state-of-the-art approaches.

Abstract

Chest X-rays are widely used to diagnose thoracic diseases, but the lack of detailed information about these abnormalities makes it challenging to develop accurate automated diagnosis systems, which is crucial for early detection and effective treatment. To address this challenge, we employed deep learning techniques to identify patterns in chest X-rays that correspond to different diseases. We conducted experiments on the "ChestX-ray14" dataset using various pre-trained CNNs, transformers, hybrid(CNN+Transformer) models and classical models. The best individual model was the CoAtNet, which achieved an area under the receiver operating characteristic curve (AUROC) of 84.2%. By combining the predictions of all trained models using a weighted average ensemble where the weight of each model was determined using differential evolution, we further improved the AUROC to 85.4%, outperforming other state-of-the-art methods in this field. Our findings demonstrate the potential of deep learning techniques, particularly ensemble deep learning, for improving the accuracy of automatic diagnosis of thoracic diseases from chest X-rays. Code available at:https://github.com/syednabilashraf/SynthEnsemble