Ensemble of ConvNeXt V2 and MaxViT for Long-Tailed CXR Classification with View-Based Aggregation

TL;DR

This paper presents an ensemble approach combining ConvNeXt V2 and MaxViT models, pretrained on chest X-ray data, with view-based aggregation and asymmetric loss to improve long-tailed CXR classification, achieving top results in MICCAI 2024 challenge.

Contribution

It introduces a novel ensemble method with view-based aggregation and class imbalance handling for long-tailed CXR classification, demonstrating improved accuracy.

Findings

Achieved 4th place in Subtask 2 and 5th in Subtask 1 of MICCAI 2024 CXR-LT challenge.

Ensemble of ConvNeXt V2 and MaxViT improves classification performance.

View-based aggregation and asymmetric loss enhance detection of rare findings.

Abstract

In this work, we present our solution for the MICCAI 2024 CXR-LT challenge, achieving 4th place in Subtask 2 and 5th in Subtask 1. We leveraged an ensemble of ConvNeXt V2 and MaxViT models, pretrained on an external chest X-ray dataset, to address the long-tailed distribution of chest findings. The proposed method combines state-of-the-art image classification techniques, asymmetric loss for handling class imbalance, and view-based prediction aggregation to enhance classification performance. Through experiments, we demonstrate the advantages of our approach in improving both detection accuracy and the handling of the long-tailed distribution in CXR findings. The code is available at https://github.com/yamagishi0824/cxrlt24-multiview-pp.