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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yamagishi, Yosuke, Hanaoka, Shouhei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912073159540736
author Yamagishi, Yosuke
Hanaoka, Shouhei
author_facet Yamagishi, Yosuke
Hanaoka, Shouhei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10710
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Ensemble of ConvNeXt V2 and MaxViT for Long-Tailed CXR Classification with View-Based Aggregation
Yamagishi, Yosuke
Hanaoka, Shouhei
Computer Vision and Pattern Recognition
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.
title Ensemble of ConvNeXt V2 and MaxViT for Long-Tailed CXR Classification with View-Based Aggregation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.10710