Cited 0 times in Scipus Cited Count

Optimization of vision transformer-based detection of lung diseases from chest X-ray images

Authors
Ko, J | Park, S | Woo, HG
Citation
BMC medical informatics and decision making, 24(1). : 191-191, 2024
Journal Title
BMC medical informatics and decision making
ISSN
1472-6947
Abstract
Background: Recent advances in Vision Transformer (ViT)-based deep learning have significantly improved the accuracy of lung disease prediction from chest X-ray images. However, limited research exists on comparing the effectiveness of different optimizers for lung disease prediction within ViT models. This study aims to systematically evaluate and compare the performance of various optimization methods for ViT-based models in predicting lung diseases from chest X-ray images. Methods: This study utilized a chest X-ray image dataset comprising 19,003 images containing both normal cases and six lung diseases: COVID-19, Viral Pneumonia, Bacterial Pneumonia, Middle East Respiratory Syndrome (MERS), Severe Acute Respiratory Syndrome (SARS), and Tuberculosis. Each ViT model (ViT, FastViT, and CrossViT) was individually trained with each optimization method (Adam, AdamW, NAdam, RAdam, SGDW, and Momentum) to assess their performance in lung disease prediction. Results: When tested with ViT on the dataset with balanced-sample sized classes, RAdam demonstrated superior accuracy compared to other optimizers, achieving 95.87%. In the dataset with imbalanced sample size, FastViT with NAdam achieved the best performance with an accuracy of 97.63%. Conclusions: We provide comprehensive optimization strategies for developing ViT-based model architectures, which can enhance the performance of these models for lung disease prediction from chest X-ray images.
Keywords

MeSH

DOI
10.1186/s12911-024-02591-3
PMID
38978027
Appears in Collections:
Journal Papers > School of Medicine / Graduate School of Medicine > Physiology
Ajou Authors
우, 현구
Full Text Link
Files in This Item:
38978027.pdfDownload
Export

qrcode

해당 아이템을 이메일로 공유하기 원하시면 인증을 거치시기 바랍니다.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse