Saved in:
Bibliographic Details
Main Authors: Agarwal, Lakshita, Verma, Bindu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.16774
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913805982760960
author Agarwal, Lakshita
Verma, Bindu
author_facet Agarwal, Lakshita
Verma, Bindu
contents The examination of chest X-ray images is a crucial component in detecting various thoracic illnesses. This study introduces a new image description generation model that integrates a Vision Transformer (ViT) encoder with cross-modal attention and a GPT-4-based transformer decoder. The ViT captures high-quality visual features from chest X-rays, which are fused with text data through cross-modal attention to improve the accuracy, context, and richness of image descriptions. The GPT-4 decoder transforms these fused features into accurate and relevant captions. The model was tested on the National Institutes of Health (NIH) and Indiana University (IU) Chest X-ray datasets. On the IU dataset, it achieved scores of 0.854 (B-1), 0.883 (CIDEr), 0.759 (METEOR), and 0.712 (ROUGE-L). On the NIH dataset, it achieved the best performance on all metrics: BLEU 1--4 (0.825, 0.788, 0.765, 0.752), CIDEr (0.857), METEOR (0.726), and ROUGE-L (0.705). This framework has the potential to enhance chest X-ray evaluation, assisting radiologists in more precise and efficient diagnosis.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16774
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Advanced Chest X-Ray Analysis via Transformer-Based Image Descriptors and Cross-Model Attention Mechanism
Agarwal, Lakshita
Verma, Bindu
Image and Video Processing
Computer Vision and Pattern Recognition
The examination of chest X-ray images is a crucial component in detecting various thoracic illnesses. This study introduces a new image description generation model that integrates a Vision Transformer (ViT) encoder with cross-modal attention and a GPT-4-based transformer decoder. The ViT captures high-quality visual features from chest X-rays, which are fused with text data through cross-modal attention to improve the accuracy, context, and richness of image descriptions. The GPT-4 decoder transforms these fused features into accurate and relevant captions. The model was tested on the National Institutes of Health (NIH) and Indiana University (IU) Chest X-ray datasets. On the IU dataset, it achieved scores of 0.854 (B-1), 0.883 (CIDEr), 0.759 (METEOR), and 0.712 (ROUGE-L). On the NIH dataset, it achieved the best performance on all metrics: BLEU 1--4 (0.825, 0.788, 0.765, 0.752), CIDEr (0.857), METEOR (0.726), and ROUGE-L (0.705). This framework has the potential to enhance chest X-ray evaluation, assisting radiologists in more precise and efficient diagnosis.
title Advanced Chest X-Ray Analysis via Transformer-Based Image Descriptors and Cross-Model Attention Mechanism
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.16774