M3T: Multi-Modal Medical Transformer to bridge Clinical Context with Visual Insights for Retinal Image Medical Description Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shaik, Nagur Shareef, Cherukuri, Teja Krishna, Ye, Dong Hye
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909437293232128
author Shaik, Nagur Shareef
Cherukuri, Teja Krishna
Ye, Dong Hye
author_facet Shaik, Nagur Shareef
Cherukuri, Teja Krishna
Ye, Dong Hye
contents Automated retinal image medical description generation is crucial for streamlining medical diagnosis and treatment planning. Existing challenges include the reliance on learned retinal image representations, difficulties in handling multiple imaging modalities, and the lack of clinical context in visual representations. Addressing these issues, we propose the Multi-Modal Medical Transformer (M3T), a novel deep learning architecture that integrates visual representations with diagnostic keywords. Unlike previous studies focusing on specific aspects, our approach efficiently learns contextual information and semantics from both modalities, enabling the generation of precise and coherent medical descriptions for retinal images. Experimental studies on the DeepEyeNet dataset validate the success of M3T in meeting ophthalmologists' standards, demonstrating a substantial 13.5% improvement in BLEU@4 over the best-performing baseline model.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13129
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle M3T: Multi-Modal Medical Transformer to bridge Clinical Context with Visual Insights for Retinal Image Medical Description Generation
Shaik, Nagur Shareef
Cherukuri, Teja Krishna
Ye, Dong Hye
Computer Vision and Pattern Recognition
Machine Learning
Automated retinal image medical description generation is crucial for streamlining medical diagnosis and treatment planning. Existing challenges include the reliance on learned retinal image representations, difficulties in handling multiple imaging modalities, and the lack of clinical context in visual representations. Addressing these issues, we propose the Multi-Modal Medical Transformer (M3T), a novel deep learning architecture that integrates visual representations with diagnostic keywords. Unlike previous studies focusing on specific aspects, our approach efficiently learns contextual information and semantics from both modalities, enabling the generation of precise and coherent medical descriptions for retinal images. Experimental studies on the DeepEyeNet dataset validate the success of M3T in meeting ophthalmologists' standards, demonstrating a substantial 13.5% improvement in BLEU@4 over the best-performing baseline model.
title M3T: Multi-Modal Medical Transformer to bridge Clinical Context with Visual Insights for Retinal Image Medical Description Generation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2406.13129