Guardado en:
Detalles Bibliográficos
Autores principales: Ganapathy, Nagarajan, Chary, Podakanti Satyajith, Pithani, Teja Venkata Ramana Kumar, Kavati, Pavan, S, Arun Kumar
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.19944
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913624404000768
author Ganapathy, Nagarajan
Chary, Podakanti Satyajith
Pithani, Teja Venkata Ramana Kumar
Kavati, Pavan
S, Arun Kumar
author_facet Ganapathy, Nagarajan
Chary, Podakanti Satyajith
Pithani, Teja Venkata Ramana Kumar
Kavati, Pavan
S, Arun Kumar
contents This Paper presents an advanced approach for fine-tuning BiomedCLIP PubMedBERT, a multimodal model, to classify abnormalities in Video Capsule Endoscopy (VCE) frames, aiming to enhance diagnostic efficiency in gastrointestinal healthcare. By integrating the PubMedBERT language model with a Vision Transformer (ViT) to process endoscopic images, our method categorizes images into ten specific classes: angioectasia, bleeding, erosion, erythema, foreign body, lymphangiectasia, polyp, ulcer, worms, and normal. Our workflow incorporates image preprocessing and fine-tunes the BiomedCLIP model to generate high-quality embeddings for both visual and textual inputs, aligning them through similarity scoring for classification. Performance metrics, including classification, accuracy, recall, and F1 score, indicate the models strong ability to accurately identify abnormalities in endoscopic frames, showing promise for practical use in clinical diagnostics.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19944
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Multimodal Approach For Endoscopic VCE Image Classification Using BiomedCLIP-PubMedBERT
Ganapathy, Nagarajan
Chary, Podakanti Satyajith
Pithani, Teja Venkata Ramana Kumar
Kavati, Pavan
S, Arun Kumar
Computer Vision and Pattern Recognition
This Paper presents an advanced approach for fine-tuning BiomedCLIP PubMedBERT, a multimodal model, to classify abnormalities in Video Capsule Endoscopy (VCE) frames, aiming to enhance diagnostic efficiency in gastrointestinal healthcare. By integrating the PubMedBERT language model with a Vision Transformer (ViT) to process endoscopic images, our method categorizes images into ten specific classes: angioectasia, bleeding, erosion, erythema, foreign body, lymphangiectasia, polyp, ulcer, worms, and normal. Our workflow incorporates image preprocessing and fine-tunes the BiomedCLIP model to generate high-quality embeddings for both visual and textual inputs, aligning them through similarity scoring for classification. Performance metrics, including classification, accuracy, recall, and F1 score, indicate the models strong ability to accurately identify abnormalities in endoscopic frames, showing promise for practical use in clinical diagnostics.
title A Multimodal Approach For Endoscopic VCE Image Classification Using BiomedCLIP-PubMedBERT
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.19944