A Multimodal Approach For Endoscopic VCE Image Classification Using BiomedCLIP-PubMedBERT

TL;DR

This paper introduces a multimodal deep learning approach combining PubMedBERT and Vision Transformer to classify abnormalities in endoscopic videos, improving diagnostic accuracy in gastrointestinal medicine.

Contribution

It presents a novel fine-tuning method for BiomedCLIP PubMedBERT that integrates visual and textual data for endoscopic image classification.

Findings

High classification accuracy achieved

Effective multimodal embedding alignment demonstrated

Potential for clinical diagnostic support shown

Abstract

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.