A Multimodal Approach For Endoscopic VCE Image Classification Using BiomedCLIP-PubMedBERT
This work addresses the need for efficient diagnostic tools in gastrointestinal healthcare, though it is incremental as it applies an existing multimodal method to a new medical imaging domain.
The paper tackled the problem of classifying abnormalities in Video Capsule Endoscopy (VCE) frames by fine-tuning the BiomedCLIP-PubMedBERT multimodal model, achieving strong performance metrics such as accuracy, recall, and F1 score for ten specific classes.
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.