Advancements in Medical Image Classification through Fine-Tuning Natural Domain Foundation Models

TL;DR

This paper evaluates the impact of recent foundation models like DINOv2, MAE, and AIMv2 on medical image classification, showing significant performance improvements across various datasets through fine-tuning.

Contribution

It provides a comprehensive analysis of how state-of-the-art natural domain foundation models can be effectively adapted for medical image classification tasks.

Findings

AIMv2, DINOv2, and SAM2 outperform other models in classification accuracy.

Advanced models demonstrate robustness even with limited labeled data.

Progress in natural domain training benefits medical image analysis.

Abstract

Using massive datasets, foundation models are large-scale, pre-trained models that perform a wide range of tasks. These models have shown consistently improved results with the introduction of new methods. It is crucial to analyze how these trends impact the medical field and determine whether these advancements can drive meaningful change. This study investigates the application of recent state-of-the-art foundation models, DINOv2, MAE, VMamba, CoCa, SAM2, and AIMv2, for medical image classification. We explore their effectiveness on datasets including CBIS-DDSM for mammography, ISIC2019 for skin lesions, APTOS2019 for diabetic retinopathy, and CHEXPERT for chest radiographs. By fine-tuning these models and evaluating their configurations, we aim to understand the potential of these advancements in medical image classification. The results indicate that these advanced models significantly enhance classification outcomes, demonstrating robust performance despite limited labeled data. Based on our results, AIMv2, DINOv2, and SAM2 models outperformed others, demonstrating that progress in natural domain training has positively impacted the medical domain and improved classification outcomes. Our code is publicly available at: https://github.com/sajjad-sh33/Medical-Transfer-Learning.