Sam-Guided Enhanced Fine-Grained Encoding with Mixed Semantic Learning for Medical Image Captioning

TL;DR

This paper introduces a novel medical image captioning method that leverages SAM-guided encoding and mixed semantic learning to improve the description of intricate details in medical images, outperforming existing models.

Contribution

It proposes a new SAM-guided encoding technique combined with mixed semantic pre-training for enhanced medical image captioning.

Findings

Outperforms BLIP2 on multiple evaluation metrics

Effectively captures both overall and detailed image features

Demonstrates improved caption quality for medical images

Abstract

With the development of multimodality and large language models, the deep learning-based technique for medical image captioning holds the potential to offer valuable diagnostic recommendations. However, current generic text and image pre-trained models do not yield satisfactory results when it comes to describing intricate details within medical images. In this paper, we present a novel medical image captioning method guided by the segment anything model (SAM) to enable enhanced encoding with both general and detailed feature extraction. In addition, our approach employs a distinctive pre-training strategy with mixed semantic learning to simultaneously capture both the overall information and finer details within medical images. We demonstrate the effectiveness of this approach, as it outperforms the pre-trained BLIP2 model on various evaluation metrics for generating descriptions of medical images.