Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance

TL;DR

This paper introduces a novel framework for automatic ultrasound report generation that combines unsupervised and supervised learning to improve feature alignment and report accuracy, validated on large-scale datasets.

Contribution

It proposes a new method that uses unsupervised knowledge extraction and global semantic comparison to enhance ultrasound report generation.

Findings

Outperforms state-of-the-art methods on three large-scale datasets.

Effectively aligns visual and textual features in ultrasound reports.

Provides publicly available code and datasets for further research.

Abstract

Automatic report generation has arisen as a significant research area in computer-aided diagnosis, aiming to alleviate the burden on clinicians by generating reports automatically based on medical images. In this work, we propose a novel framework for automatic ultrasound report generation, leveraging a combination of unsupervised and supervised learning methods to aid the report generation process. Our framework incorporates unsupervised learning methods to extract potential knowledge from ultrasound text reports, serving as the prior information to guide the model in aligning visual and textual features, thereby addressing the challenge of feature discrepancy. Additionally, we design a global semantic comparison mechanism to enhance the performance of generating more comprehensive and accurate medical reports. To enable the implementation of ultrasound report generation, we constructed three large-scale ultrasound image-text datasets from different organs for training and validation purposes. Extensive evaluations with other state-of-the-art approaches exhibit its superior performance across all three datasets. Code and dataset are valuable at this link.