# Semiautomated breast ultrasound report generation using multimodal large language models and deep learning

## TL;DR

This paper introduces a system that uses AI to help create breast ultrasound reports faster and more accurately, reducing the workload for doctors.

## Contribution

A novel framework combining multimodal large language models and deep learning for semiautomated breast ultrasound report generation.

## Key findings

- The system achieved high accuracy in elastography classification with AUCs of 0.92, 0.91, and 0.88 for different image types.
- It detected all suspicious masses with 100% sensitivity and generated reports in 31-36 seconds per patient.
- The framework is adaptable to different ultrasound machines and reduces radiologist workload.

## Abstract

Breast ultrasound (US) imaging is essential for early breast cancer detection, yet generating diagnostic reports is labor-intensive, particularly when incorporating multimodal elastography.

This study presents a novel framework that combines multimodal large language models and deep learning to generate semiautomated breast US reports. This framework bridges the gap between manual and fully automated workflows by integrating radiologist annotations with advanced image classification and structured report compilation. A total of 2,119 elastography images and 60 annotated patient cases were retrospectively collected from two US machines.

The system demonstrated robust performance in elastography classification, achieving areas under the receiver operating characteristic curve of 0.92, 0.91, and 0.88 for shear-wave, strain, and Doppler images, respectively. In the evaluated dataset, the report generation module correctly identified all suspicious masses across both US machines, achieving 100% sensitivity in lesion detection, with an average report generation time of 31 s per patient using the GE Healthcare machine and 36 s using the Supersonic Image machine.

The proposed framework enables accurate, efficient, and device-adaptable breast US report generation by combining multimodal DL and prompt-based LLM inference. It significantly reduces radiologist workload and demonstrates potential for scalable deployment in real-world clinical workflows.