计算机科学
人工智能
模态(人机交互)
特征提取
术语
标准化
特征(语言学)
甲状腺疾病
超声波
机器学习
管道(软件)
模式识别(心理学)
钥匙(锁)
可视化
编码器
医学
匹配(统计)
放射科
对比度(视觉)
数据挖掘
计算机视觉
甲状腺
医学影像学
鉴定(生物学)
医学物理学
数据提取
作者
Siqi Zhou,Dandan Li,Yue Zhao,Xu Fang,Peng Liu,Fangang Meng
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2025-09-15
卷期号:: 1-4
标识
DOI:10.1109/ius62464.2025.11201556
摘要
Thyroid ultrasound is an essential modality for disease detection; however, its diagnostic efficacy is frequently compromised by inconsistencies in image interpretation and reporting. To address this, this study introduces a multimodal framework that leverages large language models (LLMs) to improve the efficiency, accuracy, and standardization of thyroid ultrasound report generation. The proposed framework integrates a multi-path visual encoder for hierarchical feature extraction and employs a two-stage pipeline that utilizes MiniCPM-V 2.6 and Deepseek-R1 70B to generate structured reports. The fine-tuning of MiniCPM-V 2.6 was conducted using Low-Rank Adaptation (LoRA), which substantially reduced training costs while enhancing performance. Evaluated on a dataset of 8,312 TI-RADS-compliant thyroid ultrasound samples, the model demonstrated a 25.7% improvement in feature extraction accuracy. Furthermore, it achieved 92.8% accuracy in key terminology generation and 87.8% precision for identifying pathological elements. Most notably, the TI-RADS classification accuracy increased significantly from 22.1% to 82.3%. A comparative analysis confirms that Deepseek-R1 70B surpasses other leading models across all evaluation metrics. This framework represents a significant advancement in intelligent ultrasonic diagnosis and holds considerable potential to improve clinical outcomes.
科研通智能强力驱动
Strongly Powered by AbleSci AI