零射击PI-RADS版本2.1使用ChatGPT-4 Turbo和Llama 3进行评分:诊断性能和与腹部放射科医生的协议
Negar Firoozeh1, Domenico Mastrodicasa1, Spencer Behr2
1Department of Radiology, University of Washington School of Medicine, 1959 NE Pacific St, BB308, Seattle, WA 981952.
像ChatGPT-4 Turbo和Llama 3这样的大型语言模型 (LLM) 在分配前列腺成像报告和数据系统 (PI-RADS) 对前列腺MRI报告的分数方面显示出高度一致,有助于瘤学家.
科学领域:
- 放射学和医学成像学 医学成像学
- 医疗保健中的人工智能
- 瘤学和前列腺癌诊断 癌症诊断
背景情况:
- 前列腺MRI解释依赖于标准化的评分系统,如前列腺成像报告和数据系统 (PI-RADS).
- 准确的PI-RADS评分对于诊断前列腺癌和指导治疗决策至关重要.
- 评估新兴人工智能技术,特别是大型语言模型 (LLM) 在临床报告中的作用至关重要.
研究的目的:
- 评估ChatGPT-4 Turbo和Llama 3在将PI-RADS分数分配给前列腺MRI报告中的诊断性能和评审者间的一致性.
- 将这些LLM的性能与经验丰富的腹部放射科医生进行比较.
- 确定LLM在前列腺MRI报告中提高一致性和准确性的潜力.
主要方法:
- 对500份结构化前列腺MRI报告进行了回顾性分析,原始PI-RADS得分匿名化.
- 两个LLM (ChatGPT-4 Turbo和Llama 3) 使用标准化提示符提取PI-RADS 2.1版本的分数.
- 两个腹部放射科医生独立地分配PI-RADS得分,第三位放射科医生解决了差异;前列腺活检结果作为参考标准.
主要成果:
- 两位LLM都表现出与放射科医生的高度一致 (94.7%-95.7%一致, κ = 0.89-0.91).
- 与放射科医生相比,ChatGPT-4 Turbo显示了与放射科医生相比PI-RADS得分更高的趋势 (P < .005).
- 预测前列腺癌的受体运行特征曲线 (AUC) 的受体下面面积相似:ChatGPT-4 Turbo和原始报告的0.79,放射科医生和Llama 3.的0.78.
结论:
- 大型语言模型与专家放射科医生在前列腺MRI的PI-RADS评分方面表现出强烈的一致.
- LLM显示有可能提高前列腺MRI报告的准确性和一致性,支持瘤诊断.
- 进一步整合LLM可以简化放射学工作流程,提高前列腺癌检测的诊断能力.
更多相关视频
07:45Author Spotlight: Standardizing Mouse In Vivo PET Imaging with Body Conforming Molds and Automated Analysis
Published on: October 25, 2024
09:49A Whole Body Dosimetry Protocol for Peptide-Receptor Radionuclide Therapy PRRT: 2D Planar Image and Hybrid 2D+3D SPECT/CT Image Methods
Published on: April 24, 2020
相关概念视频
Radiological Investigation III: Pulmonary Angiogram and PET Scan
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
Positron Emission Tomography
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
Radiological Investigation II: MRI and Ventilation Perfusion Scan
Magnetic Resonance Imaging (MRI) and Ventilation Perfusion Scans are two radiological investigations that offer detailed diagnostic images of the body, particularly lung structures.
MRI
MRI uses magnetic fields and radiofrequency signals to distinguish between normal and abnormal tissues. This technology provides a more detailed diagnostic image than CT scans, enabling it to characterize pulmonary nodules, stage bronchogenic carcinoma, and evaluate inflammatory activity in...
Imaging Studies II: Positron Emission Tomography and Scintigraphy
Fundamental Principles of PET
