大语言模型辅助前列腺双参数MRI PI-RADS评分的局限
这项回顾性单中心研究纳入210例接受经会阴认知融合靶向活检的可疑前列腺癌患者,由3名不同年资放射科医生和2个大语言模型(DeepSeek与ChatGPT-4.1)独立依据双参数MRI文字报告进行PI-RADS v2.1评分。以活检病理为金标准,结果显示LLM敏感度高但特异度与阳性预测值极低,高年资医生诊断效能最佳;PSA密度是PCa与csPCa的最强独立预测因子。
要点
- LLM敏感度高但特异度很低,不适宜独立出具PI-RADS评分。
- PI-RADS≥4作为阳性阈值时各阅片者特异度均明显提高,临床净获益更优。
- PSA密度是PCa与csPCa的最强独立预测因子,阅片时应结合使用。
核心结论
- LLM在检出PCa和csPCa方面表现出高敏感度,但特异度和PPV存在明显局限,尤其在移行带和外周带。
- 高年资放射科医生诊断效能优于LLM,LLM临床应用需谨慎。
- LLM更适合作为不确定病例的辅助工具,或在采用PI-RADS≥4较高阈值时使用。
研究设计与样本
- 3名不同年资放射科医生与2个LLM(DeepSeek、ChatGPT-4.1)独立审阅匿名双参数MRI文字报告并给出PI-RADS v2.1评分。
- 以活检病理结果为金标准,在病灶水平和患者水平分别计算敏感度、特异度、PPV、NPV与AUC,并进行决策曲线分析。
- 根据病灶位置(外周带与移行带)进行亚组分析,采用多因素logistic回归确定PCa与csPCa的独立预测因素。
关键影像表现/征象
- 高年资放射科医生PCa的AUC为0.847,csPCa的AUC为0.859,诊断效能最高。
- 主治医师敏感度达到100%,但特异度和PPV最低;住院医师敏感度相仿但特异度和PPV较低,AUC最低。
- 两个LLM均呈高敏感度但特异度极低,PPV低于所有人类阅片者。
- 移行带亚组中高年资医生表现显著优于LLM;外周带中LLM呈高敏感度但低特异度。
- 在患者水平将阳性阈值提升为PI-RADS≥4后,所有阅片者特异度均明显改善。
诊断标准与关键数值
- 病灶水平以PI-RADS≥3为阳性阈值,患者水平分别以PI-RADS≥3和PI-RADS≥4为阳性阈值进行评估。
- DeepSeek的AUC高于ChatGPT-4.1,但仍低于高年资放射科医生。
- 决策曲线分析显示PI-RADS≥4阈值临床净获益更优,其中高年资医生的评分净获益最高。
- PSA密度是PCa的最强独立预测因子(OR=109.49,95%CI:14.89-1000.00,P<0.001)。
- PSA密度是csPCa的最强独立预测因子(OR=152.16,95%CI:21.06-1000.00,P<0.001)。
临床应用与阅片要点
- 日常阅片中不应单独依赖LLM进行PI-RADS评分,高年资医生复核仍然必要。
- 对可疑病例可考虑将LLM作为辅助判读工具,并结合PI-RADS≥4阈值以减少假阳性。
- 阅片报告时应同时关注PSA密度,其与PCa和csPCa风险密切相关。
- 移行带病灶的PI-RADS评分尤其需要谨慎,LLM在该区域的局限性更明显。
局限性
- 回顾性单中心研究设计。
- LLM仅基于文字报告进行评分,未直接分析MRI图像。
- 样本量有限,仅纳入210例患者。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: Prostate cancer (PCa) is a significant global health challenge, and the prostate imaging reporting and data system (PI-RADS) is crucial for risk stratification using MRI. However, inter-reader variability, especially in the transition zone and among practitioners with differing experience levels, compromises diagnostic consistency. Large language models (LLMs) show potential in medical image analysis, particularly in standardizing reports to improve diagnostic consistency and efficiency.
OBJECTIVE: To evaluate the performance of LLMs in assisting PI-RADS scoring based on biparametric MRI text reports and compare them with radiologists of varying experience levels. Additionally, to identify independent predictors of PCa and csPCa using multivariable logistic regression analysis.
METHODS: This retrospective single-center study included 210 patients who underwent transperineal cognitive fusion-targeted biopsy for clinically suspected prostate cancer between December 2024 and July 2025. Three radiologists and two LLMs (DeepSeek and ChatGPT-4.1) independently reviewed anonymized reports and assigned PI-RADS v2.1 scores. Diagnostic performance was assessed using biopsy pathological results as the gold standard. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC) were calculated at both lesion-level (PI-RADS ≥3 as positive) and participant-level (PI-RADS ≥3 and ≥4 as positive thresholds). Decision curve analysis was performed to evaluate clinical utility. Subgroup analyses were conducted based on lesion location (peripheral zone vs. transition zone). Multivariable logistic regression analysis identified independent predictors of PCa and csPCa.
RESULTS: The senior radiologist demonstrated the highest diagnostic performance, with AUC values of 0.847 for PCa and 0.859 for csPCa. The attending physician achieved perfect sensitivity but had the lowest specificity and PPV. The resident physician had comparable sensitivity but lower specificity and PPV, resulting in the lowest AUC values. Both LLMs exhibited high sensitivity but extremely low specificity, leading to lower PPV than human readers. DeepSeek outperformed ChatGPT-4.1 in AUC but still fell short of the senior radiologist's performance. In region-specific analyses, the senior radiologist significantly outperformed LLMs in the transition zone, while LLMs showed high sensitivity but low specificity in the peripheral zone. At the participant level, raising the threshold to PI-RADS ≥4 substantially improved specificity for all readers. Decision curve analysis confirmed the superior clinical utility of the PI-RADS ≥4 threshold, with the senior radiologist's ratings achieving the highest net benefit. Multivariable logistic regression analysis identified PSA density as the strongest independent predictor for both PCa (OR = 109.49, 95% CI: 14.89-1000.00, P<0.001) and csPCa (OR = 152.16, 95% CI: 21.06-1000.00, P<0.001). Among all PI-RADS ratings, only the senior radiologist's scores retained independent predictive value for both PCa (OR = 17.94, P<0.001) and csPCa (OR = 22.69, P = 0.001).
CONCLUSION: While LLMs demonstrated high sensitivity in detecting PCa and csPCa, they had significant limitations in specificity and PPV, particularly in the transition and peripheral zones. The optimal utilization strategy involves deploying LLMs as adjuncts for indeterminate cases or when using higher diagnostic thresholds (PI-RADS ≥4). Experienced radiologists achieved better diagnostic performance, highlighting the need for cautious clinical application of LLMs. Future research should focus on optimizing LLMs to improve specificity and reliability, and combining them with human radiologists' expertise to enhance diagnostic accuracy and efficiency.
引用
- Zhang, Wu, Guo, et al. Limitations of Large Language Models in Assisting PI-RADS Scoring on Prostate Biparametric MRI Text Reports. Acad Radiol. 2026. PMID: 41521112. doi:10.1016/j.acra.2025.12.020
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。