基于深度学习的人工智能对放射科医生在磁敏感加权成像上识别黑质小体1异常表现的影响
这项回顾性诊断病例对照研究分析了139例磁敏感加权成像扫描(59例帕金森病患者和80名健康参与者),评估基于深度学习的人工智能软件对不同经验水平放射科医生检测黑质小体1异常的诊断性能的影响。结果显示,人工智能辅助使三位读者的特异度显著提高,读者间一致性从Fleiss kappa 0.73提高到0.87,经验较少的读者净重分类指数改善更明显(12.8% vs 0.8%)。
要点
- AI辅助使三位读者的特异度显著提高,读者间一致性Fleiss kappa从0.73升至0.87。
- 经验较少的读者净重分类指数改善(12.8%)大于经验丰富读者(0.8%)。
- 经验较少组中,读者与AI不一致在帕金森病组显著高于正常组(8.1% vs 3.8%,P=0.029)。
核心结论
- 基于深度学习的人工智能可提高磁敏感加权成像上检测黑质小体1异常的诊断性能,尤其使经验较少的放射科医生获益,这些发现凸显了改善帕金森病诊断工作流程的潜力。
研究设计与样本
- 回顾性诊断病例对照研究,分析139例磁敏感加权成像扫描(59例帕金森病患者和80名健康参与者),使用3T MRI成像,AI模型(版本1.0.1.0;Heuron Corporation,首尔,韩国)采用基于YOLOX的目标检测和SparseInst分割模型生成黑质小体1异常评估;四位放射科医生(两位经验丰富的神经放射科医生和两位经验较少的住院医师)采用交叉研究设计在有和无AI辅助下评估黑质小体1异常。
诊断标准与关键数值
- AI辅助与无AI辅助相比,三位读者的特异度显著提高(0.86 vs 0.94,P=0.004;0.91 vs 0.97,P=0.024;0.90 vs 0.97,P=0.012);读者间一致性Fleiss kappa从0.73(95%CI:0.61-0.84)提高到0.87(95%CI:0.76-0.99);净重分类指数在四位读者中的三位显示显著改善;按经验水平分组,经验较少读者净重分类指数=12.8%(95%CI:0.067-0.190),经验丰富读者净重分类指数=0.8%(95%CI:-0.037-0.051);经验较少组中读者与AI不一致在帕金森病组显著高于正常组(8.1% vs 3.8%,P=0.029)。
临床应用与阅片要点
- 作者指出基于深度学习的人工智能可提高磁敏感加权成像上检测黑质小体1异常的诊断性能,尤其使经验较少的放射科医生获益,并认为这些发现凸显了改善帕金森病诊断工作流程的潜力。
局限性
- 原文未报告局限性。
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
OBJECTIVE: To evaluate the effect of deep learning (DL)-based artificial intelligence (AI) software on the diagnostic performance of radiologists with different experience levels in detecting nigrosome 1 (N1) abnormalities on susceptibility map-weighted imaging (SMwI).
MATERIALS AND METHODS: This retrospective diagnostic case-control study analyzed 139 SMwI scans of 59 patients with Parkinson's disease (PD) and 80 healthy participants. Participants were imaged using 3T MRI, and AI-generated assessments for N1 abnormalities were obtained using an AI model (version 1.0.1.0; Heuron Corporation, Seoul, Korea), which utilized YOLOX-based object detection and SparseInst segmentation models. Four radiologists (two experienced neuroradiologists and two less experienced residents) evaluated N1 abnormalities with and without AI in a crossover study design. Diagnostic performance metrics, inter-reader agreements, and reader responses to AI-generated assessments were evaluated.
RESULTS: Use of AI significantly improved diagnostic performance compared with interpretation without it across three readers, with significant increases in specificity (0.86 vs. 0.94, P = 0.004; 0.91 vs. 0.97, P = 0.024; and 0.90 vs. 0.97, P = 0.012). Inter-reader agreement also improved with AI, as Fleiss's kappa increased from 0.73 (95% confidence interval [CI]: 0.61-0.84) to 0.87 (95% CI: 0.76-0.99). The net reclassification index (NRI) demonstrated significant improvement in three of the four readers. When grouped by experience level, less experienced readers showed greater improvement (NRI = 12.8%, 95% CI: 0.067-0.190) than experienced readers (NRI = 0.8%, 95% CI: -0.037-0.051). In the less experienced group, reader-AI disagreement was significantly higher in the PD group than in the normal group (8.1% vs. 3.8%, P = 0.029).
CONCLUSION: DL-based AI enhances the diagnostic performance in detecting N1 abnormalities on SMwI, particularly benefiting less experienced radiologists. These findings underscore the potential for improving diagnostic workflows for PD.
引用
- Park J, Lim CY, Won SY, et al. Effect of Deep Learning-Based Artificial Intelligence on Radiologists' Performance in Identifying Nigrosome 1 Abnormalities on Susceptibility Map-Weighted Imaging. Korean J Radiol. 2025. PMID: 40736409. doi:10.3348/kjr.2025.0208
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。