文献速递骨肌技术与安全DR

基于X线片的骨肿瘤风险分层深度学习模型多中心研究

Radiograph-based Deep Learning Algorithm for Assisting Bone Tumor Risk Assessment: A Multicenter Study.
PubMed 文献 · Radiology · 2026-01-01

本研究回顾性纳入10个中心1777例病理证实的骨肿瘤患者,并前瞻性测试152例,开发结合影像、临床及语义RADS特征的双视图交叉注意力模型DL-Clinic-RADS。该模型在外部测试集AUC达0.96,前瞻性测试集达0.99,显著优于放射科医生和Bone-RADS评估。AI辅助下医生平均AUC提高0.07,阅片时间缩短,报告一致性改善。

要点

  • AI辅助可将放射科医生AUC平均提升0.07,并缩短阅片时间约3秒
  • 放射科医生和Bone-RADS在外部集对骨肿瘤良恶性风险分层AUC仅为0.68-0.82
  • DL-Clinic-RADS外部集AUC达0.96,前瞻性测试集达0.99,显著优于常规评估

核心结论

  • DL-Clinic-RADS显著改善骨肿瘤X线风险分层性能,优于放射科医生和Bone-RADS评估
  • 加入AI辅助后阅片者平均AUC提升0.07,报告一致性和工作效率均改善

研究设计与样本

  • 前瞻性测试集来自其中2个中心2025年5月至8月连续招募的152例参与者(男性79例,平均年龄36.22±21.27岁)
  • 模型为双视图交叉注意力视觉Transformer,整合临床特征和语义RADS特征并以专家共识为参考标准
  • 对照评估包括9名肌骨放射科医生、Bone-RADS以及AI辅助分类,主要终点为AUC

关键影像表现/征象

  • 模型输入基于X线双视图并整合临床与语义RADS特征进行风险分层
  • Bone-RADS和放射科医生对外部集骨肿瘤良性与潜在恶性二分类评估的AUC区间为0.68-0.82

诊断标准与关键数值

  • DL-Clinic-RADS外部测试集AUC为0.96(95%CI:0.94,0.98),前瞻性测试集AUC为0.99(95%CI:0.97,1.00)
  • 模型性能优于其他5种模型(P<.001),也优于放射科医生及Bone-RADS评估(P<.001)
  • AI辅助后阅片者平均AUC增加0.07(95%CI:0.03,0.11),Fleiss κ提升+0.06至+0.23,中位阅片时间减少3秒

临床应用与阅片要点

  • 骨肿瘤X线阅片可参考AI输出的良性与潜在恶性(中间型或恶性)二分类风险提示
  • AI辅助可提升不同年资医生间报告一致性,并在日常流程中减少阅片时间

局限性

  • 研究为回顾性设计,前瞻性测试仅来自2个中心且样本量有限
  • 对照放射科医生评估AUC区间较宽,提示观察者间变异较大

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 Accurate radiograph-based risk stratification is critical for bone tumor management. However, the multicenter performance of the Bone Reporting and Data System (Bone-RADS) and the added value of deep learning-based decision support remain unclear. Purpose To develop and evaluate a radiograph-based deep learning model for binary risk stratification-benign versus potentially malignant (ie, intermediate or malignant)-and to compare it with radiologist and Bone-RADS assessments. Materials and Methods This multicenter study retrospectively obtained radiographs of histopathologically confirmed bone tumors from 10 institutions (January 2010 to December 2024) and prospectively recruited participants from two of these centers for testing (May-August 2025). The developed image-clinical/semantic-RADS attention combined model (DL-Clinic-RADS) used a two-view cross-attention vision transformer integrating clinical and semantic features with expert consensus. The model performance was compared with that of nine musculoskeletal radiologists, Bone-RADS, and artificial intelligence (AI)-aided classification. The primary endpoint was the area under the receiver operating characteristic curve (AUC), with secondary endpoints including precision-recall curves, calibration, decision curve analysis, interreader agreement, reading time and confidence, and simulated clinical decision-making. Results The retrospective dataset comprised 1777 patients (1009 male; mean age, 36.93 years ± 21.32 [SD]), and the prospective testing dataset comprised 152 participants (79 male; mean age, 36.22 years ± 21.27). The DL-Clinic-RADS achieved an AUC of 0.96 (95% CI: 0.94, 0.98) in the external set and 0.99 (95% CI: 0.97, 1.00) in the prospective set, outperforming the other five models (P < .001), radiologist assessments (external set AUC, 0.68-0.82; P < .001), and the Bone-RADS assessment (external set AUC, 0.75-0.81; P < .001). With AI assistance, the mean reader AUC increased by 0.07 (95% CI: 0.03, 0.11), the interreader agreement improved (Fleiss κ, +0.06 to +0.23), and the median reading time decreased by 3 seconds overall. Conclusion Compared with the Bone-RADS and radiologist assessments, the DL-Clinic-RADS significantly improved the radiographic risk stratification of bone tumors, enhancing clinical decision-making and workflow efficiency. © RSNA, 2026 Clinical trial registration no. ChiCTR2500102778 Supplemental material is available for this article. See also the editorial by Tordjman and Taouli in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Song, Xu, Jiang, et al. Radiograph-based Deep Learning Algorithm for Assisting Bone Tumor Risk Assessment: A Multicenter Study. Radiology. 2026. PMID: 42517768. doi:10.1148/radiol.252921

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。