文献速递骨肌CTMR

双能CT检测髋关节骨髓水肿的诊断效能:深度学习模型与肌骨医师及放射科医师的比较

Diagnostic performance for detecting bone marrow edema of the hip on dual-energy CT: Deep learning model vs. musculoskeletal physicians and radiologists.
PubMed 文献 · Eur J Radiol · 2022-04-30

本回顾性研究纳入73例在1个月内接受髋关节双能CT和MRI检查的成人患者,以MRI为参考标准,比较深度学习模型与2名骨科医师、3名放射科医师在测试集1297幅图像上检测骨髓水肿的诊断效能。深度学习模型AUC为0.84、敏感度79%、特异度90%,显著高于经验较少读者的AUC 0.61-0.70和敏感度29-66%,特异度无损失,与经验丰富放射科医师的AUC 0.83、敏感度71%、特异度94%相似。

要点

  • 深度学习模型检测髋关节骨髓水肿的AUC为0.84,敏感度79%,特异度90%。
  • 模型AUC显著高于非或低经验读者(0.61-0.70,p<0.001),与训练有素放射科医师(0.83)相似(p=0.402)。
  • 读者间一致性为一般(κ=0.303),AUC强依赖于读者双能CT经验。

核心结论

  • 深度学习模型在双能CT上检测骨髓水肿的诊断效能优于经验较少的医师,与训练有素的放射科医师相当。

研究设计与样本

  • 回顾性研究,纳入2018年4月至2020年12月间1个月内接受髋关节双能CT和MRI的成人患者73例(平均年龄59±12岁,女性38例),共8709幅双能CT图像按85%训练/验证集(7412幅增强图像)和15%测试集(1297幅图像)划分,以MRI为参考标准。

诊断标准与关键数值

  • 深度学习模型检测骨髓水肿的AUC为0.84,敏感度79%,特异度90%;非或低经验读者AUC为0.61-0.70,敏感度29-66%,特异度74-93%;训练有素放射科医师AUC为0.83,敏感度71%,特异度94%;模型AUC与低经验读者比较p<0.001,与训练有素读者比较p=0.402;读者间一致性Fleiss κ=0.303。

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

PURPOSE: To compare the diagnostic performance of a deep learning (DL) model with that of musculoskeletal physicians and radiologists for detecting bone marrow edema on dual-energy CT (DECT).

METHOD: This retrospective study included adult patients underwent hip DECT and MRI within 1 month between April 2018 and December 2020. A total of 8709 DECT images were divided into training/validation (85%, 7412 augmented images) and test (15%, 1297 images) sets. The images were labeled as present/absent bone marrow edema, with MRI as reference standard. We developed and trained a DL model to detect bone marrow edema from DECT images. Thereafter, DL model, two orthopedic surgeons, and three radiologists evaluated the presence of bone marrow edema on every test image. The diagnostic performance of the DL model and readers was compared. Inter-reader agreement was calculated using Fleiss-kappa statistics.

RESULTS: A total of 73 patients (mean age, 59 ± 12 years; 38 female) were included. The DL model had a significantly higher area under the curve (AUC, 0.84 vs. 0.61-0.70, p < 0.001) and sensitivity (79% vs. 29-66%) without loss of specificity (90% vs. 74-93%) than the non- or less-experienced readers and similar to the trained reader (AUC, 0.83, p = 0.402; sensitivity, 71%; specificity, 94%). Additionally, AUCs were strongly dependent on the reader's DECT experience. Inter-reader agreement was fair (κ = 0.303).

CONCLUSION: The DL model showed better diagnostic performance than less-experienced physicians in detecting bone marrow edema on DECT and comparable performance to a trained radiologist.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Park, Kim, Park, et al. Diagnostic performance for detecting bone marrow edema of the hip on dual-energy CT: Deep learning model vs. musculoskeletal physicians and radiologists. Eur J Radiol. 2022. PMID: 35525130. doi:10.1016/j.ejrad.2022.110337

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。