深度学习算法在数字X线摄影上检测股骨头骨坏死的性能:与放射科医生评估的比较
这项两中心回顾性非劣效研究纳入1892个髋关节(1037个病变、855个正常),比较深度学习算法与两名放射科医生在数字X线摄影上诊断股骨头骨坏死的敏感度。算法敏感度在时间外部测试集和地理外部测试集上均非劣于两位医生,且对塌陷前病变的敏感度高于经验较少医生(75.9% vs 57.4%)。
要点
- 深度学习算法诊断股骨头骨坏死的敏感度非劣于经验较少和经验丰富的放射科医生。
- 时间外部测试集算法敏感度84.8%,经验较少医生77.6%,经验丰富医生82.4%。
- 地理外部测试集算法敏感度75.2%,经验较少医生77.6%,经验丰富医生78.0%。
核心结论
- 深度学习算法在数字X线摄影上诊断股骨头骨坏死的敏感度非劣于经验较少和经验丰富的放射科医生的评估。
研究设计与样本
- 两中心回顾性非劣效研究,连续纳入年龄≥16岁、经MR图像确诊股骨头骨坏死的患者,使用单侧裁剪的髋关节正位X线摄影,数据集包括训练集(n=1346)、内部验证集(n=148)、时间外部测试集(n=148)和地理外部测试集(n=250)。
诊断标准与关键数值
- 时间外部测试集敏感度和特异度:深度学习算法84.8%和91.3%,经验较少放射科医生77.6%和100.0%,经验丰富放射科医生82.4%和100.0%;地理外部测试集敏感度和特异度:深度学习算法75.2%和97.2%,经验较少放射科医生77.6%和75.0%,经验丰富放射科医生78.0%和86.1%;时间外部测试集塌陷前股骨头骨坏死敏感度:深度学习算法75.9% vs 经验较少放射科医生57.4%,差值95%CI为4.5-32.8%。
临床应用与阅片要点
- 深度学习算法在数字X线摄影上诊断股骨头骨坏死的敏感度非劣于经验较少和经验丰富的放射科医生的评估。
- 时间外部测试集塌陷前股骨头骨坏死的敏感度:深度学习算法75.9% vs 经验较少放射科医生57.4%,差值95%CI为4.5-32.8%。
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. The objective of our study was to compare the sensitivity of a deep learning (DL) algorithm with the assessments by radiologists in diagnosing osteonecrosis of the femoral head (ONFH) using digital radiography. MATERIALS AND METHODS. We performed a two-center, retrospective, noninferiority study of consecutive patients (≥ 16 years old) with a diagnosis of ONFH based on MR images. We investigated the following four datasets of unilaterally cropped hip anteroposterior radiographs: training (n = 1346), internal validation (n = 148), temporal external test (n = 148), and geographic external test (n = 250). Diagnostic performance was measured for a DL algorithm, a less experienced radiologist, and an experienced radiologist. Noninferiority analyses for sensitivity were performed for the DL algorithm and both radiologists. Subgroup analysis for precollapse and postcollapse ONFH was done. RESULTS. Overall, 1892 hips (1037 diseased and 855 normal) were included. Sensitivity and specificity for the temporal external test set were 84.8% and 91.3% for the DL algorithm, 77.6% and 100.0% for the less experienced radiologist, and 82.4% and 100.0% for the experienced radiologist. Sensitivity and specificity for the geographic external test set were 75.2% and 97.2% for the DL algorithm, 77.6% and 75.0% for the less experienced radiologist, and 78.0% and 86.1% for the experienced radiologist. The sensitivity of the DL algorithm was noninferior to that of the assessments by both radiologists. The DL algorithm was more sensitive for precollapse ONFH than the assessment by the less experienced radiologist in the temporal external test set (75.9% vs 57.4%; 95% CI of the difference, 4.5-32.8%). CONCLUSION. The sensitivity of the DL algorithm for diagnosing ONFH using digital radiography was noninferior to that of both less experienced and experienced radiologist assessments.
引用
- Chee CG, Kim Y, Kang Y, et al. Performance of a Deep Learning Algorithm in Detecting Osteonecrosis of the Femoral Head on Digital Radiography: A Comparison With Assessments by Radiologists. AJR Am J Roentgenol. 2019. PMID: 30917021. doi:10.2214/AJR.18.20817
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。