股骨头坏死MRI深度学习模型诊断与分期效能的系统综述与荟萃分析
该系统综述纳入20项研究、4625例患者、6036髋,评估MRI深度学习模型对股骨头坏死的检测、分期及塌陷预测表现。检测的独立观察荟萃分析汇总敏感度0.900、特异度0.866、AUC 0.921;二分类分期汇总敏感度0.941、特异度0.877、AUC 0.961。作者认为模型诊断准确度高,但分期仅区分早晚期,且外部验证表现下降,需前瞻性多中心验证后才能临床常规使用。
要点
- MRI深度学习对股骨头坏死检测与早晚期二分类分期准确度高,但仅区分早晚期,不评价各分期系统内中间分级。
- 外部验证队列性能低于内部或交叉验证队列,现阶段不宜直接用于临床常规报告。
- 塌陷预测证据仅两项研究,外部AUC为0.851与0.919,证据有限,报告时需谨慎。
核心结论
- 深度学习模型在MRI上对股骨头坏死检测与二分类分期具有高诊断准确度,塌陷预测证据有限但表现有前景。
- 汇总分期准确度仅反映早期与晚期病变的区分,不涵盖各分级系统内中间级别。
- 外部验证性能下降,需要前瞻性多中心外部验证后方可考虑常规临床应用。
研究设计与样本
- 前瞻性注册的系统综述与荟萃分析,检索MEDLINE、Embase、Scopus、Web of Science及IEEE Xplore。
- 纳入20项研究,共4625例患者、6036髋,均为成人髋部MRI应用人工智能模型进行检测、分期、分割辅助分级或塌陷预测。
- 二分类分期研究与含完整2×2四格表的检测研究采用双变量随机效应模型汇总,PROSPERO注册号CRD420261347627。
诊断标准与关键数值
- 检测独立观察荟萃分析:汇总敏感度0.900(95% CI 0.812-0.949),特异度0.866(95% CI 0.773-0.924),HSROC AUC 0.921。
- 检测含分割分析的敏感性分析汇总:敏感度0.935(95% CI 0.902-0.957),特异度0.950(95% CI 0.905-0.974),HSROC AUC 0.971。
- 二分类分期荟萃分析含6项研究10个模型-数据集配对、2593髋:汇总敏感度0.941(95% CI 0.901-0.965),特异度0.877(95% CI 0.823-0.917),HSROC AUC 0.961。
- 外部验证队列分期AUC为0.895,内部或交叉验证队列为0.975,差异bootstrap 95% CI为-0.104至0.009,跨越零点。
- 塌陷预测仅两项研究,外部AUC分别为0.851和0.919,探索性汇总AUC为0.891。
临床应用与阅片要点
- 阅片时可将深度学习模型作为股骨头坏死检测与早晚期二分类分期的辅助工具,但需注意其不评价中间级别。
- 报告不宜依据模型输出区分各分级系统内的中间细分级别,仅可参考早期与晚期的大类判断。
- 外部验证表现低于内部验证,提示模型在不同中心数据上的泛化能力有限,临床使用应保守。
局限性
- 汇总分期准确度仅反映早期与晚期的二分类判别,不涵盖各分期系统内中间分级。
- 外部验证队列性能低于内部或交叉验证队列,证据支持的外部泛化性不足。
- 塌陷预测相关证据仅两项研究,证据数量有限,汇总结果属于探索性。
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
OBJECTIVES: To evaluate the diagnostic and prognostic performance of deep learning models for osteonecrosis of the femoral head (ONFH) on MRI, including detection, staging, and collapse prediction.
METHODS: This prospectively registered search was conducted in MEDLINE, Embase, Scopus, Web of Science, and IEEE Xplore. Studies applying artificial intelligence models to hip MRI for ONFH detection, staging, segmentation-assisted grading, or collapse prediction in adults were eligible. Binary staging studies and detection studies with complete 2 × 2 contingency tables were pooled using bivariate random-effects models.
RESULTS: Twenty studies comprising 4625 patients and 6036 hips, where reported, were included. For ONFH detection, the primary bivariate meta-analysis restricted to independent observations (Scenario B; k = 4) yielded a pooled sensitivity of 0.900 (95% CI: 0.812-0.949), specificity of 0.866 (95% CI: 0.773-0.924), and HSROC AUC of 0.921; a segment-inclusive sensitivity analysis (Scenario A; k = 8 from seven unique studies) yielded 0.935 (95% CI: 0.902-0.957), 0.950 (95% CI: 0.905-0.974), and 0.971, respectively. For binary staging, 10 model-dataset pairs from six studies comprising 2593 hips were included in the diagnostic test accuracy meta-analysis; pooled sensitivity was 0.941 (95% CI: 0.901-0.965), pooled specificity was 0.877 (95% CI: 0.823-0.917), and HSROC AUC was 0.961. Leave-one-out analyses confirmed robustness, whereas external validation cohorts showed lower performance than internal or cross-validation cohorts (staging AUC, 0.895 vs 0.975; bootstrap 95% CI for the difference -0.104 to 0.009, crossing zero). For collapse prediction, evidence was limited to two studies, with external AUCs of 0.851 and 0.919 and an exploratory pooled AUC of 0.891.
CONCLUSION: Deep learning models demonstrate high diagnostic accuracy on MRI for ONFH detection and binary staging, with promising but limited evidence for collapse prediction. Because pooled staging accuracy reflects discrimination between early-stage (pre-collapse/low-grade) and late-stage (post-collapse/high-grade) disease only, and does not capture intermediate gradations within each staging system, and because performance was reduced on external validation, prospective multicenter external testing is needed before routine clinical implementation.
PROSPERO REGISTRATION: CRD420261347627, Protocol version 2.0, 21 March 2026.
引用
- Başal, Karakas, Serteser, et al. Deep learning models for osteonecrosis of the femoral head on MRI: a systematic review and meta-analysis of diagnostic performance, staging accuracy, and external generalizability. Skeletal Radiol. 2026. PMID: 42791360. doi:10.1007/s00256-026-05372-3
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。