以解剖为中心的深度学习提高放射学骶髂关节炎检测的泛化能力与进展预测
这项回顾性多中心研究纳入四个中轴型脊柱关节炎患者队列的骨盆X线片,训练以解剖为中心(裁剪至骶髂关节边界框)和全片两种神经网络,并在三个独立测试集比较。以解剖为中心的模型在三个测试集上AUC分别为0.899、0.846、0.957,准确率0.821、0.744、0.906;该模型判为高风险的患者2年内放射学骶髂关节炎进展的OR为2.16(95%CI 1.19, 3.86)。
要点
- 以解剖为中心的模型在三个测试集AUC均高于标准模型(0.899 vs 0.853、0.846 vs 0.817、0.957 vs 0.947)。
- 以解剖为中心的模型判为高风险者2年内放射学骶髂关节炎进展OR为2.16(95%CI 1.19, 3.86)。
- 模型作为完全开源资源随本研究发布。
核心结论
- 以解剖为中心的深度学习可提高模型检测放射学骶髂关节炎的泛化能力,该模型作为完全开源资源随本研究发布。
研究设计与样本
- 回顾性多中心研究,纳入四个中轴型脊柱关节炎患者队列的骨盆X线片,采集自大学医院和社区医院。
- 第一队列1483张X线片,分为训练集(n=1261)和验证集(n=222)。
- 其余三个队列分别含436、340和163例患者,作为独立测试数据集。
- 第二队列中311例患者的随访数据用于检验进展预测能力。
- 训练两种神经网络:一种基于裁剪至骶髂关节边界框的图像(以解剖为中心),另一种基于全X线片。
主要发现
- 三个测试集上,标准模型AUC分别为0.853、0.817、0.947,准确率分别为0.770、0.724、0.850。
- 三个测试集上,以解剖为中心的模型AUC分别为0.899、0.846、0.957,准确率分别为0.821、0.744、0.906。
- 以解剖为中心的模型判为高风险的患者,2年内放射学骶髂关节炎进展的OR为2.16(95%CI 1.19, 3.86)。
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)。
原文
PURPOSE: To examine whether incorporating anatomy-centred deep learning can improve generalisability and enable prediction of disease progression. METHODS: This retrospective multicentre study included conventional pelvic radiographs of four different patient cohorts focusing on axial spondyloarthritis collected at university and community hospitals. The first cohort, which consisted of 1483 radiographs, was split into training (n=1261) and validation (n=222) sets. The other cohorts comprising 436, 340 and 163 patients, respectively, were used as independent test datasets. For the second cohort, follow-up data of 311 patients was used to examine progression prediction capabilities. Two neural networks were trained, one on images cropped to the bounding box of the sacroiliac joints (anatomy-centred) and the other one on full radiographs. The performance of the models was compared using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity. RESULTS: On the three test datasets, the standard model achieved AUC scores of 0.853, 0.817, 0.947, with an accuracy of 0.770, 0.724, 0.850. Whereas the anatomy-centred model achieved AUC scores of 0.899, 0.846, 0.957, with an accuracy of 0.821, 0.744, 0.906, respectively. The patients who were identified as high risk by the anatomy-centred model had an OR of 2.16 (95% CI 1.19, 3.86) for having progression of radiographic sacroiliitis within 2 years. CONCLUSION: Anatomy-centred deep learning can improve the generalisability of models in detecting radiographic sacroiliitis. The model is published as fully open source alongside this study.
引用
- Dorfner FJ, Vahldiek JL, Donle L, et al. Anatomy-centred deep learning improves generalisability and progression prediction in radiographic sacroiliitis detection. RMD Open. 2024. PMID: 39719299. doi:10.1136/rmdopen-2024-004628
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。