Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital Linkou Main Branch, Taoyuan, Taiwan.
Department of Anatomic Pathology, Chang Gung Memorial Hospital Linkou Main Branch, Taoyuan, Taiwan.
Nephrol Dial Transplant. 2022 Oct 19;37(11):2093-2101. doi: 10.1093/ndt/gfac143.
The extent of interstitial fibrosis in the kidney not only correlates with renal function at the time of biopsy but also predicts future renal outcome. However, its assessment by pathologists lacks good agreement. The aim of this study is to construct a machine learning-based model that enables automatic and reliable assessment of interstitial fibrosis in human kidney biopsies.
Validated cortex, glomerulus and tubule segmentation algorithms were incorporated into a single model to assess the extent of interstitial fibrosis. The model performances were compared with expert renal pathologists and correlated with patients' renal functional data.
Compared with human raters, the model had the best agreement [intraclass correlation coefficient (ICC) 0.90] to the reference in 50 test cases. The model also had a low mean bias and the narrowest 95% limits of agreement. The model was robust against colour variation on images obtained at different times, through different scanners, or from outside institutions with excellent ICCs of 0.92-0.97. The model showed significantly better test-retest reliability (ICC 0.98) than humans (ICC 0.76-0.94) and the amount of interstitial fibrosis inferred by the model strongly correlated with 405 patients' serum creatinine (r = 0.65-0.67) and estimated glomerular filtration rate (r = -0.74 to -0.76).
This study demonstrated that a trained machine learning-based model can faithfully simulate the whole process of interstitial fibrosis assessment, which traditionally can only be carried out by renal pathologists. Our data suggested that such a model may provide more reliable results, thus enabling precision medicine.
肾脏间质纤维化的程度不仅与活检时的肾功能相关，还可以预测未来的肾脏结局。然而，病理学家对此的评估一致性较差。本研究旨在构建一种基于机器学习的模型，以实现对人类肾活检中间质纤维化程度的自动和可靠评估。
将经过验证的皮质、肾小球和肾小管分割算法整合到一个单一的模型中，以评估间质纤维化的程度。将模型的性能与肾脏病理专家进行比较，并与患者的肾功能数据相关联。
与人类评估者相比，该模型在 50 个测试病例中与参考标准的一致性最好（组内相关系数 [ICC] 0.90）。该模型的平均偏差较小，95%的一致性界限较窄。该模型对不同时间、不同扫描仪或来自外部机构的图像的颜色变化具有很强的鲁棒性，ICC 值为 0.92-0.97。该模型的测试-再测试可靠性（ICC 0.98）明显优于人类（ICC 0.76-0.94），模型推断的间质纤维化程度与 405 名患者的血清肌酐（r=0.65-0.67）和估计的肾小球滤过率（r=-0.74 至-0.76）密切相关。
本研究表明，经过训练的基于机器学习的模型可以忠实地模拟间质纤维化评估的整个过程，而传统上这只能由肾脏病理学家进行。我们的数据表明，这种模型可能提供更可靠的结果，从而实现精准医疗。
