Supplementary Material for: Glomerular basement membrane thickness estimation and stratification via active semi-supervised learning model

Introduction: The measure of Glomerular Basement Membrane (GBM) thickness is used as diagnostic criteria for kidney glomerular diseases. The GBM thickness measurement, a time-consuming task, is performed by expert pathologists on transmission electron microscopy (TEM) images, therefore, it is affected by subjectivity and reproducibility issues.
Methods: Here we introduce a fully automated pipeline for the GBM segmentation and successive thickness estimation, starting from TEM images. This method is based on an active semi-supervised learning training procedure of a convolutional neural network model. Starting from the areas automatically identified by the model, we provide a robust measurement of membrane thickness using pixels distance matrix and computer vision techniques. Using these values, we trained a machine learning model to automatically determine the GBM thickness. To verify the accuracy of the method, we compared the predicted results with the full iconographic materials and diagnostic record reports from 42 renal biopsies having normal-thick (n. 21), thin- (n. 10), thick-GBM (n. 11).
Results: The obtained segmentations were used for the automated estimation of GBM thickness via computer vision algorithms and compared with manual measurements, obtaining a correlation of Pearson’s R2 of 0.85. The GBM thickness was stratified into 3 classes, namely normal, thin, thick with a 0.63 Matthews correlation coefficient and a 0.76 accuracy.
Conclusion: The proposed pipeline obtained state-of-the-art performance in GBM segmentation, proving its robustness under image variations, such as magnification, contrast, and complex geometrical shapes. Automated measures could assist clinicians in standard clinical practice speeding up routine procedures with high diagnostic accuracy.

引言：肾小球基底膜（Glomerular Basement Membrane, GBM）厚度的测量是肾脏肾小球疾病的诊断标准之一。GBM厚度测量是一项耗时的工作，通常由专业病理学家在透射电子显微镜（Transmission Electron Microscopy, TEM）图像上完成，因此该过程易受主观性影响，且存在可重复性差的问题。
方法：本文提出了一种从TEM图像出发，用于GBM分割及后续厚度估算的全自动化流程。该方法基于卷积神经网络（Convolutional Neural Network）模型的主动半监督学习训练流程。借助模型自动识别的区域，我们通过像素距离矩阵与计算机视觉技术，实现了对膜厚度的稳健测量。基于这些测量值，我们训练了机器学习模型以自动预测GBM厚度。为验证该方法的准确性，我们将预测结果与42例肾活检样本的完整影像资料及诊断记录报告进行了比对，其中包括21例厚度正常、10例薄基底膜、11例厚基底膜样本。
结果：通过计算机视觉算法对得到的分割结果进行处理，实现了GBM厚度的自动化估算，并将其与人工测量结果进行比对，获得了0.85的皮尔逊R²相关系数。将GBM厚度分为正常、薄、厚三个类别后，马修斯相关系数（Matthews correlation coefficient）为0.63，分类准确率为0.76。
结论：本研究提出的流程在GBM分割任务中取得了最先进的性能，证实了其在图像变化（如放大倍数、对比度及复杂几何形状）下的稳健性。自动化测量可辅助临床医师开展常规临床工作，在保证较高诊断准确性的同时，加快常规检测流程。