Nonkes Lourens J P, Kuper Willemijn F E, Berrens-Hogenbirk Karin, Musson Ruben E A, van Hasselt Peter M, Huisman Albert
Central Diagnostic Laboratory University Medical Center Utrecht Utrecht The Netherlands.
Department of Metabolic Diseases, Wilhelmina Children's Hospital, University Medical Center Utrecht Utrecht University Utrecht The Netherlands.
JIMD Rep. 2021 Jan 25;58(1):100-103. doi: 10.1002/jmd2.12191. eCollection 2021 Mar.
Quantifying lymphocyte vacuolization in peripheral blood smears (PBSs) serves as a measure for disease severity in CLN3 disease-a lysosomal storage disorder of childhood-onset. However, thus far quantification methods are based on labor-intensive manual assessment of PBSs. As machine learning techniques like convolutional neural networks (CNNs) have been deployed quite successfully in detecting pathological features in PBSs, we explored whether these techniques could be utilized to automate quantification of lymphocyte vacuolization. Here, we present and validate a deep learning pipeline that automates quantification of lymphocyte vacuolization. By using two CNNs in succession, trained for cytoplasm-segmentation and vacuolization-detection, respectively, we obtained an excellent correlation with manual quantification of lymphocyte vacuolization ( = 0.98, n = 40). These results show that CNNs can be utilized to automate the otherwise cumbersome task of manually quantifying lymphocyte vacuolization, thereby aiding prompt clinical decisions in relation to CLN3 disease, and potentially beyond.
对外周血涂片（PBS）中的淋巴细胞空泡化进行量化，可作为衡量CLN3病（一种儿童期发病的溶酶体贮积症）疾病严重程度的指标。然而，到目前为止，量化方法是基于对外周血涂片进行劳动强度大的人工评估。由于卷积神经网络（CNN）等机器学习技术已在检测外周血涂片中的病理特征方面取得了相当成功的应用，我们探讨了这些技术是否可用于自动量化淋巴细胞空泡化。在此，我们展示并验证了一种深度学习流程，该流程可自动量化淋巴细胞空泡化。通过依次使用两个分别针对细胞质分割和空泡化检测进行训练的卷积神经网络，我们获得了与淋巴细胞空泡化人工量化的极佳相关性（r = 0.98，n = 40）。这些结果表明，卷积神经网络可用于自动完成手动量化淋巴细胞空泡化这一原本繁琐的任务，从而有助于在CLN3病及可能更广泛的范围内做出迅速的临床决策。
