De Novo Identification and Visualization of Important Cell Populations for Classic Hodgkin Lymphoma Using Flow Cytometry and Machine Learning.
De Novo Identification and Visualization of Important Cell Populations for Classic Hodgkin Lymphoma Using Flow Cytometry and Machine Learning.
复制标题
使用流式细胞术和机器学习对经典霍奇金淋巴瘤的重要细胞群进行从头识别和可视化。
DOI：
10.1093/ajcp/aqab076
复制
发表时间：
2021
影响因子：
3.5
通讯作者：
Lee,AaronY
中科院分区：
文献类型：
--
作者：
Simonson,PaulD;Wu,Yue;Wu,David;Fromm,JonathanR;Lee,AaronY
目标流式细胞术数据的自动分类有可能减少错误并加速流式细胞术解释。我们需要一种准确、直观、易于理解的机器学习方法，并突出显示在算法对给定病例的预测中最重要的细胞。方法我们开发了一套卷积神经网络，用于使用二维 (2D) 直方图检测经典霍奇金淋巴瘤时对有影响的细胞群进行分类和可视化。分别使用 977 例和 245 例临床流式细胞术病例的数据进行训练和测试。每个流式细胞术文件创建了 78 个非门控 2D 直方图。计算沙普利附加解释 (SHAP) 值以确定最具影响力的二维直方图和直方图中的区域。然后，使用标准流式细胞术软件将所有 78 个直方图的 SHAP 值投影回原始细胞数据，以进行门控和可视化。结果该算法实现了 67.7% 的召回率（灵敏度）、82.4% 的精度和 0.92 的接收器操作特征面积。用于个体预测的重要细胞群的可视化证明了与已知生物学的相关性。结论所提出的方法使得模型具有可解释性，同时突出了个体流式细胞术样本中的重要细胞群，在诊断和发现以前被忽视的关键细胞群方面具有潜在的应用。
ObjectivesAutomated classification of flow cytometry data has the potential to reduce errors and accelerate flow cytometry interpretation. We desired a machine learning approach that is accurate, is intuitively easy to understand, and highlights the cells that are most important in the algorithm’s prediction for a given case.MethodsWe developed an ensemble of convolutional neural networks for classification and visualization of impactful cell populations in detecting classic Hodgkin lymphoma using two-dimensional (2D) histograms. Data from 977 and 245 clinical flow cytometry cases were used for training and testing, respectively. Seventy-eight nongated 2D histograms were created per flow cytometry file. Shapley additive explanation (SHAP) values were calculated to determine the most impactful 2D histograms and regions within histograms. SHAP values from all 78 histograms were then projected back to the original cell data for gating and visualization using standard flow cytometry software.ResultsThe algorithm achieved 67.7% recall (sensitivity), 82.4% precision, and 0.92 area under the receiver operating characteristic. Visualization of the important cell populations for individual predictions demonstrated correlations with known biology.ConclusionsThe method presented enables model explainability while highlighting important cell populations in individual flow cytometry specimens, with potential applications in both diagnosis and discovery of previously overlooked key cell populations.