用Transformers自动识别流式细胞术数据中的细胞群
Automated Identification of Cell Populations in Flow Cytometry Data with Transformers
摘要：
急性淋巴细胞白血病（ALL）是儿童和青少年最常见的血液恶性肿瘤。微小残留病（MRD）是ALL的一个强有力的预后因素，它是患者体内持续存在的白血病细胞数量的衡量标准。治疗后根据多参数流式细胞术（FCM）数据进行手动MRD评估耗时且主观。在这项工作中，我们提出了一个自动化的方法来计算MRD值直接从FCM数据。我们提出了一种新的神经网络方法的基础上的Transformer架构，学习直接识别样本中的原始细胞。我们以监督的方式训练我们的方法，并在来自三个不同临床中心的公开可用的ALL FCM数据上对其进行评估。我们的方法在519个B-ALL样本上进行评估时，F1得分中位数为~0.94，并且在4个不同数据集上显示出比现有方法更好的结果
英文摘要：
Acute Lymphoblastic Leukemia (ALL) is the most frequent hematologic malignancy in children and adolescents. A strong prognostic factor in ALL is given by the Minimal Residual Disease (MRD), which is a measure for the number of leukemic cells persistent in a patient. Manual MRD assessment from Multiparameter Flow Cytometry (FCM) data after treatment is time-consuming and subjective. In this work, we present an automated method to compute the MRD value directly from FCM data. We present a novel neural network approach based on the transformer architecture that learns to directly identify blast cells in a sample. We train our method in a supervised manner and evaluate it on publicly available ALL FCM data from three different clinical centers. Our method reaches a median F1 score of ~0.94 when evaluated on 519 B-ALL samples and shows better results than existing methods on 4 different datasets
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
