[1]张亚洲,李智伟,农卫霞,等.基于深度学习的急性白血病流式细胞术检测报告文本资料自动分类研究[J].医学信息,2025,38(08):15-20.[doi:10.3969/j.issn.1006-1959.2025.08.003]
　ZHANG Yazhou,LI Zhiwei,NONG Weixia,et al.Automatic Classification of Text Data for Flow Cytometry Detection of Acute Leukemia Based on Deep Learning[J].Journal of Medical Information,2025,38(08):15-20.[doi:10.3969/j.issn.1006-1959.2025.08.003]
点击复制

基于深度学习的急性白血病流式细胞术检测报告文本资料自动分类研究()
分享到：

医学信息[ISSN:1006-1959/CN:61-1278/R]

卷:
38卷
期数:
2025年08期
页码:
15-20
栏目:
临床信息学
出版日期:
2025-04-15

文章信息/Info

Title:
Automatic Classification of Text Data for Flow Cytometry Detection of Acute Leukemia Based on Deep Learning
文章编号:
1006-1959（2025）08-0015-06
作者:
张亚洲1; 李智伟2; 农卫霞3; 雷 伟1; 摆文丽1; 李寅臻1; 李 瑞1; 王 奎1
1.石河子大学医学院预防医学系，新疆 石河子 832000；2.新疆维吾尔自治区人民医院临床检测中心，新疆 乌鲁木齐 830001；3.石河子大学医学院风湿血液科，新疆 石河子 832000
Author(s):
ZHANG Yazhou1;  LI Zhiwei2;  NONG Weixia3;  LEI Wei1;  BAI Wenli1;  LI Yinzhen1;  LI Rui1;  WANG Kui1
1.Department of Preventive Medicine, Shihezi University School of Medicine, Shihezi 832000, Xinjiang, China; 2.Clinical Testing Center, People’s Hospital of Xinjiang Uygur Autonomous Region, Urumqi 830001, Xinjiang, China; 3.Department of Rheumatology and Hematology, Shihezi University School of Medicine, Shihezi 832000, Xinjiang, China
关键词:
流式细胞术; 文本分类; CNN; 自动化分析; 深度学习
Keywords:
Flow cytometry;  Text classification;  CNN;  Automated analysis;  Deep learning
分类号:
TP311
DOI:
10.3969/j.issn.1006-1959.2025.08.003
文献标志码:
A
摘要:
目的 探索深度学习模型在流式细胞检测报告结果部分文本资料上的分类效果。方法 使用CNN、LSTM等六种深度学习模型对流式检测报告的结果部分的文字资料进行分析，并对急性白血病患者进行分类预测，最后通过综合指标F1值对模型进行评价。结果 CNN-BiLSTM混合模型的精确率、召回率、F1值最优，分别为0.7422、0.7365、0.7361；模型在正常人、急性髓系白血病、急性B淋巴细胞白血病、有核红细胞异常、中性粒细胞异常、浆细胞异常、单核细胞异常这7类的F1值均达到了70%。结论 混合模型对流式细胞术检测报告结果部分的文本资料的分类效果较好，可与前期研究联合共同构建了一个更为完整的流式细胞术自动化分析体系，进一步提高流式细胞术分析的效率和准确性。
Abstract:
Objective To explore the classification effect of deep learning model on text data of flow cytometry report results. Methods Six deep learning models such as CNN and LSTM were used to analyze the text data of the results of the flow cytometry report, classify and predict the patients with acute leukemia, and finally evaluate the model by the comprehensive index F1 score. Results The precision, recall and F1 score of the CNN-BiLSTM mixed model were the best, which were 0.7422, 0.7365 and 0.7361, respectively, and the F1 score of the model reached 70% in seven categories: normal humans, acute myeloid leukemia, acute B lymphoblastic leukemia, nucleated red blood cell abnormalities, neutrophil abnormalities, plasma cell abnormalities and monocytic abnormalities. Conclusion The mixed model has a good effect on the classification of text data in the results of flow cytometry test report, and can be combined with previous studies to build a more complete automated flow cytometry analysis system to further improve the efficiency and accuracy of flow cytometry analysis.

参考文献/References:

[1]Paul RJ,Mario R.Flow cytometry strikes gold[J].Science,2015,350(6262):739-740.[2]Jaye DL,Bray RA,Gebel HM,et al.Translational applications of flow cytometry in clinical practice[J].J Immunol,2012,188(10):4715-4719.[3]Suo YZ,Gu ZQ,Wei XB.Advances of In Vivo Flow Cytometry on Cancer Studies[J].Cytometry A,2020,97(1):15-23.[4]Cheung M,Campbell JJ,Whitby L,et al.Current trends in flow cytometry automated data analysis software[J].Cytometry A,2021,99(10):1007-1021.[5]Greg F,Marc L,Maria J,et al.Standardizing Flow Cytometry Immunophenotyping Analysis from the Human ImmunoPhenotyping Consortium[J].Scientific Reports,2016,6(1):20686.[6]郭玉娟,李智伟,芮东升,等.急性髓系白血病流式细胞术全程自动化诊断技术研究[J].石河子大学学报(自然科学版),2022,40(4):431-437.[7]雷伟,李智伟,芮东升,等.卷积神经网络在急性髓系白血病流式细胞术自动诊断中的应用[J].安徽医科大学学报,2023,58(7):1189-1193.[8]Fuda F,Chen M,Chen W,et al.Artificial intelligence in clinical multiparameter flow cytometry and mass cytometry-key tools and progress[J].Semin Diagn Pathol,2023,40(2):120-128.[9]Van Gassen S,Callebaut B,Van Helden MJ,et al.FlowSOM: Using self-organizing maps for visualization and interpretation of cytometry data[J].Cytometry A,2015,87(7):636-645.[10]Lacombe F,Lechevalier N,Vial JP,et al.An R-Derived FlowSOM Process to Analyze Unsupervised Clustering of Normal and Malignant Human Bone Marrow Classical Flow Cytometry Data[J].Cytometry A,2019,95(11):1191-1197. [11]Collobert R,Weston J,Bottou L,et al.Natural Language Processing (almost) from Scratch[J].CoRR,2011:2493-2537.[12]Pan CP,Cao HT,Zhang WW,et al.Driver activity recognition using spatial‐temporal graph convolutional LSTM networks with attention mechanism[J].IET Intelligent Transport Systems,2020,15(2):297-307.[13]宋纯贺,李泽熙,于洪霞,等.一种基于改进GoogLeNet的油井故障识别方法[J].江苏科技大学学报(自然科学版),2021,35(2):52-58.[14]王若佳,魏思仪,王继民.BiLSTM-CRF模型在中文电子病历命名实体识别中的应用研究[J].文献与数据学报,2019,1(2):53-66.[15]Kamruzzaman M,Almazroui M,Salam MA,et al.Spatiotemporal drought analysis in Bangladesh using the standardized precipitation index (SPI) and standardized precipitation evapotranspiration index (SPEI)[J].Sci Rep,2022,12(1):20694.[16]马闪闪,董明利,张帆,等.基于核主成分分析的流式细胞数据分群方法研究[J].生物医学工程学杂志,2017,34(1):115-122.[17]Obeidat Y,Alqudah A M.A Hybrid Lightweight 1D CNN-LSTM Architecture for Automated ECG Beat-Wise Classification[J].Traitement du Signal: Signal Image Parole,2021,38(5):1281-1291.

相似文献/References:

[1]贾海英,黄睿,王玲玲,等.多发性骨髓瘤患者淋巴细胞亚群变化对免疫功能的影响研究[J].医学信息,2018,31(01):147.[doi:10.3969/j.issn.1006-1959.2018.01.057]
　JIA Hai-ying,HUANG Rui,WANG Ling-ling,et al.The Effect of Lymphocyte Subgroup Changes on Immune Function in Patients with Multiple Myeloma[J].Journal of Medical Information,2018,31(08):147.[doi:10.3969/j.issn.1006-1959.2018.01.057]
[2]徐晓雪.CD4单阳参考品辅助检测九色标记人血样品的流式分析技术[J].医学信息,2021,34(20):90.[doi:10.3969/j.issn.1006-1959.2021.20.022]
　XU Xiao-xue.Flow Pattern Analysis Technique for CD4 Single-positive Reference Substance-assisted Detection of Nine-color Labeled Human Blood Samples[J].Journal of Medical Information,2021,34(08):90.[doi:10.3969/j.issn.1006-1959.2021.20.022]
[3]邓 娜,吴冠宇,杨 柳,等.流式细胞术在多发性骨髓瘤治疗中的应用价值[J].医学信息,2022,35(02):75.[doi:10.3969/j.issn.1006-1959.2022.02.018]
　DENG Na,WU Guan-yu,YANG Liu,et al.Application Value of Flow Cytometry in the Treatment of Multiple Myeloma[J].Journal of Medical Information,2022,35(08):75.[doi:10.3969/j.issn.1006-1959.2022.02.018]
[4]赵崇山,王宁方.脾脏硬度联合流式细胞术在急性髓系白血病微小残留病监测中的意义[J].医学信息,2022,35(05):121.[doi:10.3969/j.issn.1006-1959.2022.05.031]
　ZHAO Chong-shan,WANG Ning-fang.The Significance of Spleen Stiffness Measurement Combine with Flow Cytometry in Acute Myeloid Leukemia Minimal Residual Disease[J].Journal of Medical Information,2022,35(08):121.[doi:10.3969/j.issn.1006-1959.2022.05.031]
[5]雷 伟,李智伟,郭玉娟,等.人工神经网络在流式细胞术数据分析中的应用[J].医学信息,2023,36(18):74.[doi:10.3969/j.issn.1006-1959.2023.18.013]
　LEI Wei,LI Zhi-wei,GUO Yu-juan,et al.Application of Artificial Neural Networks in Flow Cytometry Data Analysis[J].Journal of Medical Information,2023,36(08):74.[doi:10.3969/j.issn.1006-1959.2023.18.013]
[6]摆文丽,农卫霞,李智伟,等.FCM数据细胞亚群分类和标注的自动化研究[J].医学信息,2024,37(06):78.[doi:10.3969/j.issn.1006-1959.2024.06.013]
　BAI Wen-li,NONG Wei-xia,LI Zhi-wei,et al.Automatic Classification and Labeling of Cell Subsets in FCM Data[J].Journal of Medical Information,2024,37(08):78.[doi:10.3969/j.issn.1006-1959.2024.06.013]

更新日期/Last Update: 1900-01-01