[1]乔琳,吴文娜,卢振泰.基于影像组学的脑脊液细胞分类方法[J].中国医学物理学杂志,2023,40(2):244-250.[doi:DOI:10.3969/j.issn.1005-202X.2023.02.020]
　QIAO Lin,WU Wenna,LU Zhentai.Radiomics-based cerebrospinal fluid cell classification[J].Chinese Journal of Medical Physics,2023,40(2):244-250.[doi:DOI:10.3969/j.issn.1005-202X.2023.02.020]
点击复制

基于影像组学的脑脊液细胞分类方法()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
40卷
期数:
2023年第2期
页码:
244-250
栏目:
医学人工智能
出版日期:
2023-03-03

文章信息/Info

Title:
Radiomics-based cerebrospinal fluid cell classification
文章编号:
1005-202X（2023）02-0244-07
作者:
乔琳1; 吴文娜2; 卢振泰2
1.广东三九脑科医院检验科， 广东 广州 510515； 2.南方医科大学生物医学工程学院， 广东 广州 510515
Author(s):
QIAO Lin1;  WU Wenna2;  LU Zhentai2
1. Clinical Laboratory, Guangdong Sanjiu Brain Hospital, Guangzhou 510515, China 2. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China
关键词:
白细胞; 分割; 形状颜色特征; 影像组学; 特征提取
Keywords:
white cerebrospinal fluid cell segmentation shape and color features radiomics feature extraction
分类号:
R318；R331.142
DOI:
DOI:10.3969/j.issn.1005-202X.2023.02.020
文献标志码:
A
摘要:
目的：基于影像组学构建出更为高效、准确的脑脊液细胞判别模型。方法：回顾性收集3 331张脑脊液细胞显微图像，其中吞噬细胞167张、单核细胞332张、淋巴细胞1 081张、中性粒细胞1 751张。首先在显微图像上分割出细胞核、细胞核凸包区域和细胞核凸包区域的部分细胞质，然后设计3种细胞核形状特征，即圆度、凸度、坚固性。针对细胞核、凸包区域和凸包区域的部分细胞质设计48种颜色特征。基于细胞核凸包区域提取4 676种纹理特征。结果：共提取了4 727个影像组学特征，在经过ANOVA和LASSO特征选择之后，保留了519个特征，且形状特征和颜色特征都得到了较高比例的保留（100.0%, 66.7%）。特征选择之后，利用SMOTE数据增强和SVM分类器在测试集上进行预测，各项评价指标Accuracy、Sensitivity、Specificity、Precision、F1_score、AUC高达0.953、0.948、0.990、0.961、0.955、0.996。结论：本文提出的新的细胞显微图像特征提取方案和分类模型对细胞分类问题非常有效，且避免了细胞质分割的难题，无需分割细胞，只需分割细胞核和细胞核凸包区域就可以得到较好的分类结果。
Abstract:
Abstract: Objective To build a more efficient and accurate cerebrospinal fluid cell discrimination model based on radiomics. Methods A total of 3 331 microscopic images of cerebrospinal fluid cells were retrospectively collected, including 167 of phagocytes, 332 of monocytes, 1 081 of lymphocytes, and 1 751 of neutrophils. After segmenting the nucleus, nucleus convex hull and some cytoplasm of the nucleus convex hull in the microscopic images, 3 kinds of nuclear shape features, including roundness, convexity and firmness, 48 color features of the nucleus, nucleus convex hull and some cytoplasm of the nucleus convex hull, and 4 676 texture features of nucleus convex hull were extracted. Results A total of 4 727 radiomic features were obtained. After ANOVA and LASSO feature selection, only 519 features were retained, and both shape features and color features were retained in a high proportion (100.0%, 66.7%). After feature selection, SMOTE data enhancement and SVM classifier were used for the prediction on the test set. The results showed that the accuracy, sensitivity, specificity, precision, F1_score, and AUC were as high as 0.953, 0.948, 0.990, 0.961, 0.955, and 0.996, respectively. Conclusion The proposed feature extraction scheme and classification model for cell microscopic image is effective for cell classification, and avoid the cytoplasm segmentation. It is not necessary to segment cells, but only to segment the nucleus and the nucleus convex hull to obtain better classification results.

相似文献/References:

[1]张 娟,杨子立,袁克虹.基于改进SymRG算法的腹主动脉瘤分割及自动定位方法[J].中国医学物理学杂志,2015,32(01):60.[doi:10.3969/j.issn.1005-202X.2015.01.015]
[2]王晓飞,聂生东,王远军,等.改进的K-均值聚类算法及其在脑组织分割中的应用[J].中国医学物理学杂志,2014,31(02):4760.[doi:10.3969/j.issn.1005-202X.2014.02.010]
[3]王晓飞,聂生东,王远军.改进的Brain Extraction Tool算法及其在脑实质分割中的应用[J].中国医学物理学杂志,2016,33(2):113.[doi:10.3969/j.issn.1005-202X.2016.02.002]
　[J].Chinese Journal of Medical Physics,2016,33(2):113.[doi:10.3969/j.issn.1005-202X.2016.02.002]
[4]徐效文,杨志刚.光学相干层析医学图像分割研究现状[J].中国医学物理学杂志,2016,33(7):697.[doi:10.3969/j.issn.1005-202X.2016.07.011]
　[J].Chinese Journal of Medical Physics,2016,33(2):697.[doi:10.3969/j.issn.1005-202X.2016.07.011]
[5]张文莉,吕晓琪,谷宇,等. 基于肺部CT图像中肺实质分割的研究进展[J].中国医学物理学杂志,2017,34(9):902.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.009]
　[J].Chinese Journal of Medical Physics,2017,34(2):902.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.009]
[6]刘欢,虞刚,路玉昆,等.带有预处理的计划CT和在线CT的形变配准方法[J].中国医学物理学杂志,2018,35(4):410.[doi:DOI:10.3969/j.issn.1005-202X.2018.04.008]
　LIU Huan,YU Gang,LU Yukun,et al.A preprocessing-based method for deformation registration of planned CT and online CT[J].Chinese Journal of Medical Physics,2018,35(2):410.[doi:DOI:10.3969/j.issn.1005-202X.2018.04.008]
[7]高磊,段辉宏,周韡鼎,等. 基于CT影像的肺叶分割技术研究进展[J].中国医学物理学杂志,2019,36(10):1168.[doi:DOI:10.3969/j.issn.1005-202X.2019.10.010]
　GAO Lei,DUAN Huihong,ZHOU Weiding,et al. Progress on CT image-based lung lobe segmentation techniques[J].Chinese Journal of Medical Physics,2019,36(2):1168.[doi:DOI:10.3969/j.issn.1005-202X.2019.10.010]
[8]张倩雯,陈明,秦玉芳,等.基于3D ResUnet网络的肺结节分割[J].中国医学物理学杂志,2019,36(11):1356.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.021]
　ZHANG Qianwen,CHEN Ming,QIN Yufang,et al.Lung nodule segmentation based on 3D ResUnet network[J].Chinese Journal of Medical Physics,2019,36(2):1356.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.021]
[9]王月红,郝崇伟.肺超声联合白细胞、降钙素原对儿童获得性肺炎的诊断价值[J].中国医学物理学杂志,2021,38(6):717.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.011]
　WANG Yuehong,HAO Chongwei.Diagnostic value of lung ultrasound combined with white blood cells and procalcitonin in pediatric community- and hospital-acquired pneumonia[J].Chinese Journal of Medical Physics,2021,38(2):717.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.011]
[10]周意龙,卫子然,蔡清萍,等.基于卷积神经网络胃癌分割与T分期算法[J].中国医学物理学杂志,2022,39(2):215.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.015]
　ZHOU Yilong,WEI Ziran,CAI Qingping,et al.Gastric cancer segmentation and T staging algorithm based on convolutional neural network[J].Chinese Journal of Medical Physics,2022,39(2):215.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.015]

备注/Memo

备注/Memo:
【收稿日期】2022-09-11 【基金项目】广东省科技计划项目（2020A1414040021）；广州市科技计划项目（202103000037） 【作者简介】乔琳，主管技师，研究方向：细胞形态学人工智能，E-mail: 119276068@qq.com 【通信作者】吴文娜，硕士，研究方向：医学图像处理，E-mail: wu_wen_na@163.com
更新日期/Last Update: 2023-03-03