Share：
Share this content in WeChat
X
[Chinese][PDF]122887
• Clinical Article •
Machine learning to distinguish stage ⅠA cervical cancer from high-grade squamous intraepithelial lesion-based on MRI radiomics models
FAN Zhichang  XIA Yuwei  ZHEN Junping  ZHOU Yukun  JIN Bo  BIAN Wenjin  YANG Jie 

Cite this article as: Fan ZC, Xia YW, Zhen JP, et al. Machine learning to distinguish stage ⅠA cervical cancer from high-grade squamous intraepithelial lesion-based on MRI radiomics models[J]. Chin J Magn Reson Imaging, 2021, 12(6): 38-43. DOI:10.12015/issn.1674-8034.2021.06.008.


[Abstract] Objective Using cervical MRI images to extract radiomic features and establish machine learning models to identify stage ⅠA cervical cancer and high-grade squamous intraepithelial lesions (HSIL). Materials andMethods A retrospective analysis of 43 patients with stage ⅠA cervical cancer and 51 patients with HSIL confirmed by surgery and pathology was performed, and 20% (n=19) of the samples were selected as the test set. The preoperative MRI images were collected to upload to the radiomics cloud platform. sagittal T2WI, axial T2WI and T2FS were manually segmented layer by layer to obtain the three-dimensional volume of interest (VOI) of the cervix, and extract the omics features. Variance threshold analysis method, univariate feature selection method (SelectKBest) and least absolute shrinkage and selection operator (LASSO) were used for data dimensionality reduction and feature selection. Random forest model was used for machine learning, ROC curve was drawn to analyze the diagnostic efficiency of different sequence radiomics models.Results Based on OSag-T2WI, OAx-T1WI, OAx-T2FS and OSag-T2WI combined with OAx-T2FS, 8, 10, 6 and 9 effective features were obtained. The random forest model based on OSag-T2WI combined with OAx-T2FS has the highest diagnostic performance, with AUC of 0.89 [95% CI (0.74—1.00)]; the model based on OAx-T1WI has the lowest diagnostic performance, with AUC of 0.51 [95% CI (0.23—0.78)].Conclusions The random forest model of radiomics based on MRI can better distinguish stage ⅠA cervical cancer from HSIL without clear focus, which is of great significance for reducing invasive examination and guiding surgical procedures before surgery.
[Keywords] cervical cancer；high-grade squamous intraepithelial lesion；magnetic resonance imaging；radiomics；machine-learning

FAN Zhichang1   XIA Yuwei2   ZHEN Junping3   ZHOU Yukun4   JIN Bo5   BIAN Wenjin1   YANG Jie1  

1 Shanxi Medical University, Taiyuan 030001, China

2 Huiying Medical Technology, Beijing 100192, China

3 Department of Imaging, the Second Hospital of Shanxi Medical University, Taiyuan 030001, China

4 Department of Imaging, the First Hospital of Shanxi Medical University, Taiyuan 030001, China

5 Department of Imaging, the Shanxi Children's Hospital, Taiyuan 030001, China

Zhen JP, E-mail: harrygin@163.com

Conflicts of interest   None.

This work was part of Shanxi Returned Overseas Students Research Funding Project (No. 2014-077).
Received  2020-12-31
Accepted  2021-03-18
DOI: 10.12015/issn.1674-8034.2021.06.008
Cite this article as: Fan ZC, Xia YW, Zhen JP, et al. Machine learning to distinguish stage ⅠA cervical cancer from high-grade squamous intraepithelial lesion-based on MRI radiomics models[J]. Chin J Magn Reson Imaging, 2021, 12(6): 38-43. DOI:10.12015/issn.1674-8034.2021.06.008.

1
Bray F, Ferlay J, Soerjomataram I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA, 2018, 68(6): 394-424. DOI: 10.3322/caac.21492.
2
Voltaggio L, Cimino-Mathews A, Bishop JA, et al. Current concepts in the diagnosis and pathobiology of intraepithelial neoplasia: A review by organ system[J]. CA Cancer J Clin, 2016, 66(5): 408-436. DOI: 10.3322/caac.21350.
3
Bhatla N, Aoki D, Sharma DN, et al. Cancer of the cervix uteri[J]. Int J Gynaecol Obstet, 2018, 143(Suppl 2): 22-36. DOI: 10.1002/ijgo.12611.
4
Perkins RB, Guido RS, Castle PE, et al. 2019 ASCCP risk-based management consensus guidelines for abnormal cervical cancer screening tests and cancer precursors[J]. J Low Genit Tract Dis, 2020, 24(2): 102-131. DOI: 10.1097/LGT.0000000000000525.
5
Cohen PA, Jhingran A, Oaknin A, et al. Cervical cancer[J]. The Lancet, 2019, 393(10167): 169-182. DOI: 10.1016/s0140-6736(18)32470-x.
6
Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
7
Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.
8
Court LE, Fave X, Mackin D, et al. Computational resources for radiomics[J]. Translational Cancer Research, 2016, 5(4): 340-348. DOI: 10.21037/tcr.2016.06.17.
9
Cui YQ, Wang LL, Zhao LP, et al. Application progressof radiomics in cervical cancer[J]. Chin J Magn Reson Imaging, 2020, 11(6): 477-480. DOI: 10.12015/issn.1674-8034.2020.06.020.
10
Sawaya GF, Smith-McCune KM. Kuppermann cervical cancer screening: More choices in 2019[J]. JAMA, 2019, 321(20): 2018-2019. DOI: 10.1001/jama.2019.4595.
11
Hricak H, Gatsonis C, Chi DS, et al. Role of imaging in pretreatment evaluation of early invasive cervical cancer: results of the intergroup study American College of Radiology Imaging Network 6651- Gynecologic Oncology Group 183[J]. J Clin Oncol, 2005, 23(36): 9329-9337. DOI: 10.1200/jco.2005.02.0354.
12
Selman TJ, Mann C, Zamora J, et al. Diagnostic accuracy of tests for lymph node status in primary cervical cancer: a systematic review and meta-analysis[J]. CMAJ, 2008, 178(7): 855-862. DOI: 10.1503/cmaj.071124.
13
Roy S, Whitehead TD, Quirk JD, et al. Optimal co-clinical radiomics: Sensitivity of radiomic features to tumour volume, image noise and resolution in co-clinical T1-weighted and T2-weighted magnetic resonance imaging[J]. EBio Medicine, 2020, 59: 2352-3964. DOI: 10.1016/j.ebiom.2020.102963.
14
Liu Z, Zhang XY, Shi YJ, et al. Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer[J]. Clin Cancer Res, 2017, 23(23): 7253-7262. DOI: 10.1158/1078-0432.Ccr-17-1038.
15
Mu W, Chen Z, Liang Y, et al. Staging of cervical cancer based on tumor heterogeneity characterized by texture features on (18)F-FDG PET images[J]. Phys Med Biol, 2015, 60(13): 5123-5139. DOI: 10.1088/0031-9155/60/13/5123.
16
Ng F, Ganeshan B, Kozarski R, et al. Assessment of primary colorectal cancer heterogeneity by using whole-tumor texture analysis: contrast-enhanced CT texture as a biomarker of 5-year survival[J]. Radiology, 2013, 266(1): 177-184. DOI: 10.1148/radiol.12120254.
17
Conners RW, Harlow CA. A theoretical comparison of texture algorithms[J]. IEEE Trans Pattern Anal Mach Intell, 1980, 2(3): 204-222. DOI: 10.1109/tpami.1980.4767008.
18
Haralick, Robert M., Shanmugam, et al. Textural Features for Image Classification. Systems, Man and Cybernetics, IEEE Transactions on, 1973
19
Loh HH, Leu JG. The analysis of natural textures using run length features[J]. IEEE Transactions on Industrial Electronics, 1988, 35(2): 323-328.
20
Xu DH, Kurani A, Furst J, et al. Run-length encoding for volumetric texture. The 4th IASTED International Conference on Visualization, Imaging, and Image Processing, 2004.
21
Shen WC, Chen SW, Liang JA, et al. [18]Fluorodeoxyglucose positron emission tomography for the textural features of cervical cancer associated with lymph node metastasis and histological type[J]. Eur J Nucl Med Mol Imaging, 2017, 44(10): 1721-1731. DOI: 10.1007/s00259-017-3697-1.
22
Thibault Guillaume, Fertil Bernard, Navarro Claire, et al. Texture Indexes and Gray Level Size Zone Matrix Application to Cell Nuclei Classification. in 10th International Conference on Pattern Recognition and Information Processing. 2009.
23
Lucia F, Visvikis D, Desseroit MC, et al. Prediction of outcome using pretreatment F-FDG PET/CT and MRI radiomics in locally advanced cervical cancer treated with chemoradiotherapy[J]. Eur J Nucl Med Mol Imaging, 2018, 45(5): 768-786. DOI: 10.1007/s00259-017-3898-7.
24
Crandall JP, Fraum TJ, Lee M, et al. Repeatability of F-FDG PET radiomic features in cervical cancer[J]. J Nucl Med, 2020, 62(5): 1535-5667. DOI: 10.2967/jnumed.120.247999.
25
Guo R, Shen XZ, Xin RQ, et al. Predictive value of random forest based on MRI radiomics in evaluating the invasion depth of endometrial carcinoma[J]. Chin J Magn Reson Imaging, 2020, 11(12): 1133-1137. DOI: 10.12015/issn.1674-8034.2020.12.011.
26
Yu H, Meng X, Chen H, et al. Correlation between mammographic radiomics features and the level of tumor-infiltrating lymphocytes in patients with triple-negative breast cancer[J]. Front Oncol, 2020, 10: 412. DOI: 10.3389/fonc.2020.00412.

PREV Study on the relationship between epicardial adipose tissue and left ventricular remodeling in hypertrophic cardiomyopathy based on T1 mapping technology
NEXT Changes of positive and negative network connectivity related to hand knob area after stroke: A rs-fMRI study
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn