Share:
Share this content in WeChat
X
Clinical Article
Preoperative predicting lymphov-ascular space invasion in endometrial carcinoma by nomogram based on mpMRI radiomics
PENG Yongjia  LIU Xiaowen  TANG Xue  LUO Yan  JIANG Changsi  GONG Jingshan 

Cite this article as: Peng YJ, Liu XW, Tang X, et al. Preoperative predicting lymphov-ascular space invasion in endometrial carcinoma by nomogram based on mpMRI radiomics[J]. Chin J Magn Reson Imaging, 2022, 13(7): 61-67. DOI:10.12015/issn.1674-8034.2022.07.011.


[Abstract] Objective To investigate the value of multiparametric magnetic resonance imaging (mpMRI) radiomics in predicting lymphatic vascular space invasion (LVSI) in endometrial cancer (EC).Materials and Methods The clinical data of 202 patients with EC confirmed by surgery and pathology were retrospectively collected. All patients underwent pelvic mpMRI before operation,and randomly divided into training set and testing set according to ratio of 7∶3. Using the open-source ITK-SNAP software draw the outline of region of interest (ROI). EC radiomics features were extracted by the Pyradiomics software from mpMRI images. The association of clinicopathological characteristics and radiomics features with LVSI were evaluated by univariate analysis. Least absolute shrinkage and selection operator (LASSO) regression was used to screen the radiomics features and calculate rad-score. Multivariate logistic regression was used to screen for independent risk factors for LVSI. Using the R language for modeling and drawing the nomograms, and the prediction efficiency of the model was evaluated by C-index. To compare the prediction efficacy of the radiomics and the nomogram model for LVSI.Results Thirteen radiomics features were selected from 321 by LASSO regression, and calculated Rad-score. Univariate and multivariate logistic regression analyses found that the independent risk factors of LVSI were age, pathological grade, and Rad-score. The C-index of the nomogram that was constructed with the combined LVSI risk factors was 0.871 (95% CI: 0.803-0.940) and 0.810 (95% CI: 0.698-0.917) in the training set and the validation set, respectively. The C-index of the radiomics model in the training set and verification set was 0.854 (95% CI: 0.784-0.925) and 0.756 (95% CI: 0.619-0.892) respectively. Both the nomogram and the radiomics model had a good prediction efficiency for LVSI, and the nomogram was higher than the radiomics model.Conclusions The radiomics nomogram based on mpMRI can achieve a high diagnostic efficacy in preoperative evaluation of EC LVSI.
[Keywords] endometrial carcinoma;lymphatic vascular space invasion;multi-parameter magnetic resonance imaging;radiomics;nomogram

PENG Yongjia1   LIU Xiaowen1   TANG Xue2   LUO Yan2   JIANG Changsi2   GONG Jingshan2*  

1 The Second Clinical Medical College, Jinan University, Shenzhen 518020, China

2 Department of Radiology, Shenzhen People's Hospital, the Second Clinical Medical College of Jinan University, Shenzhen 518020, China

Gong JS, E-mail: jshgong@sina.com

Conflicts of interest   None.

Received  2022-03-28
Accepted  2022-06-24
DOI: 10.12015/issn.1674-8034.2022.07.011
Cite this article as: Peng YJ, Liu XW, Tang X, et al. Preoperative predicting lymphov-ascular space invasion in endometrial carcinoma by nomogram based on mpMRI radiomics[J]. Chin J Magn Reson Imaging, 2022, 13(7): 61-67.DOI:10.12015/issn.1674-8034.2022.07.011

[1]
Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019[J]. CA A Cancer J Clin, 2019, 69(1): 7-34. DOI: 10.3322/caac.21551.
[2]
Briët JM, Hollema H, Reesink N, et al. Lymphvascular space involvement: an independent prognostic factor in endometrial cancer[J]. Gynecol Oncol, 2005, 96(3): 799-804. DOI: 10.1016/j.ygyno.2004.11.033.
[3]
Long L, Sun JQ, Jiang LL, et al. MRI-based traditional radiomics and computer-vision nomogram for predicting lymphovascular space invasion in endometrial carcinoma[J]. Diagn Interv Imaging, 2021, 102(7/8): 455-462. DOI: 10.1016/j.diii.2021.02.008.
[4]
Bi Q, Chen YH, Wu KH, et al. The diagnostic value of MRI for preoperative staging in patients with endometrial cancer: a meta-analysis[J]. Acad Radiol, 2020, 27(7): 960-968. DOI: 10.1016/j.acra.2019.09.018.
[5]
Li HM, Zhang R, Li RM, et al. Noninvasive prediction of residual disease for advanced high-grade serous ovarian carcinoma by MRI-based radiomic-clinical nomogram[J]. Eur Radiol, 2021, 31(10): 7855-7864. DOI: 10.1007/s00330-021-07902-0.
[6]
Sahin H, Panico C, Ursprung S, et al. Non-contrast MRI can accurately characterize adnexal masses: a retrospective study[J]. Eur Radiol, 2021, 31(9): 6962-6973. DOI: 10.1007/s00330-021-07737-9.
[7]
Zhang Q, Guo J, Ouyang H, et al. Added-value of dynamic contrast-enhanced MRI on prediction of tumor recurrence in locally advanced cervical cancer treated with chemoradiotherapy [J]. Eur Radiol, 2022, 32(4): 2529-2539. DOI: 10.1007/s00330-021-08279-w.
[8]
Liu ZY, Wang S, Dong D, et al. The applications of radiomics in precision diagnosis and treatment of oncology: opportunities and challenges[J]. Theranostics, 2019, 9(5): 1303-1322. DOI: 10.7150/thno.30309.
[9]
Ytre-Hauge S, Dybvik JA, Lundervold A, et al. Preoperative tumor texture analysis on MRI predicts high-risk disease and reduced survival in endometrial cancer[J]. J Magn Reson Imaging, 2018, 48(6): 1637-1647. DOI: 10.1002/jmri.26184.
[10]
Sun XY, Feng QX, Xu X, et al. Radiologic-radiomic machine learning models for differentiation of benign and malignant solid renal masses: comparison with expert-level radiologists[J]. AJR Am J Roentgenol, 2020, 214(1): W44-W54. DOI: 10.2214/AJR.19.21617.
[11]
Forghani R, Chatterjee A, Reinhold C, et al. Head and neck squamous cell carcinoma: prediction of cervical lymph node metastasis by dual-energy CT texture analysis with machine learning[J]. Eur Radiol, 2019, 29(11): 6172-6181. DOI: 10.1007/s00330-019-06159-y.
[12]
Zhang KY, Zhang Y, Fang X, et al. MRI-based radiomics and ADC values are related to recurrence of endometrial carcinoma: a preliminary analysis[J]. BMC Cancer, 2021, 21: 1266. DOI: 10.1186/s12885-021-08988-x.
[13]
Yan BC, Li Y, Ma FH, et al. Radiologists with MRI-based radiomics aids to predict the pelvic lymph node metastasis in endometrial cancer: a multicenter study[J]. Eur Radiol, 2021, 31(1): 411-422. DOI: 10.1007/s00330-020-07099-8.
[14]
Chee CG, Yoon MA, Kim KW, et al. Combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT[J]. Eur Radiol, 2021, 31(9): 6825-6834. DOI: 10.1007/s00330-021-07832-x.
[15]
Xue K, Li ZL, Li ZH, et al. Identify HER-2 over expression breast cancer based on radiomics of multi-parametric MRI[J]. Radiol Pract, 2020, 35(2): 186-189. DOI: 10.13609/j.cnki.1000-0313.2020.02.012.
[16]
Ueno Y, Forghani B, Forghani R, et al. Endometrial carcinoma: MR imaging-based texture model for preoperative risk stratification-A preliminary analysis[J]. Radiology, 2017, 284(3): 748-757. DOI: 10.1148/radiol.2017161950.
[17]
Gerlinger M, Rowan AJ, Horswell S, et al. Intratumor heterogeneity and branched evolution revealed by multiregion sequencing[J]. N Engl J Med, 2012, 366(10): 883-892. DOI: 10.1056/NEJMoa1113205.
[18]
Avanzo M, Stancanello J, El Naqa I. Beyond imaging: the promise of radiomics[J]. Phys Med, 2017, 38: 122-139. DOI: 10.1016/j.ejmp.2017.05.071.
[19]
Hu QY, Whitney HM, Giger ML. Radiomics methodology for breast cancer diagnosis using multiparametric magnetic resonance imaging[J]. JMI, 2020, 7: 044502. DOI: 10.1117/1.JMI.7.4.044502.
[20]
Luo Y, Mei DD, Gong JS, et al. Multiparametric MRI-based radiomics nomogram for predicting lymphovascular space invasion in endometrial carcinoma[J]. J Magn Reson Imaging, 2020, 52(4): 1257-1262. DOI: 10.1002/jmri.27142.
[21]
Liu Y, Chen PC, Krause J, et al. How to read articles that use machine learning: users' guides to the medical literature[J]. JAMA, 2019, 322(18): 1806-1816. DOI: 10.1001/jama.2019.16489.
[22]
Antonelli M, Johnston EW, Dikaios N, et al. Machine learning classifiers can predict Gleason pattern 4 prostate cancer with greater accuracy than experienced radiologists[J]. Eur Radiol, 2019, 29(9): 4754-4764. DOI: 10.1007/s00330-019-06244-2.
[23]
Meyer HJ, Hamerla G, Leifels L, et al. Histogram analysis parameters derived from DCE-MRI in head and neck squamous cell cancer-Associations with microvessel density[J]. Eur J Radiol, 2019, 120: 108669. DOI: 10.1016/j.ejrad.2019.108669.
[24]
Hu Y, Zhang Y, Cheng JL. Diagnostic value of molybdenum target combined with DCE-MRI in different types of breast cancer[J]. Oncol Lett, 2019, 18(4): 4056-4063. DOI: 10.3892/ol.2019.10746.

PREV Differentiation of borderline and malignant epithelial tumors based on MRI-T2WI radiomics nomogram
NEXT Development and assessment of a novel nomogram based on multiple parameters MRI for predicting the risk of reintervention after high intensity focused ultrasound treatment of uterine leiomyoma
  



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