Share：
Share this content in WeChat
X
[Chinese][PDF]1131129
• Experience Exchanges •
Value of T2WI-FS based radiomics features in the diagnosis of cervical cancer metastasis and lymph vascular space invasion
ZHOU Xiaoling  LAI Hua  WEN Xilin  LIU Chunying 

Cite this article as: Zhou XL, Lai H, Wen XL, et al. Value of T2WI-FS based radiomics features in the diagnosis of cervical cancer metastasis and lymph vascular space invasion[J]. Chin J Magn Reson Imaging, 2021, 12(7): 69-71, 76. DOI:10.12015/issn.1674-8034.2021.07.014.


[Abstract] Objective To investigate the value of fat-suppression T2-weighted imaging (T2WI-FS) based radiomics features in the diagnosis of cervical cancer (CC) metastasis and lymph vascular space invasion (LVSI). Materials andMethods The clinical data and image data of 66 CC patients in our hospital from June 2017 to June 2020 were retrospectively analyzed. Preoperative magnetic resonance imaging (MRI) horizontal position T2WI-FS images delineated the region of interest (ROI). Preprocessing image and ROI image were processed using A.K. software. A total of 402 radiomics features were extracted from T2WI-FS images. ANOVA+MW combined with LASSO methods were used to perform dimensionality reduction. Receiver operating characteristic (ROC) curve was used to value of T2WI-FS based radiomics features in the diagnosis of cervical cancer lymphatic metastasis and LVSI.Results The pathological examination showed that there were 22 cases with lymphatic metastasis and 44 cases without metastasis. The analysis found that lymphatic metastasis was related to the depth of cervical interstitial infiltration and LVSI (all P＜0.01). There were 27 LVSI positive patients and 39 negative patients. Analysis found that LVSI was related to the degree of tissue differentiation, the depth of cervical interstitial infiltration and lymph node metastasis (all P＜0.01). The area under the curve (AUC), sensitivity (Sen) and specificity (Spe) of T2WI-FS imaging radiomics features in the diagnosis of lymphatic metastasis were 0.857, 85.0%, and 86.7%, respectively, and those in the diagnosis of LVSI were 0.807, 68.3% and 88.3%, respectively.Conclusions Both lymph node metastasis and LVSI are affected by the depth of cervical stromal invasion. T2WI-FS imaging has high efficiency in evaluating lymph node metastasis and LVSI. The preoperative examination is of great significance in guiding surgical treatment and predicting prognosis of cervical cancer patients.
[Keywords] fat-suppression T2-weighted imaging；radiomics features；cervical cancer；lymphatic metastasis；lymph vascular space invasion；preoperative diagnostic value

ZHOU Xiaoling   LAI Hua*   WEN Xilin   LIU Chunying  

Department of Radiology, Women and Children's Hospital Affiliated to School of Medicine, University of Electronic Science and Technology of China, Chengdu Women and Children's Central Hospital, Chengdu 611731, China

Lai H, E-mail: 449535176@qq.com

Conflicts of interest   None.

Received  2021-01-29
Accepted  2021-03-25
DOI: 10.12015/issn.1674-8034.2021.07.014
Cite this article as: Zhou XL, Lai H, Wen XL, et al. Value of T2WI-FS based radiomics features in the diagnosis of cervical cancer metastasis and lymph vascular space invasion[J]. Chin J Magn Reson Imaging, 2021, 12(7): 69-71, 76. DOI:10.12015/issn.1674-8034.2021.07.014.

1
Marquina G, Manzano A, Casado A. Targeted agents in cervical cancer: beyond bevacizumab[J]. Curr Oncol Rep, 2018, 20(5): 40. DOI: 10.1007/s11912-018-0680-3.
2
Minig L, Fagotti A, Scambia G, et al. Incidence of lymph node metastases in women with low-risk early cervical cancer (＜2 cm) without lymph-vascular invasion[J]. Int J Gynecol Cancer, 2018, 28(4): 788-793. DOI: 10.1097/IGC.0000000000001236.
3
Wu Q, Shi D, Dou S, et al. Radiomics analysis of multiparametric MRI evaluates the pathological features of cervical squamous cell carcinoma[J]. J Magn Reson Imaging, 2019, 49(4): 1141-1148. DOI: 10.1002/jmri.26301.
4
Simonsen TG, Lund KV, Hompland T, et al. DCE-MRI-derived measures of tumor hypoxia and interstitial fluid pressure predict outcomes in cervical carcinoma[J]. Int J Radiat Oncol Biol Phys, 2018, 102(4): 1193-1201. DOI: 10.1016/j.ijrobp.2018.04.035.
5
Hu T, Zhu T, Sun X, et al. Survival prognosis of patients with stage IB cervical cancer treated with neoadjuvant chemotherapy combined with surgery: a meta analysis[J]. Oncology, 2018, 38(2): 126-132. DOI: 10.3781/j.issn.1000-7431.2018.33.659.
6
Li K, Sun H, Lu Z, et al. Value of [18F]FDG PET radiomic features and VEGF expression in predicting pelvic lymphatic metastasis and their potential relationship in early-stage cervical squamous cell carcinoma[J]. Eur J Radiol, 2018, 106(1): 160-166. DOI: 10.1016/j.ejrad.2018.07.024.
7
Ding R, Lu Y. Application value of MRI in preoperative clinical staging and pelvic lymph node metastasis of patients with cervical cancer[J]. Imaging research and medical application, 2018, 2(12): 129-130. DOI: CNKI:SUN:YXYY.0.2018-12-081.
8
Qin S, Gao Y, Yang Y, et al. Identifying molecular markers of cervical cancer based on competing endogenous RNA network analysis[J]. Gynecol Obstet Invest, 2019, 84(4): 350-359. DOI: 10.1159/000493476.
9
Zhang J, Wen HW. Clinicopathological factors and survival analysis of lymphatic vascular space infiltration in early cervical adenocarcinoma[J]. Progress Mod Obstetr Gynecol, 2020, 29(11): 21-26, 31. DOI: 10.13283/jcnki.xdfckjz.2020.11.033.
10
Zhou Y. Relationship between lymphatic vascular space infiltration and lymph node metastasis in early stage cervical cancer and its prognostic value[J]. J Pract Obstetr Gynecol, 2018, 34(2): 109-112. DOI: CNKI:SUN:SFCZ.0.2018-02-013.
11
Matsuo K, Shimada M, Saito T, et al. Risk stratification models for para-aortic lymph node metastasis and recurrence in stage IB-IIB cervical cancer[J]. J Gynecol Oncol. 2018, 29(1): e11. DOI: 10.3802/jgo.2018.29.e11.
12
Xiong LL, Zhang TH, Yu H, et al. Analysis of risk factors of vascular space and parametrial invasion in early cervical cancer[J]. J Pract Obstetr Gynecol, 2020, 36 (3): 208-213. DOI: CNKI:SUN:SFCZ.0.2020-03-016.
13
Lecuru FR, McCormack M, Hillemanns P, et al. SENTICOL III: an international validation study of sentinel node biopsy in early cervical cancer. A GINECO, ENGOT, GCIG and multicenter study[J]. Int J Gynecol Cancer, 2019, 29(4): 829-834. DOI: 10.1136/ijgc-2019-000332.
14
Zheng W, Chen K, Peng C, et al. Contrast-enhanced ultrasonography vs MRI for evaluation of local invasion by cervical cancer[J]. Br J Radiol, 2018, 91(1091): 20170858. DOI: 10.1259/bjr.20170858.
15
Masroor I, Rashid S, Afzal S, et al. Diagnostic accuracy of pelvic MRI for determination of the cervical involvement in endometrial cancer[J]. J Coll Physicians Surg Pak, 2018, 28(4): 262-265. DOI: 10.29271/jcpsp.
16
Zhang J, Tian W, Bu X, et al. Diagnostic significance of magnetic resonance imaging in patients with cervical cancer after brachytherapy: a Meta-analysis[J]. Acta Radiol, 2019, 60(5): 670-676. DOI: 10.1177/0284185118791199.
17
Yan CL, Qi XL, Ma JF, et al. Comparative analysis of MRI features and pathology of giant cell tumor of tendon sheath[J]. J Med Imaging, 2020, 30(3): 463-466. DOI: CNKI:SUN:XYXZ.0.2020-03-033.
18
Wang J, Li ZH, Shen F, et al. Application value of high-resolution T2WI based imageomics in preoperative staging of rectal cancer[J]. Radiol Pract, 2019, 34(11): 1251-1254. DOI: CNKI:SUN:FSXS.0.2019-11-026.
19
Cheng N, Lv XH, Ren K, et al. The diagnostic value of ivim-dwi multi model parameter analysis for cervical cancer[J]. Radiol Pract, 2017, 32(2): 157-157. DOI: CNKI:SUN:FSXS.0.2017-02-013.
20
Xu M, Gao YJ, Wu YL, et al. Comparative study on preoperative evaluation and postoperative pathology of 3.0T MRI in early cervical cancer[J]. CT Theory Appl Res, 2018, 27(1): 55-61. DOI: 10.15953/j.1004-4140.2018.27.01.07.
21
Liang CS, Cui YN, Yang WC, et al. Prediction of the expression of human epidermal growth factor receptor 2 in breast cancer based on T2WI imageomics tag[J]. Chin Med Imaging Technol, 2019, 35(4): 555-559. DOI: CNKI:SUN:ZYXX.0.2019-04-026.
22
Hou LN, Cui YF, Guo LY, et al. Application value of multi parameter MRI imaging fusion model in preoperative prediction of cervical cancer lymph node metastasis[J]. Chin J Anatomy Clin, 2020, 25(3): 213-220. DOI: 10.3760/cma.j.cn101202-20200310-00074.
23
Li HJ, Cao K, Zheng H, et al. Multi-sequence MRI texture analysis for predicting efficacy of neoadjuvant chemotherapy in uterine cervical carcinoma[J]. Chin J Med Imaging Technol, 2020, 36(8): 1215-1219.

PREV Clinical characteristics and MR imaging features of metanephric adenoma
NEXT The correlation between intravoxel incoherent motion and microvessel density and pathological differentiation of cervical cancer
  


LINK


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