Share：
Share this content in WeChat
X
[Chinese] [PDF] 28 1
• Clinical Article •
The value of combined model based on 3.0 T high resolution T2WI imaging features in preoperative prediction of lymphatic vessel space invasion in endometrial cancer
LI Yuanyuan  DAI Mengqing  LIU Ruixue  FENG Qiang 

Cite this article as LI Y Y, DAI M Q, LIU R X, et al. The value of combined model based on 3.0 T high resolution T2WI imaging features in preoperative prediction of lymphatic vessel space invasion in endometrial cancer[J]. Chin J Magn Reson Imaging, 2026, 17(6): 110-117. DOI:10.12015/issn.1674-8034.2026.06.014.


[Abstract] Objective To investigate the value of machine learning model based on 3.0 T high-resolution T2-weighted imaging (HR-T2WI) radiomics features combined with traditional imaging and clinical parameters in predicting lymphovascular space invasion (LVSI) in endometrial cancer (EC).Materials and Methods The clinical, pathological and imaging data of 173 EC patients confirmed by surgery and pathology in Yidu Central Hospital of Weifang City from January 2019 to December 2024 were retrospectively analyzed. According to whether LVSI existed in postoperative pathological results, they were divided into LVSI-positive and LVSI-negative groups; they were randomly divided into training set and validation set according to 6∶4 ratio by simple random sampling method for model construction and validation. Clinical baseline parameters and conventional imaging features were collected from all patients, and potential risk factors were screened by single factor logistic regression analysis; At the same time, radiomics features were extracted based on 3.0 T HR-T2WI sequence images, and the minimum absolute shrinkage and selection operator (LASSO) algorithm combined with 10-fold cross validation was used to reduce the dimension of features, and the core radiomics features with discrimination value were screened out. The selected core radiomics features were fused with clinical indicators and traditional quantitative imaging indicators to construct five joint predictive models, including linear support vector classifier (Linear SVC), logistic regression (LR), random forest (RF), decision tree (DT), support vector machine (SVM). Area under the receiver operating characteristic curve (AUC), sensitivity and specificity were used to evaluate the predictive power of each model. Decision curve analysis (DCA) assesses the net clinical benefit of each model within a specified threshold range; calibration curves were used to evaluate the consistency and calibration between the predictive probability of each model and the actual observation results.Results Among the five models, the LR model demonstrated the best predictive performance, and multivariate logistic regression analysis suggested that radiomics score (Rad-score) and apparent diffusion coefficient (ADC) values were independent risk factors for predicting LVSI (P < 0.05). LR model had value of 0.89 (95% CI: 0.83 to 0.96), sensitivity of 0.84, and specificity of 0.88 in the training set and AUC value of 0.92 (95% CI: 0.85 to 1.00), sensitivity of 0.92, and specificity of 0.92 in the validation set, and had a high clinical net benefit.Conclusions The combined predictive model based on 3.0 T HR-T2WI imaging features has good predictive value for LVSI status of EC patients. The LR model exhibited optimal performance, with Rad-score and ADC serving as the primary contributing factors, offering reliable evidence for preoperative risk stratification.
[Keywords] endometrial carcinoma；lymphatic space invasion；magnetic resonance imaging；high resolution T2 weighted imaging；radiomics；preoperative prediction

LI Yuanyuan   DAI Mengqing   LIU Ruixue   FENG Qiang*  

Department of Medical Imaging, Yidu Central Hospital, Qingzhou 262500, China

Corresponding author: FENG Q, E-mail: fengyijun2018@163.com

Conflicts of interest   None.

Received  2026-02-10
Accepted  2026-05-30
DOI: 10.12015/issn.1674-8034.2026.06.014
Cite this article as LI Y Y, DAI M Q, LIU R X, et al. The value of combined model based on 3.0 T high resolution T2WI imaging features in preoperative prediction of lymphatic vessel space invasion in endometrial cancer[J]. Chin J Magn Reson Imaging, 2026, 17(6): 110-117. DOI:10.12015/issn.1674-8034.2026.06.014.

[1]
BROOKS R A, FLEMING G F, LASTRA R R, et al. Current recommendations and recent progress in endometrial cancer[J]. CA Cancer J Clin, 2019, 69(4): 258-279. DOI: 10.3322/caac.21561.
[2]
MCCLUGGAGE W G, BOSSE T, GILKS C B, et al. FIGO 2023 endometrial cancer staging: too much, too soon [J]. Int J Gynecol Cancer, 2024, 34(1): 138-143. DOI: 10.1136/ijgc-2023-004981.
[3]
GRAVBROT N, WEIL C R, DECESARIS C M, et al. Differentiation of survival outcomes by anatomic involvement and histology with the revised 2023 International Federation of Gynecology and Obstetrics staging system for endometrial cancer[J/OL]. Eur J Cancer, 2024, 201: 113913 [2025-09-01]. https://doi.org/10.1016/j.ejca.2024.113913. DOI: 10.1016/j.ejca.2024.113913.
[4]
FENG J, ZHANG Y, HUANG C Z, et al. Prognostic evaluation of lymph-vascular space invasion in patients with endometrioid and non-endometrioid endometrial cancer: A multicenter study[J/OL]. Eur J Surg Oncol, 2024, 50(4): 108261 [2025-09-01]. https://doi.org/10.1016/j.ejso.2024.108261. DOI: 10.1016/j.ejso.2024.108261.
[5]
WANG J Z, XU P, YANG X Y, et al. Association of myometrial invasion with lymphovascular space invasion, lymph node metastasis, recurrence, and overall survival in endometrial cancer: a meta-analysis of 79 studies with 68, 870 patients[J/OL]. Front Oncol, 2021, 11: 762329 [2025-09-02]. https://doi.org/10.3389/fonc.2021.762329. DOI: 10.3389/fonc.2021.762329.
[6]
HAN L, CHEN Y L, ZHENG A, et al. Prognostic value of three-tiered scoring system for lymph-vascular space invasion in endometrial cancer: a systematic review and meta-analysis[J]. Gynecol Oncol, 2024, 184: 198-205. DOI: 10.1016/j.ygyno.2024.01.046.
[7]
SUN Y, WANG Y P, CHENG X R, et al. Risk factors for pelvic and para-aortic lymph node metastasis in non-endometrioid endometrial cancer[J/OL]. Eur J Surg Oncol, 2024, 50(4): 108260 [2025-09-01]. https://doi.org/10.1016/j.ejso.2024.108260. DOI: 10.1016/j.ejso.2024.108260.
[8]
CONCIN N, MATIAS-GUIU X, CIBULA D, et al. ESGO–ESTRO–ESP guidelines for the management of patients with endometrial carcinoma: update 2025[J/OL]. Lancet Oncol, 2025, 26(8): e423-e435 [2025-10-01]. https://doi.org/10.1016/S1470-2045(25)00167-6. DOI: 10.1016/S1470-2045(25)00167-6.
[9]
PETERS E E M, NUCCI M R, GILKS C B, et al. Practical guidance for assessing and reporting lymphovascular space invasion (LVSI) in endometrial carcinoma[J]. Histopathology, 2025, 86(2): 173-182. DOI: 10.1111/his.15272.
[10]
BEREK J S, MATIAS-GUIU X, CREUTZBERG C, et al. FIGO staging of endometrial cancer: 2023[J]. Int J Gynecol Obstet, 2023, 162(2): 383-394. DOI: 10.1002/ijgo.14923.
[11]
SUN B W, ZHANG X B, DONG Y Y, et al. Prognostic significance of lymphovascular space invasion in early-stage low-grade endometrioid endometrial cancer: a fifteen-year retrospective Chinese cohort study[J/OL]. World J Surg Oncol, 2024, 22(1): 203 [2026-04-02]. https://doi.org/10.1186/s12957-024-03483-6. DOI: 10.1186/s12957-024-03483-6.
[12]
QIN Z J, WANG Y S, CHEN Y L, et al. Evaluation of prognostic significance of lymphovascular space invasion in early stage endometrial cancer: a systematic review and meta-analysis[J/OL]. Front Oncol, 2023, 13: 1286221 [2024-04-03]. https://doi.org/10.3389/fonc.2023.1286221. DOI: 10.3389/fonc.2023.1286221.
[13]
KAYRAKLIOGLU N, KATSAKHYAN L, COHEN P A, et al. Perceptions of controversies and unresolved issues in the 2014 FIGO staging system for endometrial cancer: Survey results from members of the international society of gynecological pathologists and international gynecologic cancer society[J]. Int J Gynecol Pathol, 2024, 43(3): 242-252. DOI: 10.1097/PGP.0000000000000977.
[14]
AKÇAY A, GÜLTEKIN M A, ALTıNTAŞ F, et al. Updated endometrial cancer FIGO staging: the role of MRI in determining newly included histopathological criteria[J]. Abdom Radiol (NY), 2024, 49(10): 3711-3721. DOI: 10.1007/s00261-024-04398-2.
[15]
MANGANARO L, NICOLINO G M, DOLCIAMI M, et al. Radiomics in cervical and endometrial cancer[J/OL]. Br J Radiol, 2021, 94(1125): 20201314 [2025-10-09]. https://doi.org/10.1259/bjr.20201314. DOI: 10.1259/bjr.20201314.
[16]
LI H X, REN Z, MO F, et al. The value of ADC histogram in preoperative prediction of lymphvascular space invasion in early cervical cancer[J]. Chin J Magn Reson Imaging, 2025, 16(9): 132-139. DOI: 10.12015/issn.1674-8034.2025.09.020.
[17]
YI Q Q, WANG Y, ZOU S S, et al. Super-resolution reconstruction technique enhances the diagnostic efficacy of deep learning-based prediction of lymphvascular space invasion in endometrial cancer[J]. Chin J Magn Reson Imaging, 2025, 16(10): 83-88. DOI: 10.12015/issn.1674-8034.2025.10.013.
[18]
LIU X F, YAN B C, LI Y, et al. Radiomics feature as a preoperative predictive of lymphovascular invasion in early-stage endometrial cancer: A multicenter study[J/OL]. Front Oncol, 2022, 12: 966529 [2025-10-12]. https://doi.org/10.3389/fonc.2022.966529. DOI: 10.3389/fonc.2022.966529.
[19]
LUO Y, MEI D D, GONG J S, et al. Multiparametric MRI-based radiomics nomogram for predicting lymphovascular space invasion in endometrial carcinoma[J]. Magnetic Resonance Imaging, 2020, 52(4): 1257-1262. DOI: 10.1002/jmri.27142.
[20]
LIU D, HUANG J Y, ZHANG Y F, et al. Multimodal MRI-based radiomics models for the preoperative prediction of lymphovascular space invasion of endometrial carcinoma[J/OL]. BMC Med Imaging, 2024, 24(1): 252 [2025-11-01]. https://doi.org/10.1186/s12880-024-01430-1. DOI: 10.1186/s12880-024-01430-1.
[21]
YAN Z H, SHENG Y L, HOU X R, et al. Impact of lymphovascular space invasion on prognosis and adjuvant therapy in early-stage endometrial carcinoma[J]. Chin J Radiat Oncol, 2025, 34(5): 502-507. DOI: 10.3760/cma.j.cn113030-20240807-00304.
[22]
HAN Y, SUN M Y. Advances in MRI studies of lymphvascular space invasion in endometrial carcinoma[J]. Chin J Magn Reson Imaging, 2024, 15(7): 216-220, 234. DOI: 10.12015/issn.1674-8034.2024.07.036.
[23]
LIU Y, CHEN P C, 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.
[24]
YTRE-HAUGE S, DYBVIK J A, 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.
[25]
SAARELAINEN S K, PELTONEN N, LEHTIMÄKI T, et al. Predictive value of serum human epididymis protein 4 and cancer antigen 125 concentrations in endometrial carcinoma[J/OL]. Am J Obstet Gynecol, 2013, 209(2): 142.e1-142.e6 [2025-11-10]. https://doi.org/10.1016/j.ajog.2013.04.014. DOI: 10.1016/j.ajog.2013.04.014.
[26]
AYHAN A, ŞAHIN H, SARI M E, et al. Prognostic significance of lymphovascular space invasion in low-risk endometrial cancer[J]. Int J Gynecol Cancer, 2019, 29(3): 505-512. DOI: 10.1136/ijgc-2018-000069.
[27]
OLIVER-PEREZ M R, PADILLA-ISERTE P, ARENCIBIA-SANCHEZ O, et al. Lymphovascular space invasion in early-stage endometrial cancer (LySEC): patterns of recurrence and predictors. A multicentre retrospective cohort study of the Spain gynecologic oncology group[J/OL]. Cancers, 2023, 15(9): 2612 [2025-12-01]. https://doi.org/10.3390/cancers15092612. DOI: 10.3390/cancers15092612.
[28]
OAKNIN A, BOSSE T J, CREUTZBERG C L, et al. Endometrial cancer: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up[J]. Ann Oncol, 2022, 33(9): 860-877. DOI: 10.1016/j.annonc.2022.05.009.
[29]
TAŞKUM İ, BADEMKıRAN M H, ÇETIN F, et al. A novel predictive model of lymphovascular space invasion in early-stage endometrial cancer[J]. Turk J Obstet Gynecol, 2024, 21(1): 37-42. DOI: 10.4274/tjod.galenos.2024.92597.
[30]
RAFIEE A, MOHAMMADIZADEH F. Association of lymphovascular space invasion (LVSI) with histological tumor grade and myometrial invasion in endometrial carcinoma: a review study[J]. Adv Biomed Res, 2023, 12: 159 [2025-11-13]. https://doi.org/10.4103/abr.abr_52_23. DOI: 10.4103/abr.abr_52_23.
[31]
CUI J, GUO R, XIN R Q. Predictive value of machine learning model based on ADC radiomics in evaluating the invasion depth of endometrial carcinoma[J]. Chin J Magn Reson Imaging, 2025, 16(3): 77-82. DOI: 10.12015/issn.1674-8034.2025.03.012.
[32]
ZHANG M, JING M Y, CAO Y T, et al. The value of the apparent diffusion coefficient in preoperative prediction of myometrial infiltration, Ki-67 and P53 expression levels in endometrial carcinoma[J]. Chin J Magn Reson Imaging, 2023, 14(7): 78-85. DOI: 10.12015/issn.1674-8034.2023.07.014.
[33]
VARGHESE B A, FIELDS B K K, HWANG D H, et al. Spatial assessments in texture analysis: what the radiologist needs to know[J/OL]. Front Radiol, 2023, 3: 1240544 [2025-11-13]. https://doi.org/10.3389/fradi.2023.1240544. DOI: 10.3389/fradi.2023.1240544.
[34]
LIU T, DONG D, ZHAO X, et al. Radiomic signatures reveal multiscale intratumor heterogeneity associated with tissue tolerance and survival in re-irradiated nasopharyngeal carcinoma: A multicenter study[J/OL]. BMC Med, 2023, 21(1): 464 [2026-04-02]. https://doi.org/10.1186/s12916-023-03164-3. DOI: 10.1186/s12916-023-03164-3.

PREV Value of intratumoral and peritumoral DCE-MRI combined with mDixon-Quant parameters in predicting lymphovascular invasion of rectal cancer
NEXT A study on associated factors of adolescent knee joint sports injuries based on MRI examinations
  


LINK


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