Multi-Parametric MRI Combined with Radiomics for the Evaluation of Lymphovascular Space Invasion in Cervical Cancer
Open Access
- 25 March 2024
- journal article
- research article
- Published by IMR Press in Clinical and Experimental Obstetrics & Gynecology
- Vol. 51 (4) , 81
Abstract
Background: To explore the feasibility of radiomic models using different magnetic resonance imaging (MRI) sequences combined with clinical information in evaluating the status of lymphovascular space invasion (LVSI) in cervical cancer. Methods: One hundred one cervical cancer patients were included from January 2018 to December 2020. All patients underwent 3.0T MRI examination including T2 weighted imaging (T2WI), diffusion weighted imaging (DWI) and contrast-enhanced T1 weighted imaging (T1WI + C) enhanced sequences. Age, preoperative squamous cell carcinoma (SCC) associated antigen value and the depth of muscular invasion were collected. The 101 patients were divided into training set and validation set. Three different models were developed using T2WI, DWI and T1WI + C parameters respectively. One model was developed combining the three different sequences. The diagnostic performance of each model was compared via receiver operating characteristic curve analysis. Results: Forty-eight cases were pathologically confirmed with lymphovascular space invasion. The average SCC value of the LVSI positive group (10.82 ± 20.11 ng/mL) was higher than that of the negative group (6.71 ± 14.45 ng/mL), however there was no significant statistical difference between the two groups. No clinical or traditional imaging features were selected by spearman correlation analysis. Among the corresponding radiomic models, the machine learning model based on multi-modality showed the best diagnostic efficiency in the evaluation of LVSI (receiver operating characteristic (ROC) curve of multimodal radiomics in the training set (area under the ROC curve (AUC) = 0.990 (0.975–0.999)) and in the validation set (AUC = 0.832 (0.693–0.971)). Conclusions: The diagnostic efficacy of radiomics is superior to conventional MRI parameters and clinical parameters. The radiomics-based machine learning model can help improve accuracy for the preoperative evaluation of LVSI in cervical cancer.Keywords
Funding Information
- Key project foundation of Nanjing for the development of medical technology (ZKX 20024)
This publication has 23 references indexed in Scilit:
- Interpretation of radiomics features–A pictorial reviewComputer Methods and Programs in Biomedicine, 2022
- Rs2686344 and serum squamous cell carcinoma antigen could predict clinical efficacy of neoadjuvant chemotherapy for cervical cancerCurrent Problems in Cancer, 2021
- Multiparametric magnetic resonance imaging-derived radiomics for the prediction of disease-free survival in early-stage squamous cervical cancerEuropean Radiology, 2021
- Tumor grading of soft tissue sarcomas using MRI-based radiomicsEBioMedicine, 2019
- Radiomics Analysis of Multiparametric MRI Evaluates the Pathological Features of Cervical Squamous Cell CarcinomaJournal of Magnetic Resonance Imaging, 2018
- Combined detection of Twist1, Snail1 and squamous cell carcinoma antigen for the prognostic evaluation of invasion and metastasis in cervical squamous cell carcinomaInternational Journal of Clinical Oncology, 2018
- Minimum apparent diffusion coefficient for predicting lymphovascular invasion in invasive cervical cancerJournal of Magnetic Resonance Imaging, 2016
- Body diffusion kurtosis imaging: Basic principles, applications, and considerations for clinical practiceJournal of Magnetic Resonance Imaging, 2015
- Management of recurrent cervical cancer: A review of the literatureSurgical Oncology, 2012
- Radiomics: Extracting more information from medical images using advanced feature analysisEuropean Journal of Cancer, 2012