Multi-Parametric MRI Combined with Radiomics for the Evaluation of Lymphovascular Space Invasion in Cervical Cancer

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

• cervical cancer
• lymphovascular space invasion
• machine learning
• magnetic resonance imaging
• radiomics