Multi-Parametric Magnetic Resonance Imaging-Based Radiomics Analysis of Cervical Cancer for Preoperative Prediction of Lymphovascular Space Invasion

Abstract

BackgroundDetection of lymphovascular space invasion (LVSI) in early cervical cancer (CC) is challenging. To date, no standard clinical markers or screening tests have been used to detect LVSI preoperatively. Therefore, non-invasive risk stratification tools are highly desirable.ObjectiveTo train and validate a multi-parametric magnetic resonance imaging (mpMRI)-based radiomics model to detect LVSI in patients with CC and investigate its potential as a complementary tool to enhance the efficiency of risk assessment strategies.Materials and MethodsThe model was developed from the tumor volume of interest (VOI) of 125 patients with CC. A total of 1037 radiomics features obtained from conventional magnetic resonance imaging (MRI), including a small field-of-view (sFOV) high-resolution (HR)-T2-weighted MRI (T2WI), apparent diffusion coefficient (ADC), T2WI, fat-suppressed (FS)-T2WI, as well as axial and sagittal contrast-enhanced T1-weighted MRI (T1c). We conducted a radiomics-based characterization of each tumor region using pretreatment image data. Feature selection was performed using the least absolute shrinkage and selection operator method on the training set. The predictive performance was compared with single variates (clinical data and single-layer radiomics signatures) analyzed using a receiver operating characteristic (ROC) curve. Three-fold cross-validation performed 20 times was used to evaluate the accuracy of the trained classifiers and the stability of the selected features. The models were validated by using a validation set.ResultsFeature selection extracted the six most important features (3 from sFOV HR-T2WI, 1 T2WI, 1 FS-T2WI, and 1 T1c) for model construction. The mpMRI-combined radiomics model (area under the curve [AUC]: 0.940) reached a significantly higher performance (better than the clinical parameters [AUC: 0.730]), including any single-layer model using sFOV HR-T2WI (AUC: 0.840), T2WI (AUC: 0.770), FS-T2WI (AUC: 0.710), ADC maps (AUC: 0.650), sagittal, and axial T1c values (AUC: 0.710, 0.680) in the validation set.ConclusionBiomarkers using multi-parametric radiomics features derived from preoperative MR images could predict LVSI in patients with CC.

PreliminaryMRIStudy of Extracellular Volume Fraction for Identification of Lymphovascular Space Invasion of Cervical Cancer

“…[34][35][36] In terms of the application value of DCE-MRI in assessing LVSI in cervical cancer, only few radiomics studies have been published, and the AUC value of the model ranged from 0.754 to 0.814. 18,19 In our study, a higher K trans value was significantly associated with the LVSI group, and k ep and V e showed no statistical difference between the LVSI group and non-LVSI group. For the standard Toft's model, tumor K trans was more sensitive to reflect tissue perfusion than other parameters.…”

“…Instead, the ECV fraction represents a quantitative assessment of the entire extracellular stromal space of the tumor, including blood and lymphatic vessels. Compared with previous MRI-based radiomics studies, [15][16][17][18][19][20] our results showed that ECV fraction, as a potential imaging parameter for predicting LVSI in cervical cancer, exhibited diagnostic value comparable to that of radiomics models. However, MRI-based radiomics models involve feature extraction and modeling of different MR sequences and combinations between sequences, so the whole process of radiomics is relatively complex and difficult to apply to clinical routine.…”

“…MR-based radiomics studies have also made some attempts at preoperative prediction of LVSI in cervical cancer, with model AUC values ranging from 0.754 to 0.940. [15][16][17][18][19][20] However, due to the complexity of the entire radiomics process and the low universality of the model in different institutions, it is difficult to use radiomics to predict the LVSI of cervical cancer in routine clinical applications.…”

Prediction of Postoperative Pathologic Risk Factors in Cervical Cancer Patients Treated with Radical Hysterectomy by Machine Learning

“…Another study [ 50 ] in 2020 found that pretreatment albumin to fibrinogen ratio was significantly related to lymph node metastasis, depth of stromal infiltration, etc. Many studies focused on prediction for survival outcomes or a single PRF of cervical cancer based on clinical factors [ 51 , 52 , 53 ] and/or radiomic parameters [ 54 , 55 ]. However, no studies have made an attempt to predict three PRFs based on a series of clinically readily available blood markers.…”

Amide proton transfer weighted imaging combined with dynamic contrast-enhanced MRI in predicting lymphovascular space invasion and deep stromal invasion of IB1-IIA1 cervical cancer

“…However, as an invasive approach, it may also lead to excessive bleeding and inflammatory reaction in the local cervical tissue after surgery. Therefore, a non-invasive assessment of the coexistence of DSI and LVSI before initial treatment would also be of great value for cervical cancer patients in defining patient therapeutic strategies and evaluating prognosis or tailor follow-up intervals ( 16 ).…”