Preoperative detection of lymphovascular invasion in rectal cancer using intravoxel incoherent motion imaging based on radiomics

Abstract Background Lymphovascular invasion (LVI) status plays an important role in treatment decision‐making in rectal cancer (RC). Intravoxel incoherent motion (IVIM) imaging has been shown to detect LVI; however, making better use of IVIM data remains an important issue that needs to be discussed. Purpose We proposed to explore the best way to use IVIM quantitative parameters and images to construct radiomics models for the noninvasive detection of LVI in RC. Methods A total of 83 patients (LVI negative (LVI‐): LVI positive (LVI+) = 51:32) with postoperative pathology‐confirmed LVI status in RC were divided into a training group ( n = 58) and a validation group ( n = 25). Images were acquired from a 3.0 Tesla machine, including oblique axial T2 weighted imaging (T2WI) and IVIM with 11 b values. The ADC, D, D * and f values were measured on IVIM maps. The ROIs of tumors were delineated on T2WI, DWI, ADC map , and D map images, and three mapping methods were used: ROIs_mapping from DWI, ROIs_mapping from ADC map , and ROIs_mapping from D map . Three‐dimensional radiomics features were extracted from the delineated ROIs. Multivariate logistic regression was used for radiomics feature selection. Radiomics models based on different mapping methods were developed. Receiver operating characteristic (ROC) curves, calibration, and decision curve analyses (DCA) were used to evaluate the performance of the models. Results Model B, which was constructed with radiomics features from ADC map , D map and f map by “ROIs_mapping from DWI” and T2WI (AUC 0.894), performed better than other models based on single sequence (AUC 0.600‐0.806) and even better than Model A, which was based on “ROIs_mapping from ADC” and T2WI (AUC 0.838). Furthermore, an integrated model was constructed with Model B and the IVIM parameter (f value) with an AUC of 0.920 (95% CI: 0.820‐1.000), which was higher than that of Model B, in the validation group. Conclusions The integrated model incorporating the radiomics features and IVIM parameters accurately detected LVI of RC. The “ROIs_mapping from DWI” method provided the best results.