Contrast‐enhanced CT radiomics for preoperative evaluation of microvascular invasion in hepatocellular carcinoma: A two‐center study

Abstract

Background The present study constructed and validated the use of contrast‐enhanced computed tomography (CT)‐based radiomics to preoperatively predict microvascular invasion (MVI) status (positive vs negative) and risk (low vs high) in patients with hepatocellular carcinoma (HCC). Methods We enrolled 637 patients from two independent institutions. Patients from Institution I were randomly divided into a training cohort of 451 patients and a test cohort of 111 patients. Patients from Institution II served as an independent validation set. The LASSO algorithm was used for the selection of 798 radiomics features. Two classifiers for predicting MVI status and MVI risk were developed using multivariable logistic regression. We also performed a survival analysis to investigate the potentially prognostic value of the proposed MVI classifiers. Results The developed radiomics signature predicted MVI status with an area under the receiver operating characteristic curve (AUC) of .780, .776, and .743 in the training, test, and independent validation cohorts, respectively. The final MVI status classifier that integrated two clinical factors (age and α‐fetoprotein level) achieved AUC of .806, .803, and .796 in the training, test, and independent validation cohorts, respectively. For MVI risk stratification, the AUCs of the radiomics signature were .746, .664, and .700 in the training, test, and independent validation cohorts, respectively, and the AUCs of the final MVI risk classifier‐integrated clinical stage were .783, .778, and .740, respectively. Survival analysis showed that our MVI status classifier significantly stratified patients for short overall survival or early tumor recurrence. Conclusions Our CT radiomics‐based models were able to predict MVI status and MVI risk of HCC and might serve as a reliable preoperative evaluation tool.

Prediction of Microvascular Invasion in Hepatocellular Carcinoma With a Multi-Disciplinary Team-Like Radiomics Fusion Model on Dynamic Contrast-Enhanced Computed Tomography

“…Radiomics have exhibited great potential in predictive/discriminative models by integrating diseaserelated imaging features with clinical, pathological, and genetic data (22)(23)(24). Progress has been made in applying CT or MRI based radiomics for investigating MVI in HCC (25)(26)(27)(28). However, most studies only included a single phase of dynamic contrastenhanced (DCE)-CT or MRI.…”

“…Therefore, key image information beyond the tumor core might be lost since MVI often occurs in regions neighboring the tumor/non-tumor interface ( 6 , 29 ). Image texture from the peripheral liver parenchyma, such as a settled 5mm or 10mm distance from the tumor edge, have shown encouraging predictive ability in MVI ( 26 , 28 , 30 ). To our knowledge, no study has comprehensively reported on MVI predictive performances using different combinations of DCE-CT/MRI phase(s) with varying distances from the tumor margin.…”

Using Deep Learning to Predict Microvascular Invasion in Hepatocellular Carcinoma Based on Dynamic Contrast-enhanced MRI Combined with Clinical Parameters

“…2019), while those with solitary tumor displayed MVI are not easy to be identi ed. For patients with multiple tumors, previous studies only assessed the largest tumor to predict MVI status (Xu et al 2019;Zhang et al 2020b) but it is not accurate to identify which lesion exists MVI. The other point is that multicarcinogenesis may not be controlled by extended liver resection due to the limited liver volume.…”

Spatiotemporal molecular imaging is a critical part of spatiotemporal molecular medicine

“…Spatial temporalization of clinical images has been developed and evidenced as a critical approach in clinical and translational practices, e.g., radiomics which was used to detect the alternations in the microenvironmental circulation and vascularization in solid tumors and to predict the prognosis of patients. 6,7 In addition, clinical images represent multi-dimensional events of organs and/or tumors and can be dynamically monitored. Rizk evidenced that the dynamic three-dimensional volume, velocity, and vascularization of the MRI-based heart could demonstrate the quantity and quality of hemodynamics in physiological and pathophysiological conditions through adequate spatiotemporal resolution.…”