A T2 Weighted Imaging-based Radiomics Nomogram for the Classification of Hepatic Blood-rich Lesions: Hepatocellular Carcinoma and Benign Liver Lesions

Abstract

PurposeFocal lesions of the liver are usually detected by enhanced CT and further diagnosed by enhanced MR in clinical practice. The harmful effects of repeated contrast use in CT and MR, and the subjectivity of conventional imaging increase the risk of misdiagnosis. Our aim is to establish a radiomics nomogram based on T2-weighted imaging for differentiating hepatocellular carcinoma and benign liver lesions with rich blood supply and to estimate the enhancive value to the traditional imaging diagnosis.MethodsThe retrospective study analyzed the imaging and clinical data of 144 patients with hepatocellular carcinoma (n=101) and benign blood-rich lesions of the liver (n=43) pathologically confirmed. These patients were randomly assigned to the training cohort (n=100) and the validation cohort (n=44). We developed three prediction models - a radiomic model, a clinical model, and a fusion model that combined radiomics score (Rad-score) with clinical factors. Comparing the predictive performance of three models, we obtained the best prediction model, which was then compared with the diagnostic efficacy of junior and senior radiologists. The efficacy was evaluated using the area under receiver operating characteristic curve (ROC).ResultsFour radiomics features and three clinical factors (age, sex, lesion location) were chosen for construction of the radiomics model and the clinical model, respectively. Comparing to the radiomics model and the clinical model, the fusion model showed significant discrimination capability in the training set (AUC, 0.972; 95%CI 0.918 - 0.995) and the validation set (AUC, 0.943; 95%CI 0.829 - 0.990). And it was statistically better than the junior radiologist and the senior radiologist in the training cohort (p=0.007 and p=0.005, respectively).ConclusionsThe T2WI-based radiomics nomogram greatly complements the flaw of traditional imaging diagnosis and avoid the reuse of contrast agents. It might facilitate early clinical diagnosis and precision treatment with performed exceedingly favorable predictive efficacy in differentiating HCC and BLLs with rich blood supply.

MRI Radiomics in Imaging of Focal Hepatic Lesions: A Narrative Review

“…According to the findings, MRI-based radiomics may be able to assist in the noninvasive separation of ICC and HCC [ 30 ]. The goal of the study by Yang et al was to create a radiomics nomogram based on T2-weighted imaging that could distinguish between benign liver lesions with rich blood supply and hepatocellular cancer [ 31 ]. One hundred forty-four individuals with benign blood-rich liver lesions and hepatocellular cancer had their imaging and clinical data examined [ 31 ].…”

“…The goal of the study by Yang et al was to create a radiomics nomogram based on T2-weighted imaging that could distinguish between benign liver lesions with rich blood supply and hepatocellular cancer [ 31 ]. One hundred forty-four individuals with benign blood-rich liver lesions and hepatocellular cancer had their imaging and clinical data examined [ 31 ]. Three prediction models were created: a fusion model that integrated clinical and radiomic parameters, a clinical model, and a radiomic model [ 31 ].…”

“…One hundred forty-four individuals with benign blood-rich liver lesions and hepatocellular cancer had their imaging and clinical data examined [ 31 ]. Three prediction models were created: a fusion model that integrated clinical and radiomic parameters, a clinical model, and a radiomic model [ 31 ]. The most accurate prediction model was compared to junior and senior radiologists' diagnostic performance [ 31 ].…”

“…Three prediction models were created: a fusion model that integrated clinical and radiomic parameters, a clinical model, and a radiomic model [ 31 ]. The most accurate prediction model was compared to junior and senior radiologists' diagnostic performance [ 31 ]. In both the training and validation sets, the fusion model significantly outperformed senior and younger radiologists in terms of discrimination capabilities [ 31 ].…”

“…The most accurate prediction model was compared to junior and senior radiologists' diagnostic performance [ 31 ]. In both the training and validation sets, the fusion model significantly outperformed senior and younger radiologists in terms of discrimination capabilities [ 31 ]. By avoiding the need for repeating contrast chemicals and enhancing conventional imaging diagnosis, the T2WI-based radiomics nomogram enables early clinical diagnosis and targeted treatment [ 31 ].…”