Radiomics Analysis on Noncontrast CT for Distinguishing Hepatic Hemangioma (HH) and Hepatocellular Carcinoma (HCC)

Abstract

Background. To form a radiomic model on the basis of noncontrast computed tomography (CT) to distinguish hepatic hemangioma (HH) and hepatocellular carcinoma (HCC). Methods. In this retrospective study, a total of 110 patients were reviewed, including 72 HCC and 38 HH. We accomplished feature selection with the least absolute shrinkage and operator (LASSO) and built a radiomics signature. Another improved model (radiomics index) was established using forward conditional multivariate logistic regression. Both models were tested in an internal validation group (38 HCC and 21 HH). Results. The radiomic signature we built including 5 radiomic features demonstrated significant differences between the hepatic HH and HCC groups P < 0.05 . The improved model demonstrated a higher net benefit based on only 2 radiomic features. In the validation group, radiomics signature and radiomics index achieved great diagnostic performance with AUC values of 0.716 (95% confidence interval (CI): 0.581, 0.850) and 0.870 (95% CI: 0.782, 0.957), respectively. Conclusions. Our developed radiomics-based model can successfully distinguish HH and HCC patients, which can help clinical decision-making with lower cost.

Focal Lesions of the Liver and Radiomics: What Do We Know?

“…The radiomics nomogram was better able to distinguish HCC from HCA in a non-cirrhotic liver than the radiomic signature alone [44]. Hu et al built a radiomic index on an unenhanced CT using two features (wavelet-LLL first-order median and wavelet-LHL-GLSZM-zone entropy) that showed great performance in differentiating HH from HCC; lower GLSZM zone entropy and higher median values of the voxel intensity values indicate more uniform pixels in the region of interest, and these results might be highly consistent with the pathological differences between HH and HCC, in which HH consists of a vascular malformation and HCC contains mainly cytological atypia [45]. Song et al investigated the ability of CTTA to distinguish different hypervascular hepatic focal lesions by dividing the benign lesions (HH, HA, FNH) from the malignant ones (HCC, LM).…”

“…cytological atypia [45]. Song et al investigated the ability of CTTA to distinguish different hypervascular hepatic focal lesions by dividing the benign lesions (HH, HA, FNH) from the malignant ones (HCC, LM).…”

Hepatocellular carcinoma‑cavernous hemangioma collision tumor: A case report

“…When an imaging examination shows that there may be two tumor components, the possibility of a collision tumor and the performance of further examinations should be considered, even if the probability of a collision tumor is low. For example, contrast-enhanced CT can distinguish hemangioma from HCC ( 21 ). In the patient, the CT revealed another mass other than hepatocellular carcinoma, but the mass did not exhibit typical characteristics of liver hemangioma enhancement (marked enhancement).…”

Editorial: The use of data mining in radiological-pathological images for personal medicine

“…High-order features depend on image analysis techniques which attracted great attention in the last few years. Most research focused on tumor characteristics and prognosis ( Xu et al, 2019 ; Ji et al, 2020 ; Hu et al, 2022 ; Xu et al, 2022 ), and chronic disease can also be fully detected ( Wang et al, 2020 ; Zhang et al, 2022a ; Zhang et al, 2022b ; Wang et al, 2022 ). Different from image findings, it is hard to explain biological role of each high-order feature which is worthy of more exploration.…”