Computed Tomography Radiomics to Differentiate Intrahepatic Cholangiocarcinoma and Hepatocellular Carcinoma. Issue 5 (May 2023)

• Record Type: Journal Article
• Authors: Mahmoudi, S.; Bernatz, S.; Ackermann, J.; Koch, V.; Dos Santos, D.P.; Grünewald, L.D.; Yel, I.; Martin, S.S.; Scholtz, J.-E.; Stehle, A.; Walter, D.; Zeuzem, S.; Wild, P.J.; Vogl, T.J.; Kinzler, M.N.
• Is Part Of: Clinical oncology. Volume 35:Issue 5(2023)
• Page Start: e312
• Page End: e318
• Publication Date: 2023-05
• Subjects: Artificial intelligence -- Biomarkers -- Hepatocellular carcinoma -- Intrahepatic cholangiocarcinoma -- Machine learning -- Predictive medicine; Oncology -- Periodicals; Tumors -- Periodicals; Cancer -- Treatment -- Periodicals; Radiotherapy -- Periodicals; Neoplasms -- Periodicals; Cancer -- Radiotherapy; Cancer -- Treatment; Oncology; Medical radiology; Radiotherapy; Tumors; Electronic journals; Periodicals; 616.994
• DOI: 10.1016/j.clon.2023.01.018
• Languages: English
• ISSNs: 0936-6555

Abstract

Abstract: Aims: Intrahepatic cholangiocarcinoma (iCCA) and hepatocellular carcinoma (HCC) differ in prognosis and treatment. We aimed to non-invasively differentiate iCCA and HCC by means of radiomics extracted from contrast-enhanced standard-of-care computed tomography (CT). Materials and methods: In total, 94 patients (male, n = 68, mean age 63.3 ± 12.4 years) with histologically confirmed iCCA ( n = 47) or HCC ( n = 47) who underwent contrast-enhanced abdominal CT between August 2014 and November 2021 were retrospectively included. The enhancing tumour border was manually segmented in a clinically feasible way by defining three three-dimensional volumes of interest per tumour. Radiomics features were extracted. Intraclass correlation analysis and Pearson metrics were used to stratify robust and non-redundant features with further feature reduction by LASSO (least absolute shrinkage and selection operator). Independent training and testing datasets were used to build four different machine learning models. Performance metrics and feature importance values were computed to increase the models' interpretability. Results: The patient population was split into 65 patients for training (iCCA, n = 32) and 29 patients for testing (iCCA, n = 15). A final combined feature set of three radiomics features and the clinical features age and sex revealed a top test model performance of receiver operating characteristic (ROC) area under the curve (AUC) = 0.82 (95% confidence interval =0.66–0.98; train ROC AUC = 0.82) using a logistic regression classifier. The model was well calibrated, and the Youden J Index suggested an optimal cut-off of 0.501 to discriminate between iCCA and HCC with a sensitivity of 0.733 and a specificity of 0.857. Conclusions: Radiomics-based imaging biomarkers can potentially help to non-invasively discriminate between iCCA and HCC. Highlights: Radiomics can facilitate discrimination between iCCA and HCC non-invasively. Sensitivity of 0.73 and specificity of 0.86 was achieved to discriminate both entities. 10 Percentile, Energy and GrayLevelNonUniformity yielded best diagnostic performance.