Breaking Ground on the Application of AI to HCC: It’s All about Data

Abstract

H epatocellular carcinoma (HCC), the most common primary liver malignancy, persists as an increasingly concerning global health problem, ranking sixth in global cancer incidence rates and third in cancer-related mortality (1).The various etiologies of underlying liver disease and molecular phenotypes of HCC pose a major challenge in the advancement of HCC management (2).The complexity of HCC necessitates the development of radiologic advances to optimize patient outcomes.Notably, specific multiphase CT and MRI protocols have resulted in the advent of the Liver Imaging Reporting and Data System (LI-RADS) classification system to promptly diagnose lesions with signature features suspicious for HCC in patients with underlying liver disease (3).Recent advances include major developments in systemic immunotherapy and various novel image-guided therapy options.Transarterial chemoembolization (TACE) has been established as a mainstay in the Barcelona Clinic Liver Cancer (BCLC) treatment algorithm for patients diagnosed with intermediate-stage HCC (4).Despite these advances, integration of clinical data, radiologic features, and outcomes to predict prognosis remains suboptimal.Artificial intelligence (AI) introduces a unique opportunity to guide clinical management via the input of baseline clinical characteristics, biomarkers, quantitative radiologic features (ie, radiomics), treatment regimens, and associated patient outcomes into a Breaking Ground on the Application of AI to HCC: It's All about

Ähnliche Arbeiten