Current impact of viral hepatitis on liver cancer development: The challenge remains.

Chronic infections due to hepatitis B and hepatitis C viruses are responsible for most cases of hepatocellular carcinoma (HCC) worldwide, and this association is likely to remain during the next decade. Moreover, viral hepatitis-related HCC imposes an important burden on public health in terms of disability-adjusted life years. In order to reduce such a burden, some major challenges must be faced. Universal vaccination against hepatitis B virus, especially in the neonatal period, is probably the most relevant primary preventive measure against the development of HCC. Moreover, considering the large adult population already infected with hepatitis B and C viruses, it is also imperative to identify these individuals to ensure their access to treatment. Both hepatitis B and C currently have highly effective therapies, which are able to diminish the risk of development of liver cancer. Finally, it is essential for individuals at high-risk of HCC to be included in surveillance programs, so that tumors are detected at an early stage. Patients with hepatitis B or C and advanced liver fibrosis or cirrhosis benefit from being followed in a surveillance program. As hepatitis B virus is oncogenic and capable of leading to liver cancer even in individuals with early stages of liver fibrosis, other high-risk groups of patients with hepatitis B are also candidates for surveillance. Considerable effort is required concerning these strategies in order to decrease the incidence and the mortality of viral hepatitis-related HCC.

Deep learning in hepatocellular carcinoma: Current status and future perspectives.

Hepatocellular carcinoma (HCC) is among the leading causes of cancer incidence and death. Despite decades of research and development of new treatment options, the overall outcomes of patients with HCC continue to remain poor. There are areas of unmet need in risk prediction, early diagnosis, accurate prognostication, and individualized treatments for patients with HCC. Recent years have seen an explosive growth in the application of artificial intelligence (AI) technology in medical research, with the field of HCC being no exception. Among the various AI-based machine learning algorithms, deep learning algorithms are considered state-of-the-art techniques for handling and processing complex multimodal data ranging from routine clinical variables to high-resolution medical images. This article will provide a comprehensive review of the recently published studies that have applied deep learning for risk prediction, diagnosis, prognostication, and treatment planning for patients with HCC.

Circulating Tumor DNA Profiling of Advanced Biliary Tract Cancers.

PURPOSE: Recent advances in molecular diagnostic technologies have allowed for the evaluation of solid tumor malignancies via noninvasive blood sampling, including circulating tumor DNA (ctDNA) profiling. We sought to characterize the ctDNA genomic alteration landscape in patients with biliary tract cancers (BTCs). PATIENTS AND METHODS: From January 2015 to February 2018, 124 patients with BTC at the Mayo Clinic Comprehensive Cancer Center underwent ctDNA testing using a clinically available assay. The majority of samples (n = 122) were tested using the 73-gene panel that includes somatic genomic targets, including complete or critical exon coverage in 30 and 40 genes, respectively, and in some, amplifications, fusions, and indels. RESULTS: A total of 138 samples were included, with approximately 70% of patients having intrahepatic BTC. All patients had locally advanced or metastatic BTC. Samples with one or more alterations, when variants of unknown significance were excluded, numbered 105 (76%). Each sample contained, on average, three alterations with a median allelic fraction of 0.52%. The overall landscape of alterations is summarized in Figures 1 and 2. After excluding variants of unknown significance, therapeutically relevant alterations were observed in 76 patients (55%), including BRAF mutations, ERBB2 amplifications, FGFR2 fusions, FGFR2 mutations, and IDH1 mutations seen in 21% of patients. A different spectrum of alterations was observed in patients with early-onset BTC (younger than age 50 years) compared with older patients (older than age 50 years). CONCLUSION: Data on ctDNA in BTC is currently limited. Our study, the largest cohort reported to date to our knowledge, demonstrates the feasibility of ctDNA testing in this disease. We provide a foundation upon which the field can continue to grow.