Background: Ultrasonography (US) is widely used for the diagnosis of liver tumors. However, the accuracy of the diagnosis largely depends on the visual perception of humans. Hence, we aimed to construct artificial intelligence (AI) models for the diagnosis of liver tumors in US. Methods: We constructed three AI models based on still B-mode images: model-1 using 24,675 images, model-2 using 57,145 images, and model-3 using 70,950 images. A convolutional neural network was used to train the US images. The four-class liver tumor discrimination by AI, namely, cysts, hemangiomas, hepatocellular carcinoma, and metastatic tumors, was examined. The accuracy of the AI diagnosis was evaluated using tenfold cross-validation. The diagnostic performances of the AI models and human experts were also compared using an independent test cohort of video images. Results: The diagnostic accuracies of model-1, model-2, and model-3 in the four tumor types are 86.8%, 91.0%, and 91.1%, whereas those for malignant tumor are 91.3%, 94.3%, and 94.3%, respectively. In the independent comparison of the AIs and physicians, the percentages of correct diagnoses (accuracies) by the AIs are 80.0%, 81.8%, and 89.1% in model-1, model-2, and model-3, respectively. Meanwhile, the median percentages of correct diagnoses are 67.3% (range 63.6%–69.1%) and 47.3% (45.5%–47.3%) by human experts and non-experts, respectively. Conclusion: The performance of the AI models surpassed that of human experts in the four-class discrimination and benign and malignant discrimination of liver tumors. Thus, the AI models can help prevent human errors in US diagnosis.

Liver fibrosis is one of the risk factors for hepatocellular carcinoma (HCC) development. The staging of liver fibrosis can be evaluated only via a liver biopsy, which is an invasive procedure. Noninvasive methods for the diagnosis of liver fibrosis can be divided into morphological tests such as elastography and serum biochemical tests. Transient elastography is reported to have excellent performance in the diagnosis of liver fibrosis and has been accepted as a useful tool for the prediction of HCC development and other clinical outcomes. Two-dimensional shear wave elastography is a new technique and provides a real-time stiffness image. Serum fibrosis markers have been studied based on the mechanism of fibrogenesis and fibrolysis. In the healthy liver, homeostasis of the extracellular matrix is maintained directly by enzymes called matrix metalloproteinases (MMPs) and their specific inhibitors, tissue inhibitors of metalloproteinases (TIMPs). MMPs and TIMPs could be useful serum biomarkers for liver fibrosis and promising candidates for the treatment of liver fibrosis. Further studies are required to establish liver fibrosis-specific markers based on further clinical and molecular research. In this review, we summarize noninvasive fibrosis tests and molecular mechanism of liver fibrosis in current daily clinical practice.

Hepatitis A virus (HAV) infection is one of the major causes of acute hepatitis, and this infection occasionally causes acute liver failure. HAV infection is associated with HAV-contaminated food and water as well as sexual transmission among men who have sex with men. Although an HAV vaccine has been developed, outbreaks of hepatitis A and life-threatening severe HAV infections are still observed worldwide. Therefore, an improved HAV vaccine and anti-HAV drugs for severe hepatitis A should be developed. Here, we reviewed cell culture systems for HAV infection, and other issues. This review may help with improving the HAV vaccine and developing anti-HAV drugs.

Cytokines are secreted soluble glycoproteins that regulate cellular growth, proliferation, and differentiation. Suppressors of cytokine signaling (SOCS) proteins negatively regulate cytokine signaling and form a classical negative feedback loop in the signaling pathways. There are eight members of the SOCS family. The SOCS proteins are all comprised of a loosely conserved N-terminal domain, a central Src homology 2 (SH2) domain, and a highly conserved SOCS box at the C-terminus. The role of SOCS proteins has been implicated in the regulation of cytokines and growth factors in liver diseases. The SOCS1 and SOCS3 proteins are involved in immune response and inhibit protective interferon signaling in viral hepatitis. A decreased expression of SOCS3 is associated with advanced stage and poor prognosis of patients with hepatocellular carcinoma (HCC). DNA methylations of SOCS1 and SOCS3 are found in HCC. Precise regulation of liver regeneration is influenced by stimulatory and inhibitory factors after partial hepatectomy (PH), in particular, SOCS2 and SOCS3 are induced at an early time point after PH. Evidence supporting the important role of SOCS signaling during liver regeneration also supports a role of SOCS signaling in HCC. Immuno-oncology drugs are now the first-line therapy for advanced HCC. The SOCS can be potential targets for HCC in terms of cell proliferation, cell differentiation, and immune response. In this literature review, we summarize recent findings of the SOCS family proteins related to HCC and liver diseases.

Multiple kinase inhibitors are available for patients with advanced hepatocellular carcinoma (HCC). It is largely unknown whether regorafenib or lenvatinib modulates innate immunity including Toll-like receptor (TLR)-signaling pathways in HCC. We performed real-time RT-PCR to investigate 84 TLR-associated gene expression levels and compared these gene expression levels in each hepatoma cells treated with or without regorafenib or lenvatinib. In response to regorafenib, nine and 10 genes were upregulated in Huh7 and HepG2 cells, respectively, and only C-X-C motif chemokine ligand 10 was upregulated in both cell lines. A total of 14 and 12 genes were downregulated in Huh7 and HepG2 cells, respectively, and two genes (Fos proto-oncogene, AP-1 transcription factor subunit, and ubiquitin conjugating enzyme E2 N) were downregulated in both cell lines. In response to lenvatinib, four and 16 genes were upregulated in Huh7 and HepG2 cells, respectively, and two genes (interleukin 1 alpha and TLR4) were upregulated in both cells. Six and one genes were downregulated in Huh7 and HepG2, respectively, and no genes were downregulated in both cell lines. In summary, regorafenib and lenvatinib affect TLR signaling pathways in human hepatoma cell lines. Modulation of TLR signaling pathway may improve the treatment of HCC patients with refractory disease.