Diagnosis of Liver Cirrhosis and Liver Fibrosis by Artificial Intelligence Algorithm-Based Multislice Spiral Computed Tomography

Artificial Intelligence in Liver Diseases: Recent Advances

Liver diseases cause a significant burden on public health worldwide. In spite of great advances during recent years, there are still many challenges in the diagnosis and treatment of liver diseases. During recent years, artificial intelligence (AI) has been widely used for the diagnosis, risk stratification, and prognostic prediction of various diseases based on clinical datasets and medical images. Accumulative studies have shown its performance for diagnosing patients with nonalcoholic fatty liver disease and liver fibrosis and assessing their severity, and for predicting treatment response and recurrence of hepatocellular carcinoma, outcomes of liver transplantation recipients, and risk of drug-induced liver injury. Herein, we aim to comprehensively summarize the current evidence regarding diagnostic, prognostic, and/or therapeutic role of AI in these common liver diseases.

Retracted: Diagnosis of Liver Cirrhosis and Liver Fibrosis by Artificial Intelligence Algorithm-Based Multislice Spiral Computed Tomography

[This retracts the article DOI: 10.1155/2022/1217003.].

Integrated bioinformatical and in vitro study on drug targets for liver cirrhosis based on unsupervised consensus clustering and immune cell infiltration

Liver cirrhosis is one of the most common cause of death in the world. The progress of liver cirrhosis involves health, liver cirrhosis and liver cancer, leading to great challenges in the diagnosis of the disease. Drug targets, which could be obtained conveniently, can help clinicians improve prognosis and treatment. Liver cirrhosis is associated with serum calcium levels. And studies reported Tanshinone IIA plays a therapeutic role in liver injury through activating calcium-dependent apoptosis. In this study, we explored the diagnostic key targets of Tanshinone IIA in liver cirrhosis through exploration of comprehensive dataset including health, liver cirrhosis and liver cancer patients. The unsupervised consensus clustering algorithm identified 3 novel subtypes in which differentially expressed genes (DEGs) between both subtypes were found by pairwise comparison. Then, 4 key drug targets of Tanshinone IIA were determined through the intersection of these DEGs. The diagnostic performance of target genes was assessed and further verified in the external dataset. We found that the 4 key drug targets could be used as effective diagnostic biomarkers. Then the immune scores in the high and low expression groups of target genes were estimated to identify significantly expressed immune cells. In addition, the immune infiltration of high and low target gene expression groups in several immune cells were significantly different. The findings suggest that 4 key drug targets may be a simple and useful diagnostic tool for predicting patients with cirrhosis. We further studied the carcinogenesis role of AKR1C3 and TPX2 in vitro. Both mRNA and protein expression in hepatoma carcinoma cells was detected using qRT-PCR and Western blot. And the knockdown of AKR1C3 and TPX2 significantly suppressed cell proliferation, migration and invasion.

Efficacy Analysis of Double-Low Dynamic Contrast-Enhanced CT and Hepatic Extracellular Volume Fraction in the Diagnosis of Liver Fibrosis

Objective

The aim of the study was to analyze the efficacy of double-low dynamic contrast-enhanced CT (DCE-CT) and hepatic extracellular volume fraction (fECV) in the diagnosis of liver fibrosis (LF).

Methods

A total of 200 patients with LF and cirrhosis who underwent the histopathological examination of liver biopsy and multiphase DCE-CT of the liver at the same time in our hospital (January 2020–December 2020) were selected as the research subjects, and the degree of liver fibrosis was staged according to pathological criteria to analyze the clinical diagnostic value of double-low DCE-CT and fECV.

Results

Compared with the S2–S4 group, the S1 group had obviously higher Eaorta and HCT values (P < 0.05), a lower fECV value (P < 0.001), and lower serum IVC and LN levels (P < 0.001). Serum IVC and LN levels were positively correlated with fECV (r₁ = 0.803 and r₂ = 0.890; P < 0.001). The fECV had the highest specificity and negative predictive value in the diagnosis of S1 and had the highest sensitivity and positive predictive value in the diagnosis of S2–S4.

Conclusion

The double-low DCE-CT and fECV can provide a reliable basis for the clinical diagnosis of LF, and their results will provide a new direction for the treatment of LF and have a high application value in the clinical practice.