Artificial intelligence in imaging for liver disease diagnosis

Area of Science:

• Medical Imaging and Diagnostics
• Artificial Intelligence in Medicine
• Hepatology

Background:

• Liver diseases (hepatitis, NAFLD, cirrhosis, HCC) are significant global health issues requiring early, accurate diagnosis.
• Non-invasive imaging (US, CT, MRI) is vital but has limitations in sensitivity and accuracy.
• Traditional diagnosis often relies on invasive liver biopsy, which carries risks and limitations.

Purpose of the Study:

• To review the applications and clinical utility of artificial intelligence (AI) in liver imaging for disease diagnosis.
• To explore how AI enhances pattern recognition, quantification, and detection across various liver imaging modalities.
• To discuss the implications of AI integration for improving diagnostic accuracy, efficiency, and clinical decision-making in hepatology.

Main Methods:

• Review of recent advancements in AI applications for liver imaging.
• Analysis of AI's role in improving fibrosis staging using ultrasound, CT, MRI, and elastography.
• Evaluation of AI-assisted methods for liver steatosis quantification and grading.
• Assessment of AI models in hepatocellular carcinoma (HCC) detection, characterization, and risk stratification.

Main Results:

• AI improves fibrosis staging accuracy, potentially reducing the need for liver biopsy.
• AI-assisted imaging enhances sensitivity and consistency in grading liver steatosis (NAFLD).
• AI models demonstrate improved lesion identification, classification, and risk stratification for HCC across imaging techniques.

Conclusions:

• AI integration in liver imaging is transforming diagnostic workflows.
• AI-driven techniques show significant promise in enhancing the accuracy and efficiency of diagnosing various liver diseases.
• AI holds substantial potential to improve clinical decision-making and patient outcomes in liver disease management.