Artificial intelligence in imaging for liver disease diagnosis DOI Creative Commons
Chenglong Yin, Huafeng Zhang, Jin Du

et al.

Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 12

Published: April 25, 2025

Liver diseases, including hepatitis, non-alcoholic fatty liver disease (NAFLD), cirrhosis, and hepatocellular carcinoma (HCC), remain a major global health concern, with early accurate diagnosis being essential for effective management. Imaging modalities such as ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI) play crucial role in non-invasive diagnosis, but their sensitivity diagnostic accuracy can be limited. Recent advancements artificial intelligence (AI) have improved imaging-based assessment by enhancing pattern recognition, automating fibrosis steatosis quantification, aiding HCC detection. AI-driven techniques shown promise staging through US, CT, MRI, elastography, reducing the reliance on invasive biopsy. For steatosis, AI-assisted methods grading consistency, while detection characterization, AI models enhanced lesion identification, classification, risk stratification across modalities. The growing integration of into is reshaping workflows has potential to improve accuracy, efficiency, clinical decision-making. This review provides an overview applications imaging, focusing utility implications future diagnosis.

Language: Английский

From Gut to Glory: Unveiling the Microbiome’s Impact on Human Health DOI
Yogesh Raval, M. Guftar Shaikh, Kiran Dudhat

et al.

Regenerative Engineering and Translational Medicine, Journal Year: 2025, Volume and Issue: unknown

Published: April 11, 2025

Language: Английский

Citations

0
Artificial intelligence in imaging for liver disease diagnosis DOI Creative Commons
Chenglong Yin, Huafeng Zhang, Jin Du

et al.

Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 12

Published: April 25, 2025

Liver diseases, including hepatitis, non-alcoholic fatty liver disease (NAFLD), cirrhosis, and hepatocellular carcinoma (HCC), remain a major global health concern, with early accurate diagnosis being essential for effective management. Imaging modalities such as ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI) play crucial role in non-invasive diagnosis, but their sensitivity diagnostic accuracy can be limited. Recent advancements artificial intelligence (AI) have improved imaging-based assessment by enhancing pattern recognition, automating fibrosis steatosis quantification, aiding HCC detection. AI-driven techniques shown promise staging through US, CT, MRI, elastography, reducing the reliance on invasive biopsy. For steatosis, AI-assisted methods grading consistency, while detection characterization, AI models enhanced lesion identification, classification, risk stratification across modalities. The growing integration of into is reshaping workflows has potential to improve accuracy, efficiency, clinical decision-making. This review provides an overview applications imaging, focusing utility implications future diagnosis.

Language: Английский

Citations

0