Auto-LSN: fully automated liver surface nodularity quantification in CT based on deep learning for the evaluation of advanced chronic liver disease

Key Points

• Quantification of liver surface nodularity significantly enhances evaluation accuracy for chronic liver disease.
• Deep learning methods achieved an accuracy of 95% in nodularity detection from CT images.
• Assessment involving automated analysis effectively reduces assessment time compared to manual methods.
• Results imply that automated systems may greatly assist radiologists in diagnosing liver conditions.