Related Experiment Video
Updated: Apr 21, 2026
09:21
A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy
Published on: April 17, 2026
16
Advances in Artificial Intelligence-Based Liver-Related Semantic Segmentation Techniques and Applications Using CT
Jun Pu1, Xuan Wang1, Liang Zhu1
1Department of Radiology, Peking Union Medical College Hospital, Beijing, People's Republic of China.
Cancer Medicine
|April 19, 2026
Summary
Artificial intelligence (AI) enhances liver computed tomography (CT) image segmentation for disease assessment and surgical planning. While AI shows promise, challenges in segmenting small tumors and integrating into clinical workflows remain.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Hepatology
Background:
- AI-assisted semantic segmentation of liver CT images is crucial for clinical applications.
- It aids in disease assessment, surgical planning, treatment evaluation, and monitoring.
Purpose of the Study:
- To review current clinical applications of AI-based liver segmentation on CT.
- To summarize recent technical advances in AI models for liver CT analysis.
Main Methods:
- Narrative review synthesizing studies on liver organ, tumor, and vascular segmentation.
- Focus on clinical applications and technical developments in AI models.
Main Results:
- AI models (U-Net, attention/Transformer) automate tasks like remnant estimation, volumetry, and tumor burden evaluation.
- Challenges persist in segmenting small tumors, fine vessels, and clinical deployment.
Conclusions:
- AI-based liver CT segmentation holds potential for precision hepatobiliary imaging and workflow improvement.
- Future progress requires enhanced robustness, efficiency, and clinical integration.
