Prompt-mamba filtering networks for accurate hepatocellular carcinoma lesion segmentation in abdominal CT

By
Long Xia
Hai-Yang Chen
Ya-Wen Cao
Chen-Quan Gan
Jun-Zhang Zhao
Wei-Hua Zheng
Haiwen Jia
Shuai Jiang
Xuwang Li
Hua Li
Yi-Nuo Tu
Jun-Jing Zhang
January 27, 2026
0 min

Npj Digital Medicine

Objective:

To improve the segmentation of hepatocellular carcinoma (HCC) lesions in abdominal CT scans by addressing challenges such as morphological heterogeneity and low contrast.

Key Findings:

Prompt-Mamba-AF outperforms existing CNN and Transformer architectures in HCC segmentation.
Achieves leading Dice similarity and boundary accuracy with a compact parameter footprint of 27.6M.
Demonstrates significant improvements in sensitivity for small nodules and generalization across diverse imaging domains.

Interpretation:

The results indicate that Prompt-Mamba-AF is an efficient and effective solution for HCC segmentation, suitable for multi-center clinical workflows.

Limitations:

Further validation may be needed across additional datasets.
Potential dependency on specific imaging protocols and scanner types.

Conclusion:

Prompt-Mamba-AF represents a significant advancement in the segmentation of HCC lesions, enhancing diagnostic capabilities and surgical planning.

Prompt-mamba filtering networks for accurate hepatocellular carcinoma lesion segmentation in abdominal CT

Objective:

Key Findings:

Interpretation:

Limitations:

Conclusion:

Original Source(s)

Prompt-mamba filtering networks for accurate hepatocellular carcinoma lesion segmentation in abdominal CT

Related Content

Prognostic value of body composition on early recurrence and long-term survival of resectable pancreatic ductal adenocarcinoma

Assessment of bone density and microarchitecture in patients with familial partial lipodystrophy

AI Scribes: Efficiency for Whom?