Prompt-mamba filtering networks for accurate hepatocellular carcinoma lesion segmentation in abdominal CT.
Authors
Affiliations (10)
Affiliations (10)
- Department of Hepatobiliary Surgery, Hohhot First Hospital, Hohhot, Inner Mongolia, China.
- Department of Hepatobiliary Surgery, Inner Mongolia Autonomous Region People's Hospital, Hohhot, Inner Mongolia, China.
- Department of Radiation Oncology, The Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, China.
- Department of General Surgery, The Third Affiliated Hospital of Southern Medical University, Guangzhou, Guangdong, China.
- School of Cyber Security and Information Law, Chongqing University of Posts and Telecommunication, Chongqing, China.
- Department of Oncology Science, University of Oklahoma Health Sciences Center, Oklahoma City, OK, USA.
- Department of Hepatic Surgery and Liver Transplantation Center, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, Guangdong, China. [email protected].
- Department of Hepatobiliary Surgery, Guangzhou Institute of Cancer Research, the Affiliated Cancer Hospital, Guangzhou Medical University, Guangzhou, Guangdong, China. [email protected].
- Department of Hepatobiliary Surgery, Hohhot First Hospital, Hohhot, Inner Mongolia, China. [email protected].
- Inner Mongolia Key Laboratory of Allergic Diseases, Foundational and Translational Medical Research Center, Hohhot First Hospital, Hohhot, Inner Mongolia, China. [email protected].
Abstract
Precise delineation of hepatocellular carcinoma (HCC) in abdominal CT is pivotal for early diagnosis and surgical planning, yet remains challenged by morphological heterogeneity, low contrast in small lesions, and scanner variability. To address these limitations, we propose Prompt-Mamba-AF, a framework tailored for robust HCC segmentation. Our method uniquely integrates anatomy-aware prompts to guide feature extraction within liver regions and leverages Mamba-based state-space modeling to capture long-range volumetric dependencies with linear complexity. Furthermore, we introduce structure-aware filtering to enforce topological consistency along lesion boundaries. Extensive validation on the LiTS, 3DIRCADb, and CHAOS benchmarks demonstrates that Prompt-Mamba-AF outperforms current state-of-the-art CNN and Transformer architectures. The model achieves leading Dice similarity and boundary accuracy while maintaining a compact parameter footprint (27.6M). Results indicate significant improvements in small nodule sensitivity and generalization across diverse imaging domains, positioning Prompt-Mamba-AF as an efficient solution for multi-center clinical workflows.