Deep learning CT signature for predicting early liver metastases in pancreatic ductal adenocarcinoma.
Authors
Affiliations (10)
Affiliations (10)
- Cultivation and Construction Site of the State Key Laboratory of Intelligent Imaging and Interventional Medicine, Department of Radiology, Zhongda Hospital, Medical School of Southeast University, Nanjing, China.
- School of Biological Science and Medical Engineering, Southeast University, Nanjing, China.
- Department of Radiology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
- Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
- Department of Radiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China.
- Department of Medical Imaging, Clinic Medical School, Yangzhou University, Northern Jiangsu Province Hospital, Yangzhou, China.
- MR Research Collaboration Team, Siemens Healthineers Ltd, Shanghai, China.
- Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
- Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China.
- Cultivation and Construction Site of the State Key Laboratory of Intelligent Imaging and Interventional Medicine, Department of Radiology, Zhongda Hospital, Medical School of Southeast University, Nanjing, China. [email protected].
Abstract
Accurately predicting the risk of early liver metastases (ELM) and identifying patients who are most likely to benefit from neoadjuvant therapy (NAT) are critical for pancreatic ductal adenocarcinoma (PDAC). Here, we develop a Mamba-based predictive model that integrates imaging features from both the primary pancreatic tumor and the liver to assess the risk of ELM. The model is evaluated in a multi-institutional cohort of 1063 PDAC patients and demonstrates robust performance in predicting ELM (AUCs: 0.806-0.890). Besides, model-defined high-risk patients exhibit significantly shorter progression-free survival (PFS: HR = 1.93, p < 0.001) and overall survival (OS: HR = 1.89, p < 0.001). Notably, NAT confers significant OS benefits in model-defined high-risk patients (17.4 vs. 34.1 months; p < 0.001), even after propensity score matching (p = 0.004), while no survival benefit occurs in low-risk patients. Radiotranscriptomic analyses further reveal relative biological aggressiveness in the high-risk group. Overall, our proposed Mamba-based framework enables accurate prediction of ELM and may serve as a clinically actionable tool for identifying PDAC patients most likely to benefit from NAT.