CECT-Mamba: a Hierarchical Contrast-enhanced-aware Model for Pancreatic Tumor Subtyping from Multi-phase CECT

2025-09-16

AI Summary

To address insufficient exploitation of temporal information across multiphase contrast-enhanced computed tomography (CECT) and challenges in modeling lesion heterogeneity for pancreatic tumor subtype diagnosis, this paper proposes a hierarchical contrast-enhanced perception model based on the Mamba architecture. It introduces state space models (SSMs) into multiphase CECT analysis for the first time, incorporating a dual-level contrast-enhanced perception module and a similarity-guided temporal optimization mechanism, jointly with a spatially complementary integrator and a multi-granularity fusion module to effectively capture spatiotemporal heterogeneous features across arterial, venous, and other phases. Evaluated on 270 clinical cases, the model achieves 97.4% classification accuracy and 98.6% AUC, significantly improving discrimination between pancreatic ductal adenocarcinoma and pancreatic neuroendocrine tumors. This work establishes a novel paradigm for temporal modeling in medical imaging.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Contrast-enhanced computed tomography (CECT) is the primary imaging technique that provides valuable spatial-temporal information about lesions, enabling the accurate diagnosis and subclassification of pancreatic tumors. However, the high heterogeneity and variability of pancreatic tumors still pose substantial challenges for precise subtyping diagnosis. Previous methods fail to effectively explore the contextual information across multiple CECT phases commonly used in radiologists' diagnostic workflows, thereby limiting their performance. In this paper, we introduce, for the first time, an automatic way to combine the multi-phase CECT data to discriminate between pancreatic tumor subtypes, among which the key is using Mamba with promising learnability and simplicity to encourage both temporal and spatial modeling from multi-phase CECT. Specifically, we propose a dual hierarchical contrast-enhanced-aware Mamba module incorporating two novel spatial and temporal sampling sequences to explore intra and inter-phase contrast variations of lesions. A similarity-guided refinement module is also imposed into the temporal scanning modeling to emphasize the learning on local tumor regions with more obvious temporal variations. Moreover, we design the space complementary integrator and multi-granularity fusion module to encode and aggregate the semantics across different scales, achieving more efficient learning for subtyping pancreatic tumors. The experimental results on an in-house dataset of 270 clinical cases achieve an accuracy of 97.4% and an AUC of 98.6% in distinguishing between pancreatic ductal adenocarcinoma (PDAC) and pancreatic neuroendocrine tumors (PNETs), demonstrating its potential as a more accurate and efficient tool.

Problem

• Automatically subtyping pancreatic tumors using multi-phase CECT imaging
• Addressing tumor heterogeneity and variability for precise diagnosis
• Integrating spatial-temporal modeling across multiple CECT phases effectively

Innovation

• Hierarchical contrast-enhanced-aware Mamba module
• Similarity-guided refinement for temporal variations
• Space complementary integrator and multi-granularity fusion