Problem
Research questions and friction points this paper is trying to address.
blood vessel segmentation
cardiovascular system
CT imaging
vascular heterogeneity
system-level analysis
vesselFM-CT: Segmenting All Blood Vessels in CT Images for System-Level Cardiovascular Analysis
🤖 AI Summary
Current methods struggle to robustly segment the full vascular network in CT images due to its high structural heterogeneity and vast scale variation, limiting comprehensive cardiovascular analysis. This work proposes vesselFM-CT, the first end-to-end 3D model capable of whole-scale vascular segmentation—from the aorta down to minute mesenteric vessels. By integrating a multi-stage iterative training strategy with TubeLoss, a novel loss function specifically designed to capture tubular vascular morphology, vesselFM-CT effectively models vascular structural diversity. The method substantially outperforms existing baselines, enabling precise extraction of the entire cardiovascular system. This advancement facilitates downstream applications such as automated disease classification and high-quality synthetic CT generation, thereby promoting systematic cardiovascular assessment and automated diagnosis.
📝 Abstract
The vascular network in the human body is characterized by blood vessels exhibiting drastic structural variations in radius, length, topological properties, and branching patterns. This heterogeneity, together with location-specific anatomical background variations, poses a significant challenge for robust, large-scale analysis of the entire cardiovascular system. As a result, most research has focused on narrow, isolated segments of the vascular network. While such targeted studies provide valuable insights, they inherently limit the ability to assess the systemic health and functional integrity of the vascular network as a whole. In this work, we aim to bridge this gap to advance both clinical diagnostics and our fundamental understanding of vascular physiology. We propose the task of segmenting all vessels in CT images, ranging from the largest components of the cardiovascular system to even minuscule mesenteric vessels. To this end, we introduce vesselFM-CT, the first model capable of robustly segmenting all blood vessels in 3D CT images. VesselFM-CT is trained via an iterative, multi-step process and optimizes our proposed TubeLoss loss function, effectively addressing the inherent heterogeneity of the cardiovascular system. We demonstrate that vesselFM-CT outperforms all baselines and enables automated, precise extraction of the cardiovascular system from CT images, thereby unlocking a wide range of clinical and technical perspectives, including automated disease classification and synthetic CT image generation.
Innovation
Methods, ideas, or system contributions that make the work stand out.
vessel segmentation
TubeLoss
system-level cardiovascular analysis
3D CT imaging
iterative multi-step training
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
