AI summaryⓘ
The authors developed MARVEL, a new method that improves blood vessel image analysis by including rules based on how real blood vessels grow and branch (Murray's law). Unlike other deep learning tools, MARVEL makes sure the vessel shapes and connections it finds make biological sense, which helps avoid mistakes in identifying vessels. They tested MARVEL on many datasets and found it worked better at accurately mapping vessels and preserving their real structures. This allowed more reliable simulations of blood flow, helping to better tell apart eyes with high blood pressure from normal ones. Overall, the authors show that combining biology-based rules with AI helps create more trustworthy medical imaging results.
Murray's lawvascular segmentationdeep learningbiophysical constraintsbifurcationtopologyhemodynamic simulationarteriovenous pressurehypertensionvascular tree extraction
Authors
Yi Zhou, Thiara Sana Ahmed, Jacqueline Chua, Meng Wang, Qinrong Zhang, Alejandro F. Frangi, Huazhu Fu, Jun Cheng, Leopold Schmetterer, Bingyao Tan
Abstract
Vascular circulation follows fundamental biophysical principles that optimize mass transport and metabolic energy expenditure, which can be effectively modeled by Murray's law. However, contemporary deep learning methods for vascular segmentation often neglect these biophysical constraints. This leads to physiologically implausible branching and misclassification vascular trees, rendering. These automated segmentation results are unreliable unreliable for downstream clinical tasks such as blood flow simulation or disease quantification. In this paper, we introduce MARVEL (Universal MurrAy's law-infoRmed Vessel sEgmentation and topoLogy estimation), a backbone-agnostic framework that integrates biophysical priors into vascular tree extraction. MARVEL combines per-pixel supervision with explicit radius predictions to enforce local bifurcation constraints derived from an empirical width-exponent mapping. We implement these constraints as differentiable regularizers during training to guide models toward physiologically consistent reconstructions. We evaluate MARVEL on eight public datasets across multiple vascular modalities and segmentation backbones. Results demonstrate MARVEL's superior performance in segmentation accuracy, topological consistency, and physiological plausibility. By converting segmented masks into graph-based hemodynamic simulations, we demonstrate that MARVEL preserves the subtle pathological narrowing and topological connectivity required to distinguish hypertensive from normotensive eyes. Results show that MARVEL significantly improves the classification of hypertension via arteriovenous pressure differences in the eye (p < 0.001), outperforming baseline models in both topological consistency and clinical predictive value.