Hierarchical LoG Bayesian Neural Network for Enhanced Aorta Segmentation

2025-01-18

AI Summary

Addressing the challenges of multi-scale fine segmentation of the aorta and its branches, as well as quantification of predictive uncertainty, this paper proposes a Bayesian neural network architecture integrating a 3D U-Net with hierarchical learnable Laplacian of Gaussian (LoG) kernels. We innovatively design a hierarchical LoG kernel learning mechanism to enable scale-adaptive modeling of the aortic trunk and supra-aortic branches. Coupled with a Bayesian parameterization framework, the model jointly produces pixel-wise segmentation maps and anatomy-specific confidence intervals. Evaluated on two public aortic datasets, our method achieves ≥3% improvement in Dice score over state-of-the-art approaches. To the best of our knowledge, this is the first work to embed learnable multi-scale LoG priors into a Bayesian deep segmentation framework—thereby simultaneously enhancing structural accuracy and prediction reliability. The resulting interpretable and trustworthy outputs advance clinical decision support for vascular disease diagnosis.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Bayesian Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

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: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate segmentation of the aorta and its associated arch branches is crucial for diagnosing aortic diseases. While deep learning techniques have significantly improved aorta segmentation, they remain challenging due to the intricate multiscale structure and the complexity of the surrounding tissues. This paper presents a novel approach for enhancing aorta segmentation using a Bayesian neural network-based hierarchical Laplacian of Gaussian (LoG) model. Our model consists of a 3D U-Net stream and a hierarchical LoG stream: the former provides an initial aorta segmentation, and the latter enhances blood vessel detection across varying scales by learning suitable LoG kernels, enabling self-adaptive handling of different parts of the aorta vessels with significant scale differences. We employ a Bayesian method to parameterize the LoG stream and provide confidence intervals for the segmentation results, ensuring robustness and reliability of the prediction for vascular medical image analysts. Experimental results show that our model can accurately segment main and supra-aortic vessels, yielding at least a 3% gain in the Dice coefficient over state-of-the-art methods across multiple volumes drawn from two aorta datasets, and can provide reliable confidence intervals for different parts of the aorta. The code is available at https://github.com/adlsn/LoGBNet.

Problem

• Cardiovascular Image Segmentation
• Diagnostic Accuracy
• Vascular Disease

Innovation

• LoG-based Neural Network
• Bayesian Optimization
• Enhanced Vascular Recognition