CV-Attention UNet: Attention-based UNet for 3D Cerebrovascular Segmentation of Enhanced TOF-MRA Images

TL;DR

This paper introduces CV-AttentionUNet, an attention-based 3D UNet architecture that improves cerebrovascular segmentation accuracy in TOF-MRA images, especially with small batch sizes and limited data, aiding stroke diagnosis.

Contribution

It proposes a novel attention mechanism combined with deep supervision in a 3D UNet for precise brain vessel segmentation, effective on both labeled and unlabeled data.

Findings

Outperforms existing state-of-the-art methods on TubeTK dataset.

Effective on both labeled and unlabeled data with image processing enhancement.

Improves segmentation accuracy for cerebrovascular structures.

Abstract

Due to the lack of automated methods, to diagnose cerebrovascular disease, time-of-flight magnetic resonance angiography (TOF-MRA) is assessed visually, making it time-consuming. The commonly used encoder-decoder architectures for cerebrovascular segmentation utilize redundant features, eventually leading to the extraction of low-level features multiple times. Additionally, convolutional neural networks (CNNs) suffer from performance degradation when the batch size is small, and deeper networks experience the vanishing gradient problem. Methods: In this paper, we attempt to solve these limitations and propose the 3D cerebrovascular attention UNet method, named CV-AttentionUNet, for precise extraction of brain vessel images. We proposed a sequence of preprocessing techniques followed by deeply supervised UNet to improve the accuracy of segmentation of the brain vessels leading to a stroke. To combine the low and high semantics, we applied the attention mechanism. This mechanism focuses on relevant associations and neglects irrelevant anatomical information. Furthermore, the inclusion of deep supervision incorporates different levels of features that prove to be beneficial for network convergence. Results: We demonstrate the efficiency of the proposed method by cross-validating with an unlabeled dataset, which was further labeled by us. We believe that the novelty of this algorithm lies in its ability to perform well on both labeled and unlabeled data with image processing-based enhancement. The results indicate that our method performed better than the existing state-of-the-art methods on the TubeTK dataset. Conclusion: The proposed method will help in accurate segmentation of cerebrovascular structure leading to stroke