DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images

Abstract

Segmentation of intracranial aneurysm images acquired using magnetic resonance angiography (MRA) is essential for medical auxiliary treatments, which can effectively prevent subarachnoid hemorrhages. This paper proposes an image segmentation model based on a dense convolutional attention U-Net, which fuses deep and rich semantic information with shallow-detail information for adaptive and accurate segmentation of MRA-acquired aneurysm images with large size differences. The U-Net model serves as a backbone, combining dense block and convolution block attention module (CBAM). The dense block is composed of a batch normalization layer, an randomly rectified linear unit activation function, and a convolutional layer, for mitigation of vanishing gradients, for multiplexing of aneurysm features, and for improving the network training efficiency. The CBAM is composed of a channel attention module and a spatial attention module, improving the segmentation performance of feature discrimination and enhancing the acquisition of key feature information. Owing to the large variation of aneurysm sizes, multi-scale fusion is performed during up-sampling, for adaptive segmentation of MRA-acquired aneurysm images. The model was tested on the MICCAI 2020 ADAM dataset, and its generalizability was validated on the clinical aneurysm dataset (aneurysm sizes: < 3 mm, 3–7 mm, and > 7 mm) supplied by the Affiliated Hospital of Qingdao University. A good clinical application segmentation performance was demonstrated.

Pocket Convolution Mamba for Brain Tumor Segmentation

“…Unet++ effectively dealt with challenges of multi-scale information and class imbalance by combining the advantages of U-Net and residual networks [22], while DenseUNet utilized dense blocks for more robust feature extraction and integrated multiple feature fusion technologies to improve the precision of feature extraction. Yuan et al, the DCAU-Net [23] model was introduced for segmenting intracranial aneurysm images, integrating dense blocks and the Convolutional Block Attention Module (CBAM) into the U-Net architecture. This adaptation aimed at capturing more detailed features and improving segmentation accuracy by addressing the significant variance in aneurysm sizes.…”

A Comprehensive Study: Intracranial Aneurysm Detection via Vgg16-Densenet Hybrid Deep Learning on Dsa Images

“…Yuan et al [22] Daiju Ueda, MD et al [21] developed a deep-learning framework for detecting brain aneurysms using time-of-flight MRI, achieving improved detection rates. The focus on avoiding misses, though resulting in lower specificity, prompted suggestions for further improvements, including incorporating additional imaging data for comprehensive evaluations.…”

“…For transfer learning, all the layers of both models are frozen so that they cannot be changed during the training process. Global average pooling layers are added to both the DenseNet121 and VGG16 models [22], which diminishes the spatial dimensions of the feature maps. Now, the outputs of the global average pooling of both models are concatenated into a single 11 tensor.…”

Development and application of a more refined process for extracting rock crack width information based on artificial intelligence

“…Compared to the SENet model, which focuses only on the channel attention module, CBAM can achieve better results [53]. Moreover, CBAM is a plug-and-play attention module that can be used not only in bottleneck, but also in any intermediate convolutional layer module [54].…”