Abstract: The irregular morphology of cerebral aneurysms, especially the presence of a daughter sac, is a crucial risk factor of aneurysm rupture. Clinical assessment of daughter sac relies mainly on image reconstruction by TOF-MRA and judgment based on physicians' vision and experience, which limits the efficiency and accuracy of diagnosis. In this paper, we propose an improved Parallel Multiscale Fusion Attention (PMAF) network based on 3D ResNet50 for classification. PMAF uses multi-scale convolution and weighted fusion channel and spatial attention weights to enhance the feature extraction capability. The experiment used 291 cases of TOF-MRA data, including 128 cases in the training set, 32 cases in the validation set, and 131 cases in the test set. Compared with other classification networks, PMAF-Net performs best on the test set, with the accuracy of 83.97%, recall of 84.48%, precision of 80.33%, and F1-score of 0.823 5, and the Receiver Operating Characteristic Curve (ROC) also reflects the model's optimal classification performance (AUC of 0.900 8). The results show that the network can identify daughter sac type aneurysms more accurately, which is expected to support the assessment and quantification of the risk of aneurysm rupture.

Key words: TOF-MRA, daughter sac of cerebral aneurysms, multiscale convolution attention, automatic classification, deep learning