MBH-Net: Multi-branch Hybrid Network with Auxiliary Attention Guidance for Large Vessel Occlusion Detection

Yao, Rui; Tan, Duo; Yang, Yehui; Li, Yongmei; Liu, Jiayang; Wu, Jiajing; Chen, Shanxiong; Wang, Jingjie

doi:10.1109/bibm55620.2022.9995268

Cited by 2 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this method faces issues with inaccurate vessel position localization. To overcome these challenges, Yao et al (Yao et al 2022) introduced a convolutional neural model called MBH-Net with an auxiliary attention-guided module. This module guides the attention distribution of MBH-Net, enabling the model to produce more reasonable visual interpretations.…”

Section: Deep Learning-based Approachesmentioning

confidence: 99%

“…To further evaluate the classification performance of our model for intracranial occluded large vessels, we compared our proposed LVONet with other algorithms in table 3, including ResNet18, Res2Net (Gao et al 2019), HRNet (Wang et al 2020b), DeepSymNet (Barman et al 2019), FCA (Qin et al 2021) and MBH-Net (Yao et al 2022). Both our algorithm and the comparative algorithms underwent fine-tuning to optimize model performance.…”

Section: Comparison Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

LVONet: automatic classification model for large vessel occlusion based on the difference information between left and right hemispheres

Ma,

Chen,

Xiong

et al. 2024

Phys. Med. Biol.

Self Cite

View full text Add to dashboard Cite

Stroke is a highly lethal condition, with intracranial vessel occlusion being one of its primary causes. Intracranial vessel occlusion can typically be categorized into four types, each requiring different intervention measures. Therefore, the automatic and accurate classification of intracranial vessel occlusions holds significant clinical importance for assessing vessel occlusion conditions. However, due to the visual similarities in shape and size among different vessels and variations in the degree of vessel occlusion, the automated classification of intracranial vessel occlusions remains a challenging task. Our study proposes an automatic classification model for large vessel occlusion based on the difference information between the left and right hemispheres. Our approach is as follows: We first introduce a dual-branch attention module to learn long-range dependencies through spatial and channel attention, guiding the model to focus on vessel-specific features. Subsequently, based on the symmetry of vessel distribution, we design a differential information classification module to dynamically learn and fuse the differential information of vessel features between the two hemispheres, enhancing the sensitivity of the classification model to occluded vessels. To optimize the feature differential information among similar vessels, we further propose a novel cooperative learning loss function to minimize changes within classes and similarities between classes. We evaluate our proposed model on an intracranial large vessel occlusion dataset. Compared to state-of-the-art deep learning models, our model performs optimally, achieving a classification accuracy of 83.33%, sensitivity of 93.73%, accuracy of 89.91%, and a Macro-F1 score of 87.13%. This method can adaptively focus on occluded vessel regions and effectively train in scenarios with high inter-class similarity and intra-class variability, thereby improving the performance of large vessel occlusion classification.

show abstract

Section: Deep Learning-based Approachesmentioning

confidence: 99%