AGGN: Attention-based glioma grading network with multi-scale feature extraction and multi-modal information fusion

In this paper, a magnetic resonance imaging (MRI) oriented novel attention-based glioma grading network (AGGN) is proposed. By applying the dual-domain attention mechanism, both channel and spatial information can be considered to assign weights, which benefits highlighting the key modalities and locations in the feature maps. Multi-branch convolution and pooling operations are applied in a multi-scale feature extraction module to separately obtain shallow and deep features on each modality, and a multi-modal information fusion module is adopted to sufficiently merge low-level detailed and high-level semantic features, which promotes the synergistic interaction among different modality information. The proposed AGGN is comprehensively evaluated through extensive experiments, and the results have demonstrated the effectiveness and superiority of the proposed AGGN in comparison to other advanced models, which also presents high generalization ability and strong robustness. In addition, even without the manually labeled tumor masks, AGGN can present considerable performance as other state-of-the-art algorithms, which alleviates the excessive reliance on supervised information in the end-to-end learning paradigm.

Automated summary

In this paper, a novel attention-based glioma grading network (AGGN) oriented towards magnetic resonance imaging (MRI) is proposed. The AGGN utilizes a dual-domain attention mechanism to consider both channel and spatial information for weight assignment. It also incorporates multi-branch convolution, pooling, and multi-modal information fusion modules to extract and merge features from different modalities. Experimental results demonstrate the effectiveness, superiority, high generalization ability, and strong robustness of the proposed AGGN compared to other models, even without manually labeled tumor masks, alleviating the reliance on supervised information.