English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Brain tumor represents one of the most fatal cancers around the world, and isvery common in children and the elderly. Accurate identification of the typeand grade of tumor in the early stages plays an important role in choosing aprecise treatment plan. The Magnetic Resonance Imaging (MRI) protocols ofdifferent sequences provide clinicians with important contradictory informationto identify tumor regions. However, manual assessment is time-consuming anderror-prone due to big amount of data and the diversity of brain tumor types.Hence, there is an unmet need for MRI automated brain tumor diagnosis. Weobserve that the predictive capability of uni-modality models is limited andtheir performance varies widely across modalities, and the commonly usedmodality fusion methods would introduce potential noise, which results insignificant performance degradation. To overcome these challenges, we propose anovel cross-modality guidance-aided multi-modal learning with dual attentionfor addressing the task of MRI brain tumor grading. To balance the tradeoffbetween model efficiency and efficacy, we employ ResNet Mix Convolution as thebackbone network for feature extraction. Besides, dual attention is applied tocapture the semantic interdependencies in spatial and slice dimensionsrespectively. To facilitate information interaction among modalities, we designa cross-modality guidance-aided module where the primary modality guides theother secondary modalities during the process of training, which caneffectively leverage the complementary information of different MRI modalitiesand meanwhile alleviate the impact of the possible noise.

Cross-modality Guidance-aided Multi-modal Learning with Dual Attention for MRI Brain Tumor Grading