H-CNN-ViT: A Hierarchical Gated Attention Multi-Branch Model for Bladder Cancer Recurrence Prediction
This work addresses the challenge of accurate post-operative monitoring for bladder cancer patients, though it is incremental as it builds on existing AI-assisted diagnostic tools with a new dataset and model.
The paper tackles bladder cancer recurrence prediction from multi-sequence MRI by introducing a new dataset and proposing H-CNN-ViT, a hierarchical gated attention multi-branch model that selectively fuses global and local features, achieving an AUC of 78.6% and surpassing state-of-the-art models.
Bladder cancer is one of the most prevalent malignancies worldwide, with a recurrence rate of up to 78%, necessitating accurate post-operative monitoring for effective patient management. Multi-sequence contrast-enhanced MRI is commonly used for recurrence detection; however, interpreting these scans remains challenging, even for experienced radiologists, due to post-surgical alterations such as scarring, swelling, and tissue remodeling. AI-assisted diagnostic tools have shown promise in improving bladder cancer recurrence prediction, yet progress in this field is hindered by the lack of dedicated multi-sequence MRI datasets for recurrence assessment study. In this work, we first introduce a curated multi-sequence, multi-modal MRI dataset specifically designed for bladder cancer recurrence prediction, establishing a valuable benchmark for future research. We then propose H-CNN-ViT, a new Hierarchical Gated Attention Multi-Branch model that enables selective weighting of features from the global (ViT) and local (CNN) paths based on contextual demands, achieving a balanced and targeted feature fusion. Our multi-branch architecture processes each modality independently, ensuring that the unique properties of each imaging channel are optimally captured and integrated. Evaluated on our dataset, H-CNN-ViT achieves an AUC of 78.6%, surpassing state-of-the-art models. Our model is publicly available at https://github.com/XLIAaron/H-CNN-ViT.