View-Disentangled Transformer for Brain Lesion Detection
This work addresses brain lesion detection for medical imaging, offering an incremental improvement in efficiency and accuracy for a specific domain.
The paper tackles the challenge of detecting small brain lesions in 2D MRI slices by proposing a view-disentangled transformer that efficiently aggregates 3D context to enhance feature extraction, resulting in improved performance on a challenging brain MRI dataset.
Deep neural networks (DNNs) have been widely adopted in brain lesion detection and segmentation. However, locating small lesions in 2D MRI slices is challenging, and requires to balance between the granularity of 3D context aggregation and the computational complexity. In this paper, we propose a novel view-disentangled transformer to enhance the extraction of MRI features for more accurate tumour detection. First, the proposed transformer harvests long-range correlation among different positions in a 3D brain scan. Second, the transformer models a stack of slice features as multiple 2D views and enhance these features view-by-view, which approximately achieves the 3D correlation computing in an efficient way. Third, we deploy the proposed transformer module in a transformer backbone, which can effectively detect the 2D regions surrounding brain lesions. The experimental results show that our proposed view-disentangled transformer performs well for brain lesion detection on a challenging brain MRI dataset.