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.
@article{arxiv.2209.09657,
title = {View-Disentangled Transformer for Brain Lesion Detection},
author = {Haofeng Li and Junjia Huang and Guanbin Li and Zhou Liu and Yihong Zhong and Yingying Chen and Yunfei Wang and Xiang Wan},
journal= {arXiv preprint arXiv:2209.09657},
year = {2022}
}
Comments
International Symposium on Biomedical Imaging (ISBI) 2022, code: https://github.com/lhaof/ISBI-VDFormer