MT-NeT: Multi-Modality Transfer Learning Network for Automated Carotid Vessel Wall Segmentation using Sparse Annotation in MRI

Xibao Li, Xi Ouyang, Jiadong Zhang, Dongdong Gu, Zehong Cao, Zhongxiang Ding, Yiqiang Zhan, Xiang Sean Zhou, Zhong Xue, Yuyao Zhang, Feng Shi, Dinggang Shen

Abstract

Vessel Wall Magnetic Resonance Imaging (VW-MRI) is an emerging technique for visualizing lumen and vessel wall structures and facilitating the diagnosis of vascular diseases such as atherosclerosis. However, annotations on VW-MRI are usually sparse due to their labor-intensive nature. On the other hand, computed tomography angiography (CTA) images are widely used in atherosclerosis analysis, where data and annotation are relatively sufficient. To this end, we propose a multi-modality transfer learning network (MT-Net) to transfer anatomical knowledge of vessels from CTA to MR, based on fully-annotated training CTA images and sparsely-annotated training MR images. Furthermore, in the MR branch, we utilize the vessel lumen results to guide the multi-channel network for final vessel wall segmentation. Experimental results on the COSMOS Challenge dataset demonstrate advantage of our method in producing robust lumen and vessel wall segmentations with sparse annotation.
BibTeX
@inproceedings{li2023mt,
  author = {Xibao Li and Xi Ouyang and Jiadong Zhang and Dongdong Gu and Zehong Cao and Zhongxiang Ding and Yiqiang Zhan and Xiang Sean Zhou and Zhong Xue and Yuyao Zhang and Feng Shi and Dinggang Shen},
  title = {{MT-NeT: Multi-Modality Transfer Learning Network for Automated Carotid Vessel Wall Segmentation using Sparse Annotation in MRI}},
  booktitle = {ISBI},
  year = {2023},
  doi = {10.1109/isbi53787.2023.10230750},
}

Loading related content...

Figure