DIKA-Nets: Domain-invariant knowledge-guided attention networks for brain skull stripping of early developing macaques
| Autor: | Tao Zhong, Fenqiang Zhao, Lufan Liao, Li Wang, Yu Zhang, Yuyu Niu, Gang Li, Dinggang Shen, Zhengwang Wu, Yuchen Pei, Zhenyuan Ning |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Brain development
Computer science Cognitive Neuroscience Macaque 050105 experimental psychology lcsh:RC321-571 03 medical and health sciences 0302 clinical medicine Deep Learning Neuroimaging biology.animal Stripping (linguistics) Image Processing Computer-Assisted Animals 0501 psychology and cognitive sciences Brain magnetic resonance imaging Segmentation lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry Brain Mapping Skull stripping biology business.industry 05 social sciences Brain Pattern recognition Magnetic Resonance Imaging Dual self-attention Prior knowledge Infant macaques Neurology Feature (computer vision) Macaca Artificial intelligence business Distance transform 030217 neurology & neurosurgery |
| Zdroj: | NeuroImage, Vol 227, Iss, Pp 117649-(2021) |
| ISSN: | 1095-9572 |
| Popis: | As non-human primates, macaques have a close phylogenetic relationship to human beings and have been proven to be a valuable and widely used animal model in human neuroscience research. Accurate skull stripping (aka. brain extraction) of brain magnetic resonance imaging (MRI) is a crucial prerequisite in neuroimaging analysis of macaques. Most of the current skull stripping methods can achieve satisfactory results for human brains, but when applied to macaque brains, especially during early brain development, the results are often unsatisfactory. In fact, the early dynamic, regionally-heterogeneous development of macaque brains, accompanied by poor and age-related contrast between different anatomical structures, poses significant challenges for accurate skull stripping. To overcome these challenges, we propose a fully-automated framework to effectively fuse the age-specific intensity information and domain-invariant prior knowledge as important guiding information for robust skull stripping of developing macaques from 0 to 36 months of age. Specifically, we generate Signed Distance Map (SDM) and Center of Gravity Distance Map (CGDM) based on the intermediate segmentation results as guidance. Instead of using local convolution, we fuse all information using the Dual Self-Attention Module (DSAM), which can capture global spatial and channel-dependent information of feature maps. To extensively evaluate the performance, we adopt two relatively-large challenging MRI datasets from rhesus macaques and cynomolgus macaques, respectively, with a total of 361 scans from two different scanners with different imaging protocols. We perform cross-validation by using one dataset for training and the other one for testing. Our method outperforms five popular brain extraction tools and three deep-learning-based methods on cross-source MRI datasets without any transfer learning. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect