Using Simulated Training Data of Voxel-Level Generative Models to Improve 3D Neuron Reconstruction

doi:10.1109/TMI.2022.3191011

KMS > iHuman研究所

	Using Simulated Training Data of Voxel-Level Generative Models to Improve 3D Neuron Reconstruction
	Chao Liu 1,2,3; Deli Wang 1,2,3; Han Zhang 1,2,3; Wei Wu4,5,6 ; Wenzhi Sun 7,8; Ting Zhao 9; Nenggan Zheng 1,2,3,10
	2022-12-01
发表期刊	IEEE TRANSACTIONS ON MEDICAL IMAGING (IF:8.9[JCR-2023],11.3[5-Year])
ISSN	1558-254X
卷号	41 期号:12 页码:1-1
发表状态	已发表
DOI	10.1109/TMI.2022.3191011
摘要	Reconstructing neuron morphologies from fluorescence microscope images plays a critical role in neuroscience studies. It relies on image segmentation to produce initial masks either for further processing or final results to represent neuronal morphologies. This has been a challenging step due to the variation and complexity of noisy intensity patterns in neuron images acquired from microscopes. Whereas progresses in deep learning have brought the goal of accurate segmentation much closer to reality, creating training data for producing powerful neural networks is often laborious. To overcome the difficulty of obtaining a vast number of annotated data, we propose a novel strategy of using two-stage generative models to simulate training data with voxel-level labels. Trained upon unlabeled data by optimizing a novel objective function of preserving predefined labels, the models are able to synthesize realistic 3D images with underlying voxel labels. We showed that these synthetic images could train segmentation networks to obtain even better performance than manually labeled data. To demonstrate an immediate impact of our work, we further showed that segmentation results produced by networks trained upon synthetic data could be used to improve existing neuron reconstruction methods.
URL	查看原文
收录类别	EI ; SCI
来源库	IEEE
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/211756
专题	iHuman研究所生命科学与技术学院_博士生
作者单位	1.Qiushi Academy for Advanced Studies (QAAS), Zhejiang University, Hangzhou, China 2.College of Computer Science and Technology, Zhejiang University, Hangzhou, China 3.Zhejiang Lab, Hangzhou, China 4.School of Life Science and Technology, ShanghaiTech University, Shanghai, China 5.iHuman Institute, ShanghaiTech University, Shanghai, China 6.Institute of Neuroscience, Chinese Academy of Sciences, Shanghai, China 7.Chinese Institute for Brain Research, Beijing, China 8.School of Basic Medical Sciences, Capital Medical University, Beijing, China 9.Janelia Research Campus, Howard Hughes Medical Institute, Ashburn, VA, USA 10.Collaborative Innovation Center for Artificial Intelligence by MOE and Zhejiang Provincial Government, Zhejiang University, Hangzhou, China
推荐引用方式 GB/T 7714	Chao Liu,Deli Wang,Han Zhang,et al. Using Simulated Training Data of Voxel-Level Generative Models to Improve 3D Neuron Reconstruction[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2022,41(12):1-1.
APA	Chao Liu.,Deli Wang.,Han Zhang.,Wei Wu.,Wenzhi Sun.,...&Nenggan Zheng.(2022).Using Simulated Training Data of Voxel-Level Generative Models to Improve 3D Neuron Reconstruction.IEEE TRANSACTIONS ON MEDICAL IMAGING,41(12),1-1.
MLA	Chao Liu,et al."Using Simulated Training Data of Voxel-Level Generative Models to Improve 3D Neuron Reconstruction".IEEE TRANSACTIONS ON MEDICAL IMAGING 41.12(2022):1-1.