期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 41, 期 12, 页码 3624-3635出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2022.3191011
关键词
Neuron reconstruction; microscope image simulation; generative model; image segmentation
类别
资金
- National Key Research and Development Program of China [2020YFB1313501]
- Zhejiang Laboratory [2020KB0AC02]
- Zhejiang Provincial Natural Science Foundation [LR19F020005]
- National Natural Science Foundation of China [61972347]
- Key Research and Development Program of Zhejiang Province [2021C03003, 2022C01022]
- Fundamental Research Funds for the Central Universities [226-2022-00051]
Reconstructing neuron morphologies from fluorescence microscope images is crucial for neuroscience studies. This study proposes a strategy of using two-stage generative models to simulate training data with voxel-level labels, resulting in realistic 3D images with underlying voxel labels. The results show that networks trained on synthetic data outperform those trained on manually labeled data in segmentation performance.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据