Deep learning based neuronal soma detection and counting for Alzheimer's disease analysis. Li, Q., Zhang, Y., Liang, H., Gong, H., Jiang, L., Liu, Q., & Shen, L. Computer Methods and Programs in Biomedicine, 203:106023, May, 2021. ![Deep learning based neuronal soma detection and counting for Alzheimer's disease analysis [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Background and objective Alzheimer's Disease (AD) is associated with neuronal damage and decrease. Micro-Optical Sectioning Tomography (MOST) provides an approach to acquire high-resolution images for neuron analysis in the whole-brain. Application of this technique to AD mouse brain enables us to investigate neuron changes during the progression of AD pathology. However, how to deal with the huge amount of data becomes the bottleneck. Methods Using MOST technology, we acquired 3D whole-brain images of six AD mice, and sampled the imaging data of four regions in each mouse brain for AD progression analysis. To count the number of neurons, we proposed a deep learning based method by detecting neuronal soma in the neuronal images. In our method, the neuronal images were first cut into small cubes, then a Convolutional Neural Network (CNN) classifier was designed to detect the neuronal soma by classifying the cubes into three categories, “soma”, “fiber”, and “background”. Results Compared with the manual method and currently available NeuroGPS software, our method demonstrates faster speed and higher accuracy in identifying neurons from the MOST images. By applying our method to various brain regions of 6-month-old and 12-month-old AD mice, we found that the amount of neurons in three brain regions (lateral entorhinal cortex, medial entorhinal cortex, and presubiculum) decreased slightly with the increase of age, which is consistent with the experimental results previously reported. Conclusion This paper provides a new method to automatically handle the huge amounts of data and accurately identify neuronal soma from the MOST images. It also provides the potential possibility to construct a whole-brain neuron projection to reveal the impact of AD pathology on mouse brain.
@article{li_deep_2021,
title = {Deep learning based neuronal soma detection and counting for {Alzheimer}'s disease analysis},
volume = {203},
issn = {0169-2607},
url = {https://www.sciencedirect.com/science/article/pii/S0169260721000985},
doi = {10.1016/j.cmpb.2021.106023},
abstract = {Background and objective
Alzheimer's Disease (AD) is associated with neuronal damage and decrease. Micro-Optical Sectioning Tomography (MOST) provides an approach to acquire high-resolution images for neuron analysis in the whole-brain. Application of this technique to AD mouse brain enables us to investigate neuron changes during the progression of AD pathology. However, how to deal with the huge amount of data becomes the bottleneck.
Methods
Using MOST technology, we acquired 3D whole-brain images of six AD mice, and sampled the imaging data of four regions in each mouse brain for AD progression analysis. To count the number of neurons, we proposed a deep learning based method by detecting neuronal soma in the neuronal images. In our method, the neuronal images were first cut into small cubes, then a Convolutional Neural Network (CNN) classifier was designed to detect the neuronal soma by classifying the cubes into three categories, “soma”, “fiber”, and “background”.
Results
Compared with the manual method and currently available NeuroGPS software, our method demonstrates faster speed and higher accuracy in identifying neurons from the MOST images. By applying our method to various brain regions of 6-month-old and 12-month-old AD mice, we found that the amount of neurons in three brain regions (lateral entorhinal cortex, medial entorhinal cortex, and presubiculum) decreased slightly with the increase of age, which is consistent with the experimental results previously reported.
Conclusion
This paper provides a new method to automatically handle the huge amounts of data and accurately identify neuronal soma from the MOST images. It also provides the potential possibility to construct a whole-brain neuron projection to reveal the impact of AD pathology on mouse brain.},
language = {en},
urldate = {2021-04-01},
journal = {Computer Methods and Programs in Biomedicine},
author = {Li, Qiufu and Zhang, Yu and Liang, Hanbang and Gong, Hui and Jiang, Liang and Liu, Qiong and Shen, Linlin},
month = may,
year = {2021},
keywords = {Alzheimer's disease (AD), Brain region, CNN, Convolutional Neural Networks, Deep learning, Micro-optical sectioning tomography (MOST), Neuronal soma},
pages = {106023},
}
Downloads: 0
{"_id":"zusk46RhFQYaEzuY5","bibbaseid":"li-zhang-liang-gong-jiang-liu-shen-deeplearningbasedneuronalsomadetectionandcountingforalzheimersdiseaseanalysis-2021","author_short":["Li, Q.","Zhang, Y.","Liang, H.","Gong, H.","Jiang, L.","Liu, Q.","Shen, L."],"bibdata":{"bibtype":"article","type":"article","title":"Deep learning based neuronal soma detection and counting for Alzheimer's disease analysis","volume":"203","issn":"0169-2607","url":"https://www.sciencedirect.com/science/article/pii/S0169260721000985","doi":"10.1016/j.cmpb.2021.106023","abstract":"Background and objective Alzheimer's Disease (AD) is associated with neuronal damage and decrease. Micro-Optical Sectioning Tomography (MOST) provides an approach to acquire high-resolution images for neuron analysis in the whole-brain. Application of this technique to AD mouse brain enables us to investigate neuron changes during the progression of AD pathology. However, how to deal with the huge amount of data becomes the bottleneck. Methods Using MOST technology, we acquired 3D whole-brain images of six AD mice, and sampled the imaging data of four regions in each mouse brain for AD progression analysis. To count the number of neurons, we proposed a deep learning based method by detecting neuronal soma in the neuronal images. In our method, the neuronal images were first cut into small cubes, then a Convolutional Neural Network (CNN) classifier was designed to detect the neuronal soma by classifying the cubes into three categories, “soma”, “fiber”, and “background”. Results Compared with the manual method and currently available NeuroGPS software, our method demonstrates faster speed and higher accuracy in identifying neurons from the MOST images. By applying our method to various brain regions of 6-month-old and 12-month-old AD mice, we found that the amount of neurons in three brain regions (lateral entorhinal cortex, medial entorhinal cortex, and presubiculum) decreased slightly with the increase of age, which is consistent with the experimental results previously reported. Conclusion This paper provides a new method to automatically handle the huge amounts of data and accurately identify neuronal soma from the MOST images. It also provides the potential possibility to construct a whole-brain neuron projection to reveal the impact of AD pathology on mouse brain.","language":"en","urldate":"2021-04-01","journal":"Computer Methods and Programs in Biomedicine","author":[{"propositions":[],"lastnames":["Li"],"firstnames":["Qiufu"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Yu"],"suffixes":[]},{"propositions":[],"lastnames":["Liang"],"firstnames":["Hanbang"],"suffixes":[]},{"propositions":[],"lastnames":["Gong"],"firstnames":["Hui"],"suffixes":[]},{"propositions":[],"lastnames":["Jiang"],"firstnames":["Liang"],"suffixes":[]},{"propositions":[],"lastnames":["Liu"],"firstnames":["Qiong"],"suffixes":[]},{"propositions":[],"lastnames":["Shen"],"firstnames":["Linlin"],"suffixes":[]}],"month":"May","year":"2021","keywords":"Alzheimer's disease (AD), Brain region, CNN, Convolutional Neural Networks, Deep learning, Micro-optical sectioning tomography (MOST), Neuronal soma","pages":"106023","bibtex":"@article{li_deep_2021,\n\ttitle = {Deep learning based neuronal soma detection and counting for {Alzheimer}'s disease analysis},\n\tvolume = {203},\n\tissn = {0169-2607},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0169260721000985},\n\tdoi = {10.1016/j.cmpb.2021.106023},\n\tabstract = {Background and objective\nAlzheimer's Disease (AD) is associated with neuronal damage and decrease. Micro-Optical Sectioning Tomography (MOST) provides an approach to acquire high-resolution images for neuron analysis in the whole-brain. Application of this technique to AD mouse brain enables us to investigate neuron changes during the progression of AD pathology. However, how to deal with the huge amount of data becomes the bottleneck.\nMethods\nUsing MOST technology, we acquired 3D whole-brain images of six AD mice, and sampled the imaging data of four regions in each mouse brain for AD progression analysis. To count the number of neurons, we proposed a deep learning based method by detecting neuronal soma in the neuronal images. In our method, the neuronal images were first cut into small cubes, then a Convolutional Neural Network (CNN) classifier was designed to detect the neuronal soma by classifying the cubes into three categories, “soma”, “fiber”, and “background”.\nResults\nCompared with the manual method and currently available NeuroGPS software, our method demonstrates faster speed and higher accuracy in identifying neurons from the MOST images. By applying our method to various brain regions of 6-month-old and 12-month-old AD mice, we found that the amount of neurons in three brain regions (lateral entorhinal cortex, medial entorhinal cortex, and presubiculum) decreased slightly with the increase of age, which is consistent with the experimental results previously reported.\nConclusion\nThis paper provides a new method to automatically handle the huge amounts of data and accurately identify neuronal soma from the MOST images. It also provides the potential possibility to construct a whole-brain neuron projection to reveal the impact of AD pathology on mouse brain.},\n\tlanguage = {en},\n\turldate = {2021-04-01},\n\tjournal = {Computer Methods and Programs in Biomedicine},\n\tauthor = {Li, Qiufu and Zhang, Yu and Liang, Hanbang and Gong, Hui and Jiang, Liang and Liu, Qiong and Shen, Linlin},\n\tmonth = may,\n\tyear = {2021},\n\tkeywords = {Alzheimer's disease (AD), Brain region, CNN, Convolutional Neural Networks, Deep learning, Micro-optical sectioning tomography (MOST), Neuronal soma},\n\tpages = {106023},\n}\n\n","author_short":["Li, Q.","Zhang, Y.","Liang, H.","Gong, H.","Jiang, L.","Liu, Q.","Shen, L."],"key":"li_deep_2021","id":"li_deep_2021","bibbaseid":"li-zhang-liang-gong-jiang-liu-shen-deeplearningbasedneuronalsomadetectionandcountingforalzheimersdiseaseanalysis-2021","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S0169260721000985"},"keyword":["Alzheimer's disease (AD)","Brain region","CNN","Convolutional Neural Networks","Deep learning","Micro-optical sectioning tomography (MOST)","Neuronal soma"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/iagogv","dataSources":["ovn29uG6Mbp3JWCRR"],"keywords":["alzheimer's disease (ad)","brain region","cnn","convolutional neural networks","deep learning","micro-optical sectioning tomography (most)","neuronal soma"],"search_terms":["deep","learning","based","neuronal","soma","detection","counting","alzheimer","disease","analysis","li","zhang","liang","gong","jiang","liu","shen"],"title":"Deep learning based neuronal soma detection and counting for Alzheimer's disease analysis","year":2021}