Utilizing 2D-region-based CNNs for automatic dendritic spine detection in 3D live cell imaging
Abstract Dendritic spines are considered a morphological proxy for excitatory synapses, rendering them a target of many different lines of research. Over recent years, it has become possible to simultaneously image large numbers of dendritic spines in 3D volumes of neural tissue. In contrast, curren...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-47070-3 |
| _version_ | 1797452851001163776 |
|---|---|
| author | Fabian W. Vogel Sercan Alipek Jens-Bastian Eppler Pamela Osuna-Vargas Jochen Triesch Diane Bissen Amparo Acker-Palmer Simon Rumpel Matthias Kaschube |
| author_facet | Fabian W. Vogel Sercan Alipek Jens-Bastian Eppler Pamela Osuna-Vargas Jochen Triesch Diane Bissen Amparo Acker-Palmer Simon Rumpel Matthias Kaschube |
| author_sort | Fabian W. Vogel |
| collection | DOAJ |
| description | Abstract Dendritic spines are considered a morphological proxy for excitatory synapses, rendering them a target of many different lines of research. Over recent years, it has become possible to simultaneously image large numbers of dendritic spines in 3D volumes of neural tissue. In contrast, currently no automated method for 3D spine detection exists that comes close to the detection performance reached by human experts. However, exploiting such datasets requires new tools for the fully automated detection and analysis of large numbers of spines. Here, we developed an efficient analysis pipeline to detect large numbers of dendritic spines in volumetric fluorescence imaging data acquired by two-photon imaging in vivo. The core of our pipeline is a deep convolutional neural network that was pretrained on a general-purpose image library and then optimized on the spine detection task. This transfer learning approach is data efficient while achieving a high detection precision. To train and validate the model we generated a labeled dataset using five human expert annotators to account for the variability in human spine detection. The pipeline enables fully automated dendritic spine detection reaching a performance slightly below that of the human experts. Our method for spine detection is fast, accurate and robust, and thus well suited for large-scale datasets with thousands of spines. The code is easily applicable to new datasets, achieving high detection performance, even without any retraining or adjustment of model parameters. |
| first_indexed | 2024-03-09T15:14:38Z |
| format | Article |
| id | doaj.art-6c54906e2957479196bffbbd04209935 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T15:14:38Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-6c54906e2957479196bffbbd042099352023-11-26T13:09:43ZengNature PortfolioScientific Reports2045-23222023-11-0113111410.1038/s41598-023-47070-3Utilizing 2D-region-based CNNs for automatic dendritic spine detection in 3D live cell imagingFabian W. Vogel0Sercan Alipek1Jens-Bastian Eppler2Pamela Osuna-Vargas3Jochen Triesch4Diane Bissen5Amparo Acker-Palmer6Simon Rumpel7Matthias Kaschube8Frankfurt Institute for Advanced Studies and Department of Computer Science and Mathematics, Goethe University FrankfurtFrankfurt Institute for Advanced Studies and Department of Computer Science and Mathematics, Goethe University FrankfurtFrankfurt Institute for Advanced Studies and Department of Computer Science and Mathematics, Goethe University FrankfurtFrankfurt Institute for Advanced Studies and Department of Computer Science and Mathematics, Goethe University FrankfurtFrankfurt Institute for Advanced Studies and Department of Computer Science and Mathematics, Goethe University FrankfurtInstitute for Cell Biology and Neuroscience, Goethe University FrankfurtInstitute for Cell Biology and Neuroscience, Goethe University FrankfurtInstitute of Physiology, FTN, University Medical Center, Johannes Gutenberg University MainzFrankfurt Institute for Advanced Studies and Department of Computer Science and Mathematics, Goethe University FrankfurtAbstract Dendritic spines are considered a morphological proxy for excitatory synapses, rendering them a target of many different lines of research. Over recent years, it has become possible to simultaneously image large numbers of dendritic spines in 3D volumes of neural tissue. In contrast, currently no automated method for 3D spine detection exists that comes close to the detection performance reached by human experts. However, exploiting such datasets requires new tools for the fully automated detection and analysis of large numbers of spines. Here, we developed an efficient analysis pipeline to detect large numbers of dendritic spines in volumetric fluorescence imaging data acquired by two-photon imaging in vivo. The core of our pipeline is a deep convolutional neural network that was pretrained on a general-purpose image library and then optimized on the spine detection task. This transfer learning approach is data efficient while achieving a high detection precision. To train and validate the model we generated a labeled dataset using five human expert annotators to account for the variability in human spine detection. The pipeline enables fully automated dendritic spine detection reaching a performance slightly below that of the human experts. Our method for spine detection is fast, accurate and robust, and thus well suited for large-scale datasets with thousands of spines. The code is easily applicable to new datasets, achieving high detection performance, even without any retraining or adjustment of model parameters.https://doi.org/10.1038/s41598-023-47070-3 |
| spellingShingle | Fabian W. Vogel Sercan Alipek Jens-Bastian Eppler Pamela Osuna-Vargas Jochen Triesch Diane Bissen Amparo Acker-Palmer Simon Rumpel Matthias Kaschube Utilizing 2D-region-based CNNs for automatic dendritic spine detection in 3D live cell imaging Scientific Reports |
| title | Utilizing 2D-region-based CNNs for automatic dendritic spine detection in 3D live cell imaging |
| title_full | Utilizing 2D-region-based CNNs for automatic dendritic spine detection in 3D live cell imaging |
| title_fullStr | Utilizing 2D-region-based CNNs for automatic dendritic spine detection in 3D live cell imaging |
| title_full_unstemmed | Utilizing 2D-region-based CNNs for automatic dendritic spine detection in 3D live cell imaging |
| title_short | Utilizing 2D-region-based CNNs for automatic dendritic spine detection in 3D live cell imaging |
| title_sort | utilizing 2d region based cnns for automatic dendritic spine detection in 3d live cell imaging |
| url | https://doi.org/10.1038/s41598-023-47070-3 |
| work_keys_str_mv | AT fabianwvogel utilizing2dregionbasedcnnsforautomaticdendriticspinedetectionin3dlivecellimaging AT sercanalipek utilizing2dregionbasedcnnsforautomaticdendriticspinedetectionin3dlivecellimaging AT jensbastianeppler utilizing2dregionbasedcnnsforautomaticdendriticspinedetectionin3dlivecellimaging AT pamelaosunavargas utilizing2dregionbasedcnnsforautomaticdendriticspinedetectionin3dlivecellimaging AT jochentriesch utilizing2dregionbasedcnnsforautomaticdendriticspinedetectionin3dlivecellimaging AT dianebissen utilizing2dregionbasedcnnsforautomaticdendriticspinedetectionin3dlivecellimaging AT amparoackerpalmer utilizing2dregionbasedcnnsforautomaticdendriticspinedetectionin3dlivecellimaging AT simonrumpel utilizing2dregionbasedcnnsforautomaticdendriticspinedetectionin3dlivecellimaging AT matthiaskaschube utilizing2dregionbasedcnnsforautomaticdendriticspinedetectionin3dlivecellimaging |