Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography images
Abstract The complex shape of embryonic cartilage represents a true challenge for phenotyping and basic understanding of skeletal development. X-ray computed microtomography (μCT) enables inspecting relevant tissues in all three dimensions; however, most 3D models are still created by manual segment...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-05-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-12329-8 |
| _version_ | 1811258872034230272 |
|---|---|
| author | Jan Matula Veronika Polakova Jakub Salplachta Marketa Tesarova Tomas Zikmund Marketa Kaucka Igor Adameyko Jozef Kaiser |
| author_facet | Jan Matula Veronika Polakova Jakub Salplachta Marketa Tesarova Tomas Zikmund Marketa Kaucka Igor Adameyko Jozef Kaiser |
| author_sort | Jan Matula |
| collection | DOAJ |
| description | Abstract The complex shape of embryonic cartilage represents a true challenge for phenotyping and basic understanding of skeletal development. X-ray computed microtomography (μCT) enables inspecting relevant tissues in all three dimensions; however, most 3D models are still created by manual segmentation, which is a time-consuming and tedious task. In this work, we utilised a convolutional neural network (CNN) to automatically segment the most complex cartilaginous system represented by the developing nasal capsule. The main challenges of this task stem from the large size of the image data (over a thousand pixels in each dimension) and a relatively small training database, including genetically modified mouse embryos, where the phenotype of the analysed structures differs from the norm. We propose a CNN-based segmentation model optimised for the large image size that we trained using a unique manually annotated database. The segmentation model was able to segment the cartilaginous nasal capsule with a median accuracy of 84.44% (Dice coefficient). The time necessary for segmentation of new samples shortened from approximately 8 h needed for manual segmentation to mere 130 s per sample. This will greatly accelerate the throughput of μCT analysis of cartilaginous skeletal elements in animal models of developmental diseases. |
| first_indexed | 2024-04-12T18:21:00Z |
| format | Article |
| id | doaj.art-c2fca9b406e0413781b27ebb3b061be5 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T18:21:00Z |
| publishDate | 2022-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-c2fca9b406e0413781b27ebb3b061be52022-12-22T03:21:26ZengNature PortfolioScientific Reports2045-23222022-05-0112111310.1038/s41598-022-12329-8Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography imagesJan Matula0Veronika Polakova1Jakub Salplachta2Marketa Tesarova3Tomas Zikmund4Marketa Kaucka5Igor Adameyko6Jozef Kaiser7Central European Institute of Technology, Brno University of TechnologyCentral European Institute of Technology, Brno University of TechnologyCentral European Institute of Technology, Brno University of TechnologyCentral European Institute of Technology, Brno University of TechnologyCentral European Institute of Technology, Brno University of TechnologyMax Planck Institute for Evolutionary BiologyMedical University of ViennaCentral European Institute of Technology, Brno University of TechnologyAbstract The complex shape of embryonic cartilage represents a true challenge for phenotyping and basic understanding of skeletal development. X-ray computed microtomography (μCT) enables inspecting relevant tissues in all three dimensions; however, most 3D models are still created by manual segmentation, which is a time-consuming and tedious task. In this work, we utilised a convolutional neural network (CNN) to automatically segment the most complex cartilaginous system represented by the developing nasal capsule. The main challenges of this task stem from the large size of the image data (over a thousand pixels in each dimension) and a relatively small training database, including genetically modified mouse embryos, where the phenotype of the analysed structures differs from the norm. We propose a CNN-based segmentation model optimised for the large image size that we trained using a unique manually annotated database. The segmentation model was able to segment the cartilaginous nasal capsule with a median accuracy of 84.44% (Dice coefficient). The time necessary for segmentation of new samples shortened from approximately 8 h needed for manual segmentation to mere 130 s per sample. This will greatly accelerate the throughput of μCT analysis of cartilaginous skeletal elements in animal models of developmental diseases.https://doi.org/10.1038/s41598-022-12329-8 |
| spellingShingle | Jan Matula Veronika Polakova Jakub Salplachta Marketa Tesarova Tomas Zikmund Marketa Kaucka Igor Adameyko Jozef Kaiser Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography images Scientific Reports |
| title | Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography images |
| title_full | Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography images |
| title_fullStr | Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography images |
| title_full_unstemmed | Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography images |
| title_short | Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography images |
| title_sort | resolving complex cartilage structures in developmental biology via deep learning based automatic segmentation of x ray computed microtomography images |
| url | https://doi.org/10.1038/s41598-022-12329-8 |
| work_keys_str_mv | AT janmatula resolvingcomplexcartilagestructuresindevelopmentalbiologyviadeeplearningbasedautomaticsegmentationofxraycomputedmicrotomographyimages AT veronikapolakova resolvingcomplexcartilagestructuresindevelopmentalbiologyviadeeplearningbasedautomaticsegmentationofxraycomputedmicrotomographyimages AT jakubsalplachta resolvingcomplexcartilagestructuresindevelopmentalbiologyviadeeplearningbasedautomaticsegmentationofxraycomputedmicrotomographyimages AT marketatesarova resolvingcomplexcartilagestructuresindevelopmentalbiologyviadeeplearningbasedautomaticsegmentationofxraycomputedmicrotomographyimages AT tomaszikmund resolvingcomplexcartilagestructuresindevelopmentalbiologyviadeeplearningbasedautomaticsegmentationofxraycomputedmicrotomographyimages AT marketakaucka resolvingcomplexcartilagestructuresindevelopmentalbiologyviadeeplearningbasedautomaticsegmentationofxraycomputedmicrotomographyimages AT igoradameyko resolvingcomplexcartilagestructuresindevelopmentalbiologyviadeeplearningbasedautomaticsegmentationofxraycomputedmicrotomographyimages AT jozefkaiser resolvingcomplexcartilagestructuresindevelopmentalbiologyviadeeplearningbasedautomaticsegmentationofxraycomputedmicrotomographyimages |