Detail publikace

Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography images

MATULA, J. POLÁKOVÁ, V. ŠALPLACHTA, J. TESAŘOVÁ, M. ZIKMUND, T. KAUCKÁ, M. ADAMEYKO, I. KAISER, J.

Originální název

Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography images

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

The complex shape of embryonic cartilage represents a true challenge for phenotyping and basic understanding of skeletal development. X-ray computed microtomography (mu CT) 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 mu CT analysis of cartilaginous skeletal elements in animal models of developmental diseases.

Klíčová slova

Convolutional neural network, segmentation, chondrocranium, craniofacial cartilage, nasal capsule, mouse embryo, X-ray computed tomography, CT, 3D imaging

Autoři

MATULA, J.; POLÁKOVÁ, V.; ŠALPLACHTA, J.; TESAŘOVÁ, M.; ZIKMUND, T.; KAUCKÁ, M.; ADAMEYKO, I.; KAISER, J.

Vydáno

24. 5. 2022

Nakladatel

NATURE PORTFOLIO

Místo

BERLIN

ISSN

2045-2322

Periodikum

Scientific Reports

Ročník

12

Číslo

1

Stát

Spojené království Velké Británie a Severního Irska

Strany od

1

Strany do

13

Strany počet

13

URL

https://www.nature.com/articles/s41598-022-12329-8

Plný text v Digitální knihovně

http://hdl.handle.net/11012/204432

BibTex

@article{BUT177989,
  author="Jan {Matula} and Veronika {Poláková} and Jakub {Šalplachta} and Markéta {Kaiser} and Tomáš {Zikmund} and Markéta {Kaucká} and Igor {Adameyko} and Jozef {Kaiser}",
  title="Resolving complex cartilage structures in developmental biology via deep learning-based automatic segmentation of X-ray computed microtomography images",
  journal="Scientific Reports",
  year="2022",
  volume="12",
  number="1",
  pages="1--13",
  doi="10.1038/s41598-022-12329-8",
  issn="2045-2322",
  url="https://www.nature.com/articles/s41598-022-12329-8"
}