Publication detail

Deep learning model for segmentation of trabecular tissue on CT data of the lumbar spine

ČURILLOVÁ, M. NOHEL, M.

Original Title

Deep learning model for segmentation of trabecular tissue on CT data of the lumbar spine

Type

conference paper

Language

English

Original Abstract

This paper focuses on training a deep learning model for vertebral body segmentation of the lumbar spine. The nnU-Net model was trained and tested on a publicly available dataset LumVBCanSeg consisting of 185 lumbar CT scans. Dice coefficient was used to evaluate the accuracy of the trained model. The mean Dice coefficient of the testing dataset was 0.949 with a standard deviation of 0.103. The model was also tested on clinical data containing various abnormalities, such as lytic lesions in multiple myeloma patients and metallic implants. Results were evaluated visually. While the model showed high accuracy on the testing dataset, the results on scans with anomalies showed a decline in accuracy.

Keywords

multiple myeloma, osteolytic lesions, nnU-Net, segmentation

Authors

ČURILLOVÁ, M.; NOHEL, M.

Released

23. 4. 2024

Publisher

Brno University of Technology, Faculty of Electrical Engineering and Communication

Location

Brno, Czech Republic

ISBN

978-80-214-6230-4

Book

Proceedings II of the 30st Conference STUDENT EEICT 2024: Selected papers

Edition

1

ISBN

2788-1334

Periodical

Proceedings II of the Conference STUDENT EEICT

State

Czech Republic

Pages from

8

Pages to

11

Pages count

4

URL

BibTex

@inproceedings{BUT189059,
  author="Miriam {Čurillová} and Michal {Nohel}",
  title="Deep learning model for segmentation of trabecular tissue on CT data of the lumbar spine",
  booktitle="Proceedings II of the 30st Conference STUDENT EEICT 2024: Selected papers",
  year="2024",
  series="1",
  journal="Proceedings II of the Conference STUDENT EEICT",
  pages="8--11",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno, Czech Republic",
  doi="10.13164/eeict.2024.8",
  isbn="978-80-214-6230-4",
  issn="2788-1334",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2024_sbornik_2.pdf"
}