EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Based Multi-Class Segmentation of the Paranasal Sinuses of Sinusitis Patients Based on Computed Tomographic Images

Jongwook Whangbo, Juhui Lee iD, Young Jae Kim, Seon Tae Kim iD, Kwang Gi Kim iD

Sensors · 18.03.2024 · 24 (6) · 1933

DOI: 10.3390/s24061933 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.03.2024. Verfasst von Jongwook Whangbo und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Wesleyan University, Middletown, CT 06459, USA. Hauptthemen laut MEDLINE: Deep Learning, Sinusitis. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Trade, Industry and Energy, Gachon University, Ministry of Trade, Industry & Energy (MOTIE, Korea).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate paranasal sinus segmentation is essential for reducing surgical complications through surgical guidance systems. This study introduces a multiclass Convolutional Neural Network (CNN) segmentation model by comparing four 3D U-Net variations—normal, residual, dense, and residual-dense. Data normalization and training were conducted on a 40-patient test set (20 normal, 20 abnormal) using 5-fold cross-validation. The normal 3D U-Net demonstrated superior performance with an F1 score of 84.29% on the normal test set and 79.32% on the abnormal set, exhibiting higher true positive rates for the sphenoid and maxillary sinus in both sets. Despite effective segmentation in clear sinuses, limitations were observed in mucosal inflammation. Nevertheless, the algorithm’s enhanced segmentation of abnormal sinuses suggests potential clinical applications, with ongoing refinements expected for broader utility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSinusitisHumansNeural Networks, ComputerMaxillary SinusTomography, X-Ray ComputedImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Convolutional Neural Network (CNN)chronic sinusitismulticlass segmentationparanasal sinuses

Autor:innen und Institutionen

  • Department of Computer Science, Wesleyan University, Middletown, CT 06459, USA.
  • Medical Devices R&D Center, Gachon University Gil Medical Center, Incheon 21565, Republic of Korea.
  • Department of Health Sciences and Technology, Gachon Advanced Institute for Health & Sciences and Technology (GAIHST), Gachon University, Incheon 21565, Republic of Korea.
  • Department of Otolaryngology-Head and Neck Surgery, Gachon University Gil Hospital, Incheon 21565, Republic of Korea.
  • Department of Biomedical Engineering, College of IT Convergence, Gachon University, Seongnam-si 13120, Republic of Korea.

ORCID-Profile: Juhui Lee, Seon Tae Kim, Kwang Gi Kim

Förderung

  • Ministry of Trade, Industry and Energy
  • Gachon University
  • Ministry of Trade, Industry & Energy (MOTIE, Korea)

Zitieren

APA

Whangbo, J., Lee, J., Kim, Y. J., Kim, S. T., & Kim, K. G. (2024). Deep Learning-Based Multi-Class Segmentation of the Paranasal Sinuses of Sinusitis Patients Based on Computed Tomographic Images. Sensors, 24(6), 1933. https://doi.org/10.3390/s24061933

Vancouver

Whangbo J, Lee J, Kim YJ, Kim ST, Kim KG. Deep Learning-Based Multi-Class Segmentation of the Paranasal Sinuses of Sinusitis Patients Based on Computed Tomographic Images. Sensors. 2024;24(6):1933. doi:10.3390/s24061933

BibTeX
@article{Whangbo2024,
  author = {Whangbo, Jongwook and Lee, Juhui and Kim, Young Jae and Kim, Seon Tae and Kim, Kwang Gi},
  title = {Deep Learning-Based Multi-Class Segmentation of the Paranasal Sinuses of Sinusitis Patients Based on Computed Tomographic Images},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {6},
  pages = {1933},
  doi = {10.3390/s24061933}
}
Kostenlos starten →