EUVIMEDEUVIMED entdecken
Crossref

Automated detection of maxillary sinus opacifications compatible with sinusitis from CT images

Kyung Won Kwon iD, Jihun Kim iD, Dongwoo Kang iD

Dentomaxillofacial Radiology · 2024

DOI: 10.1093/dmfr/twae042 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, 2024. Verfasst von Kyung Won Kwon und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otolaryngology, Samsung Changwon Hospital, Sungkyunkwan University School of Medicine, Changwon 51353, Republic of Korea. Hauptthemen laut MEDLINE: Maxillary Sinusitis, Tomography, X-Ray Computed, Maxillary Sinus, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: Sungkyunkwan University School of Medicine Samsung Changwon Hospital, National Research Foundation of Korea, 2024 Hongik University Research Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Sinusitis is a commonly encountered clinical condition that imposes a considerable burden on the healthcare systems. A significant number of maxillary sinus opacifications are diagnosed as sinusitis, often overlooking the precise differentiation between cystic formations and inflammatory sinusitis, resulting in inappropriate clinical treatment. This study aims to improve diagnostic accuracy by investigating the feasibility of differentiating maxillary sinusitis, retention cysts, and normal sinuses.

Methods

We developed a deep learning-based automatic detection model to diagnose maxillary sinusitis using ostiomeatal unit CT images. Of the 1080 randomly selected coronal-view CT images, including 2158 maxillary sinuses, datasets of maxillary sinus lesions comprised 1138 normal sinuses, 366 cysts, and 654 sinusitis based on radiographic findings, and were divided into training (n = 648 CT images), validation (n = 216), and test (n = 216) sets. We utilized a You Only Look Once based model for object detection, enhanced by the transfer learning method. To address the insufficiency of training data, various data augmentation techniques were adopted, thereby improving the model’s robustness.

Results

The trained You Only Look Once version 8 nano model achieved an overall precision of 97.1%, with the following class precisions on the test set: normal = 96.9%, cyst = 95.2%, and sinusitis = 99.2%. With an average F1-score of 95.4%, the F1-score was the highest for normal, then sinusitis, and finally, cysts. Upon evaluating a performance on difficulty level, the precision decreased to 92.4% on challenging test dataset.

Conclusions

The developed model is feasible for assisting clinicians in screening maxillary sinusitis lesions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Maxillary SinusitisTomography, X-Ray ComputedMaxillary SinusDeep LearningHumansMiddle AgedMaleAdultFeasibility StudiesFemaleDiagnosis, DifferentialAged

Stichwörter der Autor:innen

maxillary sinusitis detectionmaxillary sinusitis diagnosismedical artificial intelligencesinus CT imagestransfer learning

Autor:innen und Institutionen

  • Department of Otolaryngology, Samsung Changwon Hospital, Sungkyunkwan University School of Medicine, Changwon 51353, Republic of Korea.
  • School of Electronic and Electrical Engineering, Hongik University, Seoul 04066, Republic of Korea.

ORCID-Profile: Kyung Won Kwon, Jihun Kim, Dongwoo Kang

Förderung

  • Sungkyunkwan University School of Medicine Samsung Changwon Hospital
  • National Research Foundation of Korea
  • 2024 Hongik University Research Fund

Zitieren

APA

Kwon, K. W., Kim, J., & Kang, D. (2024). Automated detection of maxillary sinus opacifications compatible with sinusitis from CT images. Dentomaxillofacial Radiology. https://doi.org/10.1093/dmfr/twae042

Vancouver

Kwon KW, Kim J, Kang D. Automated detection of maxillary sinus opacifications compatible with sinusitis from CT images. Dentomaxillofacial Radiology. 2024. doi:10.1093/dmfr/twae042

BibTeX
@article{Kwon2024,
  author = {Kwon, Kyung Won and Kim, Jihun and Kang, Dongwoo},
  title = {Automated detection of maxillary sinus opacifications compatible with sinusitis from CT images},
  journal = {Dentomaxillofacial Radiology},
  year = {2024},
  doi = {10.1093/dmfr/twae042}
}
Kostenlos starten →