EUVIMEDEUVIMED entdecken
Crossref

Deep Deblurring in Teledermatology: Deep Learning Models Restore the Accuracy of Blurry Images’ Classification

Hsu-Hang Yeh iD, Benny Wei-Yun Hsu, Sheng-Yuan Chou, Ting-Jung Hsu, Vincent S Tseng, Chih-Hung Lee iD

Telemedicine and e-Health · 2024

DOI: 10.1089/tmj.2023.0703 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Telemedicine and e-Health, 2024. Verfasst von Hsu-Hang Yeh und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, National Taiwan University Hospital, Taipei, Taiwan. Hauptthemen laut MEDLINE: Deep Learning, Skin Diseases, Dermatology, Telemedicine. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 26 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Blurry images in teledermatology and consultation increased the diagnostic difficulty for both deep learning models and physicians. We aim to determine the extent of restoration in diagnostic accuracy after blurry images are deblurred by deep learning models.

Methods

We used 19,191 skin images from a public skin image dataset that includes 23 skin disease categories, 54 skin images from a public dataset of blurry skin images, and 53 blurry dermatology consultation photos in a medical center to compare the diagnosis accuracy of trained diagnostic deep learning models and subjective sharpness between blurry and deblurred images. We evaluated five different deblurring models, including models for motion blur, Gaussian blur, Bokeh blur, mixed slight blur, and mixed strong blur. Main Outcomes and Measures: Diagnostic accuracy was measured as sensitivity and precision of correct model prediction of the skin disease category. Sharpness rating was performed by board-certified dermatologists on a 4-point scale, with 4 being the highest image clarity.

Results

The sensitivity of diagnostic models dropped 0.15 and 0.22 on slightly and strongly blurred images, respectively, and deblurring models restored 0.14 and 0.17 for each group. The sharpness ratings perceived by dermatologists improved from 1.87 to 2.51 after deblurring. Activation maps showed the focus of diagnostic models was compromised by the blurriness but was restored after deblurring.

Conclusions

Deep learning models can restore the diagnostic accuracy of diagnostic models for blurry images and increase image sharpness perceived by dermatologists. The model can be incorporated into teledermatology to help the diagnosis of blurry images.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSkin DiseasesDermatologyTelemedicineHumansPhotography

Stichwörter der Autor:innen

artificial intelligencedeblurringdeep learningmedical informaticsteledermatologytelemedicine

Autor:innen und Institutionen

  • Department of Ophthalmology, National Taiwan University Hospital, Taipei, Taiwan.
  • Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan.
  • Department of Dermatology, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan.
  • Institute for Translational Research in Biomedicine, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.

ORCID-Profile: Hsu-Hang Yeh, Chih-Hung Lee

Zitieren

APA

Yeh, H. H., Hsu, B. W., Chou, S. Y., Hsu, T. J., Tseng, V. S., & Lee, C. H. (2024). Deep Deblurring in Teledermatology: Deep Learning Models Restore the Accuracy of Blurry Images’ Classification. Telemedicine and e-Health. https://doi.org/10.1089/tmj.2023.0703

Vancouver

Yeh HH, Hsu BW, Chou SY, Hsu TJ, Tseng VS, Lee CH. Deep Deblurring in Teledermatology: Deep Learning Models Restore the Accuracy of Blurry Images’ Classification. Telemedicine and e-Health. 2024. doi:10.1089/tmj.2023.0703

BibTeX
@article{Yeh2024,
  author = {Yeh, Hsu-Hang and Hsu, Benny Wei-Yun and Chou, Sheng-Yuan and Hsu, Ting-Jung and Tseng, Vincent S and Lee, Chih-Hung},
  title = {Deep Deblurring in Teledermatology: Deep Learning Models Restore the Accuracy of Blurry Images’ Classification},
  journal = {Telemedicine and e-Health},
  year = {2024},
  doi = {10.1089/tmj.2023.0703}
}
Kostenlos starten →