EUVIMEDEUVIMED entdecken
Crossref

Deep learning automatically assesses 2-µm laser-induced skin damage OCT images

Changke Wang, Qiong Ma, Yu Wei, Qi Liu, Yuqing Wang, Chenliang Xu, Caihui Li, Qingyu Cai, Haiyang Sun, Xiaoan Tang, Hongxiang Kang

Lasers in Medical Science · 2024

DOI: 10.1007/s10103-024-04053-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Lasers in Medical Science, 2024. Verfasst von Changke Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Institute of Radiation Medicine, 27 Taiping Road, 100850, Beijing, China. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The present study proposed a noninvasive, automated, in vivo assessment method based on optical coherence tomography (OCT) and deep learning techniques to qualitatively and quantitatively analyze the biological effects of 2-µm laser-induced skin damage at different irradiation doses. Different doses of 2-µm laser irradiation established a mouse skin damage model, after which the skin-damaged tissues were imaged non-invasively in vivo using OCT. The acquired images were preprocessed to construct the dataset required for deep learning. The deep learning models used were U-Net, DeepLabV3+, PSP-Net, and HR-Net, and the trained models were used to segment the damage images and further quantify the damage volume of mouse skin under different irradiation doses. The comparison of the qualitative and quantitative results of the four network models showed that HR-Net had the best performance, the highest agreement between the segmentation results and real values, and the smallest error in the quantitative assessment of the damage volume. Based on HR-Net to segment the damage image and quantify the damage volume, the irradiation doses 5.41, 9.55, 13.05, 20.85, 32.71, 52.92, 76.71, and 97.24 J/cm² corresponded to a damage volume of 4.58, 12.56, 16.74, 20.88, 24.52, 30.75, 34.13, and 37.32 mm³. The damage volume increased in a radiation dose-dependent manner.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAnimalsMiceTomography, Optical CoherenceDisease Models, AnimalLasersSkin

Stichwörter der Autor:innen

2-µm laserDeep learningImage segmentationLaser-induced skin damageOptical coherence tomography

Autor:innen und Institutionen

  • Beijing Institute of Radiation Medicine, 27 Taiping Road, 100850, Beijing, China.
  • College of Information Engineering, Henan University of Science and Technology, 263 Kaiyuan Avenue, 471023, Luoyang, China.
  • College of Life Sciences, Hebei University, 180 East Wusi Road, 071000, Baoding, China.
  • Hunan SANY Industrial Vocational Technical College, Hanli Industrial Park, 410129, Changsha, China.
  • Beijing Institute of Radiation Medicine, 27 Taiping Road, 100850, Beijing, China. khx007@163.com.

Zitieren

APA

Wang, C., Ma, Q., Wei, Y., Liu, Q., Wang, Y., Xu, C., Li, C., Cai, Q., Sun, H., Tang, X., & Kang, H. (2024). Deep learning automatically assesses 2-µm laser-induced skin damage OCT images. Lasers in Medical Science. https://doi.org/10.1007/s10103-024-04053-8

Vancouver

Wang C, Ma Q, Wei Y, Liu Q, Wang Y, Xu C, et al. Deep learning automatically assesses 2-µm laser-induced skin damage OCT images. Lasers in Medical Science. 2024. doi:10.1007/s10103-024-04053-8

BibTeX
@article{Wang2024,
  author = {Wang, Changke and Ma, Qiong and Wei, Yu and Liu, Qi and Wang, Yuqing and Xu, Chenliang and Li, Caihui and Cai, Qingyu and Sun, Haiyang and Tang, Xiaoan and Kang, Hongxiang},
  title = {Deep learning automatically assesses 2-µm laser-induced skin damage OCT images},
  journal = {Lasers in Medical Science},
  year = {2024},
  doi = {10.1007/s10103-024-04053-8}
}
Kostenlos starten →