EUVIMEDEUVIMED entdecken
Crossref

Automated classification of multiple ophthalmic diseases using ultrasound images by deep learning

Yijie Wang iD, Zihao Xu, Ruilong Dan iD, Chunlei Yao, Ji Shao, Yiming Sun, Yaqi Wang, Juan Ye iD

British Journal of Ophthalmology · 2024-07 · 108 (7) · 999-1004

DOI: 10.1136/bjo-2022-322953 ↗

Kurz gefasst

Fachartikel in der Zeitschrift British Journal of Ophthalmology, online erschienen am 18.10.2023. Verfasst von Yijie Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. Hauptthemen laut MEDLINE: Deep Learning, Ultrasonography, Eye Diseases. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: the National Key Research and Development Program of China, the Clinical Medical Research Center for Eye Diseases of Zhejiang Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Ultrasound imaging is suitable for detecting and diagnosing ophthalmic abnormalities. However, a shortage of experienced sonographers and ophthalmologists remains a problem. This study aims to develop a multibranch transformer network (MBT-Net) for the automated classification of multiple ophthalmic diseases using B-mode ultrasound images.

Methods

Ultrasound images with six clinically confirmed categories, including normal, retinal detachment, vitreous haemorrhage, intraocular tumour, posterior scleral staphyloma and other abnormalities, were used to develop and evaluate the MBT-Net. Images were derived from five different ultrasonic devices operated by different sonographers and divided into training set, validation set, internal testing set and temporal external testing set. Two senior ophthalmologists and two junior ophthalmologists were recruited to compare the model’s performance.

Results

A total of 10 184 ultrasound images were collected. The MBT-Net got an accuracy of 87.80% (95% CI 86.26% to 89.18%) in the internal testing set, which was significantly higher than junior ophthalmologists (95% CI 67.37% to 79.16%; both p

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningUltrasonographyEye DiseasesHumansMaleFemaleReproducibility of ResultsMiddle AgedAdultROC Curve

Stichwörter der Autor:innen

diagnostic tests/investigationimaging

Autor:innen und Institutionen

  • Department of Ophthalmology, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
  • Microelectronics CAD Center, Hangzhou Dianzi University, Hangzhou, China.
  • College of Media Engineering, Communication University of Zhejiang, Hangzhou, China yejuan@zju.edu.cn wangyaqi@cuz.edu.cn.
  • Department of Ophthalmology, the Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China yejuan@zju.edu.cn wangyaqi@cuz.edu.cn.

ORCID-Profile: Yijie Wang, Ruilong Dan, Juan Ye

Förderung

  • the National Key Research and Development Program of China
  • the Clinical Medical Research Center for Eye Diseases of Zhejiang Province

Zitieren

APA

Wang, Y., Xu, Z., Dan, R., Yao, C., Shao, J., Sun, Y., Wang, Y., & Ye, J. (2024). Automated classification of multiple ophthalmic diseases using ultrasound images by deep learning. British Journal of Ophthalmology, 108(7), 999-1004. https://doi.org/10.1136/bjo-2022-322953

Vancouver

Wang Y, Xu Z, Dan R, Yao C, Shao J, Sun Y, et al. Automated classification of multiple ophthalmic diseases using ultrasound images by deep learning. British Journal of Ophthalmology. 2024;108(7):999-1004. doi:10.1136/bjo-2022-322953

BibTeX
@article{Wang2024,
  author = {Wang, Yijie and Xu, Zihao and Dan, Ruilong and Yao, Chunlei and Shao, Ji and Sun, Yiming and Wang, Yaqi and Ye, Juan},
  title = {Automated classification of multiple ophthalmic diseases using ultrasound images by deep learning},
  journal = {British Journal of Ophthalmology},
  year = {2024},
  volume = {108},
  number = {7},
  pages = {999--1004},
  doi = {10.1136/bjo-2022-322953}
}
Kostenlos starten →