EUVIMEDEUVIMED entdecken
Crossref

Contrastive self-supervised learning for diabetic retinopathy early detection

Jihong Ouyang, Dong Mao, Zeqi Guo, Siguang Liu, Dong Xu, Wenting Wang

Medical & Biological Engineering & Computing · 2023-09 · 61 (9) · 2441-2452

DOI: 10.1007/s11517-023-02810-5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 29.04.2023. Verfasst von Jihong Ouyang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Technology, Jilin University, Qianjin Street, Changchun, 130015, Jilin Province, China. Hauptthemen laut MEDLINE: Diabetic Retinopathy, Diabetes Mellitus. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China-Shenzhen Robotics Research Center Project, the Scientific and Technological Developing Scheme of Jilin Province of China, the Energy Administration of Jilin Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic Retinopathy (DR) is the major cause of blindness, which seriously threatens the world's vision health. Limited medical resources make early diagnosis and a large-scale screening of DR difficult. Most of the current automatic diagnostic methods are mostly based on deep learning and large-scale labeled data. However, the insufficiency of manual annotations for medical images still is a great challenge of training deep neural networks. Self-supervised learning methods are proposed to learn general features from dataset without manual annotations. Inspired by this, we proposed a deep learning based DR classification model (SimCLR-DR). In this paper, we first use contrastive self-learning algorithm to pre-train the encoder based on convolution network with unlabeled retinal images, then retrain the encoder with classifier on a small annotated training data to detect referable DR. The experimental results on Kaggle dataset show that this proposed method can overcome the training data insufficiency problem and performs better than transfer learning. SimCLR-DR is a good beginning for other deep learning based medical image detection approaches facing the challenge of insufficient annotated data. Figure presents an overview of the proposed framework, which contains three main steps: (i) Data preprocessing; (ii) Pretext task of SimCLR-DR based on contrastive learning; (iii) Downstream Task of SimCLRDR based on CNN.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diabetic RetinopathyDiabetes MellitusHumansMachine LearningNeural Networks, ComputerAlgorithmsSupervised Machine Learning

Stichwörter der Autor:innen

Convolutional neural networksDeep learningDiabetic Retinopathy classificationMedical image analysisSelf-supervised learning

Autor:innen und Institutionen

  • Department of Computer Science and Technology, Jilin University, Qianjin Street, Changchun, 130015, Jilin Province, China.
  • Department of Computer Science and Technology, Jilin University, Qianjin Street, Changchun, 130015, Jilin Province, China. lsgmliss@163.com.
  • University of Missouri, Columbia, MO, USA.
  • Department of Computer Science, University of Texas at Dallas, Richardson, TX, USA.

Förderung

  • National Natural Science Foundation of China-Shenzhen Robotics Research Center Project
  • the Scientific and Technological Developing Scheme of Jilin Province of China
  • the Energy Administration of Jilin Province

Zitieren

APA

Ouyang, J., Mao, D., Guo, Z., Liu, S., Xu, D., & Wang, W. (2023). Contrastive self-supervised learning for diabetic retinopathy early detection. Medical & Biological Engineering & Computing, 61(9), 2441-2452. https://doi.org/10.1007/s11517-023-02810-5

Vancouver

Ouyang J, Mao D, Guo Z, Liu S, Xu D, Wang W. Contrastive self-supervised learning for diabetic retinopathy early detection. Medical & Biological Engineering & Computing. 2023;61(9):2441-2452. doi:10.1007/s11517-023-02810-5

BibTeX
@article{Ouyang2023,
  author = {Ouyang, Jihong and Mao, Dong and Guo, Zeqi and Liu, Siguang and Xu, Dong and Wang, Wenting},
  title = {Contrastive self-supervised learning for diabetic retinopathy early detection},
  journal = {Medical & Biological Engineering & Computing},
  year = {2023},
  volume = {61},
  number = {9},
  pages = {2441--2452},
  doi = {10.1007/s11517-023-02810-5}
}
Kostenlos starten →