Editorial & Opinion
Diabetic retinopathy classification for supervised machine learning algorithms.
| العنوان: | Diabetic retinopathy classification for supervised machine learning algorithms. |
|---|---|
| المؤلفون: | Nakayama LF; Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil. nakayama.luis@gmail.com., Ribeiro LZ; Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil., Gonçalves MB; Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil.; Instituto Paulista de Estudos e Pesquisas em Oftalmologia, IPEPO, Vision Institute, São Paulo, SP, Brazil.; NIHR Biomedical Research Centre for Ophthalmology, Moorfield Eye Hospital, NHS Foundation Trust, and UCL Institute of Ophthalmology, London, UK., Ferraz DA; Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil.; Instituto Paulista de Estudos e Pesquisas em Oftalmologia, IPEPO, Vision Institute, São Paulo, SP, Brazil.; NIHR Biomedical Research Centre for Ophthalmology, Moorfield Eye Hospital, NHS Foundation Trust, and UCL Institute of Ophthalmology, London, UK., Dos Santos HNV; Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil., Malerbi FK; Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil., Morales PH; Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil.; Instituto Paulista de Estudos e Pesquisas em Oftalmologia, IPEPO, Vision Institute, São Paulo, SP, Brazil., Maia M; Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil., Regatieri CVS; Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil., Mattos RB Jr; Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil.; Instituto Paulista de Estudos e Pesquisas em Oftalmologia, IPEPO, Vision Institute, São Paulo, SP, Brazil. |
| المصدر: | International journal of retina and vitreous [Int J Retina Vitreous] 2022 Jan 03; Vol. 8 (1), pp. 1. Date of Electronic Publication: 2022 Jan 03. |
| نوع المنشور: | Letter |
| اللغة: | English |
| بيانات الدورية: | Publisher: BioMed Central Country of Publication: England NLM ID: 101677897 Publication Model: Electronic Cited Medium: Print ISSN: 2056-9920 (Print) Linking ISSN: 20569920 NLM ISO Abbreviation: Int J Retina Vitreous Subsets: PubMed not MEDLINE |
| أسماء مطبوعة: | Original Publication: London : BioMed Central, [2015]- |
| مستخلص: | Background: Artificial intelligence and automated technology were first reported more than 70 years ago and nowadays provide unprecedented diagnostic accuracy, screening capacity, risk stratification, and workflow optimization. Diabetic retinopathy is an important cause of preventable blindness worldwide, and artificial intelligence technology provides precocious diagnosis, monitoring, and guide treatment. High-quality exams are fundamental in supervised artificial intelligence algorithms, but the lack of ground truth standards in retinal exams datasets is a problem. Main Body: In this article, ETDRS, NHS, ICDR, SDGS diabetic retinopathy grading, and manual annotation are described and compared in publicly available datasets. The various DR labeling systems generate a fundamental problem for AI datasets. Possible solutions are standardization of DR classification and direct retinal-finding identifications. Conclusion: Reliable labeling methods also need to be considered in datasets with more trustworthy labeling. (© 2021. The Author(s).) |
| References: | Ophthalmology. 1991 May;98(5 Suppl):786-806. (PMID: 2062513) Gastrointest Endosc. 2020 Oct;92(4):807-812. (PMID: 32565184) J Diabetes Sci Technol. 2021 Nov;15(6):1410-1411. (PMID: 34259085) Ophthalmology. 2007 Sep;114(9):1748-54. (PMID: 17368543) Transl Vis Sci Technol. 2020 Feb 27;9(2):13. (PMID: 32704419) NPJ Digit Med. 2018 Aug 28;1:39. (PMID: 31304320) N Engl J Med. 2012 Mar 29;366(13):1227-39. (PMID: 22455417) Acta Diabetol. 2017 Jun;54(6):515-525. (PMID: 28224275) Neuroimaging Clin N Am. 2020 Nov;30(4):393-399. (PMID: 33038991) Lancet Digit Health. 2021 Jan;3(1):e51-e66. (PMID: 33735069) Ophthalmic Res. 2019;62(4):190-195. (PMID: 31454808) Ophthalmology. 2020 Jan;127(1):P66-P145. (PMID: 31757498) Med Image Anal. 2012 Jan;16(1):216-26. (PMID: 21865074) Br J Ophthalmol. 2019 Feb;103(2):167-175. (PMID: 30361278) Community Eye Health. 2015;28(92):72-3. (PMID: 27418727) Ophthalmology. 2003 Sep;110(9):1677-82. (PMID: 13129861) Lancet Digit Health. 2019 Oct;1(6):e271-e297. (PMID: 33323251) Curr Opin Ophthalmol. 2020 Sep;31(5):337-350. (PMID: 32740059) PLoS One. 2017 Jun 22;12(6):e0179790. (PMID: 28640840) Acta Inform Med. 2019 Dec;27(5):327-332. (PMID: 32210500) Ophthalmology. 2020 Apr;127(4S):S97-S98. (PMID: 32200832) PLoS One. 2014 Jun 02;9(6):e96814. (PMID: 24886780) |
| فهرسة مساهمة: | Keywords: Artificial intelligence; Datasets; Diabetic retinopathy classifications |
| تواريخ الأحداث: | Date Created: 20220104 Latest Revision: 20220429 |
| رمز التحديث: | 20240628 |
| مُعرف محوري في PubMed: | PMC8722080 |
| DOI: | 10.1186/s40942-021-00352-2 |
| PMID: | 34980281 |
| قاعدة البيانات: | MEDLINE |
Find this article in full text from Springer Verlag. 
Full Text Finder | تدمد: | 2056-9920 |
|---|---|
| DOI: | 10.1186/s40942-021-00352-2 |