Diabetic retinopathy classification for supervised machine learning algorithms
Abstract 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 blindn...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-01-01
|
| Series: | International Journal of Retina and Vitreous |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40942-021-00352-2 |
| _version_ | 1818979369915252736 |
|---|---|
| author | Luis Filipe Nakayama Lucas Zago Ribeiro Mariana Batista Gonçalves Daniel A. Ferraz Helen Nazareth Veloso dos Santos Fernando Korn Malerbi Paulo Henrique Morales Mauricio Maia Caio Vinicius Saito Regatieri Rubens Belfort Mattos |
| author_facet | Luis Filipe Nakayama Lucas Zago Ribeiro Mariana Batista Gonçalves Daniel A. Ferraz Helen Nazareth Veloso dos Santos Fernando Korn Malerbi Paulo Henrique Morales Mauricio Maia Caio Vinicius Saito Regatieri Rubens Belfort Mattos |
| author_sort | Luis Filipe Nakayama |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-12-20T16:58:27Z |
| format | Article |
| id | doaj.art-bf6e8072d7e548a7a94b623993073ac9 |
| institution | Directory Open Access Journal |
| issn | 2056-9920 |
| language | English |
| last_indexed | 2024-12-20T16:58:27Z |
| publishDate | 2022-01-01 |
| publisher | BMC |
| record_format | Article |
| series | International Journal of Retina and Vitreous |
| spelling | doaj.art-bf6e8072d7e548a7a94b623993073ac92022-12-21T19:32:40ZengBMCInternational Journal of Retina and Vitreous2056-99202022-01-01811510.1186/s40942-021-00352-2Diabetic retinopathy classification for supervised machine learning algorithmsLuis Filipe Nakayama0Lucas Zago Ribeiro1Mariana Batista Gonçalves2Daniel A. Ferraz3Helen Nazareth Veloso dos Santos4Fernando Korn Malerbi5Paulo Henrique Morales6Mauricio Maia7Caio Vinicius Saito Regatieri8Rubens Belfort Mattos9Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPMPhysician, Department of Ophthalmology, Universidade Federal de São Paulo - EPMPhysician, Department of Ophthalmology, Universidade Federal de São Paulo - EPMPhysician, Department of Ophthalmology, Universidade Federal de São Paulo - EPMPhysician, Department of Ophthalmology, Universidade Federal de São Paulo - EPMPhysician, Department of Ophthalmology, Universidade Federal de São Paulo - EPMPhysician, Department of Ophthalmology, Universidade Federal de São Paulo - EPMPhysician, Department of Ophthalmology, Universidade Federal de São Paulo - EPMPhysician, Department of Ophthalmology, Universidade Federal de São Paulo - EPMPhysician, Department of Ophthalmology, Universidade Federal de São Paulo - EPMAbstract 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.https://doi.org/10.1186/s40942-021-00352-2Diabetic retinopathy classificationsArtificial intelligenceDatasets |
| spellingShingle | Luis Filipe Nakayama Lucas Zago Ribeiro Mariana Batista Gonçalves Daniel A. Ferraz Helen Nazareth Veloso dos Santos Fernando Korn Malerbi Paulo Henrique Morales Mauricio Maia Caio Vinicius Saito Regatieri Rubens Belfort Mattos Diabetic retinopathy classification for supervised machine learning algorithms International Journal of Retina and Vitreous Diabetic retinopathy classifications Artificial intelligence Datasets |
| title | Diabetic retinopathy classification for supervised machine learning algorithms |
| title_full | Diabetic retinopathy classification for supervised machine learning algorithms |
| title_fullStr | Diabetic retinopathy classification for supervised machine learning algorithms |
| title_full_unstemmed | Diabetic retinopathy classification for supervised machine learning algorithms |
| title_short | Diabetic retinopathy classification for supervised machine learning algorithms |
| title_sort | diabetic retinopathy classification for supervised machine learning algorithms |
| topic | Diabetic retinopathy classifications Artificial intelligence Datasets |
| url | https://doi.org/10.1186/s40942-021-00352-2 |
| work_keys_str_mv | AT luisfilipenakayama diabeticretinopathyclassificationforsupervisedmachinelearningalgorithms AT lucaszagoribeiro diabeticretinopathyclassificationforsupervisedmachinelearningalgorithms AT marianabatistagoncalves diabeticretinopathyclassificationforsupervisedmachinelearningalgorithms AT danielaferraz diabeticretinopathyclassificationforsupervisedmachinelearningalgorithms AT helennazarethvelosodossantos diabeticretinopathyclassificationforsupervisedmachinelearningalgorithms AT fernandokornmalerbi diabeticretinopathyclassificationforsupervisedmachinelearningalgorithms AT paulohenriquemorales diabeticretinopathyclassificationforsupervisedmachinelearningalgorithms AT mauriciomaia diabeticretinopathyclassificationforsupervisedmachinelearningalgorithms AT caioviniciussaitoregatieri diabeticretinopathyclassificationforsupervisedmachinelearningalgorithms AT rubensbelfortmattos diabeticretinopathyclassificationforsupervisedmachinelearningalgorithms |