1
|
Domalpally A, Slater R, Barrett N, Voland R, Balaji R, Heathcote J, Channa R, Blodi B. Implementation of a Large-Scale Image Curation Workflow Using Deep Learning Framework. OPHTHALMOLOGY SCIENCE 2022; 2:100198. [PMID: 36531570 PMCID: PMC9754974 DOI: 10.1016/j.xops.2022.100198] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/20/2022] [Revised: 06/09/2022] [Accepted: 07/07/2022] [Indexed: 06/17/2023]
Abstract
PURPOSE The curation of images using human resources is time intensive but an essential step for developing artificial intelligence (AI) algorithms. Our goal was to develop and implement an AI algorithm for image curation in a high-volume setting. We also explored AI tools that will assist in deploying a tiered approach, in which the AI model labels images and flags potential mislabels for human review. DESIGN Implementation of an AI algorithm. PARTICIPANTS Seven-field stereoscopic images from multiple clinical trials. METHODS The 7-field stereoscopic image protocol includes 7 pairs of images from various parts of the central retina along with images of the anterior part of the eye. All images were labeled for field number by reading center graders. The model output included classification of the retinal images into 8 field numbers. Probability scores (0-1) were generated to identify misclassified images, with 1 indicating a high probability of a correct label. MAIN OUTCOME MEASURES Agreement of AI prediction with grader classification of field number and the use of probability scores to identify mislabeled images. RESULTS The AI model was trained and validated on 17 529 images and tested on 3004 images. The pooled agreement of field numbers between grader classification and the AI model was 88.3% (kappa, 0.87). The pooled mean probability score was 0.97 (standard deviation [SD], 0.08) for images for which the graders agreed with the AI-generated labels and 0.77 (SD, 0.19) for images for which the graders disagreed with the AI-generated labels (P < 0.0001). Using receiver operating characteristic curves, a probability score of 0.99 was identified as a cutoff for distinguishing mislabeled images. A tiered workflow using a probability score of < 0.99 as a cutoff would include 27.6% of the 3004 images for human review and reduce the error rate from 11.7% to 1.5%. CONCLUSIONS The implementation of AI algorithms requires measures in addition to model validation. Tools to flag potential errors in the labels generated by AI models will reduce inaccuracies, increase trust in the system, and provide data for continuous model development.
Collapse
Affiliation(s)
- Amitha Domalpally
- A-EYE Unit, Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, Wisconsin
- Wisconsin Reading Center, Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, Wisconsin
| | - Robert Slater
- A-EYE Unit, Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, Wisconsin
| | - Nancy Barrett
- Wisconsin Reading Center, Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, Wisconsin
| | - Rick Voland
- Wisconsin Reading Center, Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, Wisconsin
| | - Rohit Balaji
- Wisconsin Reading Center, Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, Wisconsin
| | - Jennifer Heathcote
- Wisconsin Reading Center, Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, Wisconsin
| | - Roomasa Channa
- A-EYE Unit, Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, Wisconsin
| | - Barbara Blodi
- Wisconsin Reading Center, Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, Wisconsin
| |
Collapse
|
2
|
Nakayama LF, Ribeiro LZ, Gonçalves MB, Ferraz DA, Dos Santos HNV, Malerbi FK, Morales PH, Maia M, Regatieri CVS, Mattos RB. Diabetic retinopathy classification for supervised machine learning algorithms. Int J Retina Vitreous 2022; 8:1. [PMID: 34980281 PMCID: PMC8722080 DOI: 10.1186/s40942-021-00352-2] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Accepted: 12/17/2021] [Indexed: 11/10/2022] Open
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.
Collapse
Affiliation(s)
- Luis Filipe Nakayama
- Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil.
| | - Lucas Zago Ribeiro
- Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil
| | - Mariana Batista Gonçalves
- 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
| | - Daniel A Ferraz
- 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
| | - Helen Nazareth Veloso Dos Santos
- Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil
| | - Fernando Korn Malerbi
- Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil
| | - Paulo Henrique Morales
- 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
| | - Mauricio Maia
- Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil
| | - Caio Vinicius Saito Regatieri
- Physician, Department of Ophthalmology, Universidade Federal de São Paulo - EPM, Botucatu Street, 821, Vila Clementino, São Paulo, SP, 04023-062, Brazil
| | - Rubens Belfort Mattos
- 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
| |
Collapse
|
3
|
Faber H, Berens P, Rohrbach JM. [Ocular changes as a diagnostic tool for malaria]. Ophthalmologe 2021; 119:693-698. [PMID: 34940911 DOI: 10.1007/s00347-021-01554-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Revised: 10/29/2021] [Accepted: 11/26/2021] [Indexed: 11/28/2022]
Abstract
BACKGROUND According to the WHO Malaria Report 2019 a total of 229 million people fall ill with malaria each year and two thirds of deaths involve children under 5 years of age. AIM To review the fundus changes in the context of malaria and the importance of ophthalmoscopy in the diagnosis. MATERIAL AND METHODS Summary of changes in cerebral malaria visible on fundus examination, possible underlying pathomechanisms and the value of ophthalmoscopy in practice. RESULTS Retinal findings in malaria include white or gray staining of the retina (retinal whitening), color change of retinal vessels (orange or white staining), hemorrhages often with a white center, such as Roth's spot and papilledema. DISCUSSION The retinal changes in malaria are specific and may help to differentiate malaria from other causes of coma and fever. Smartphone-based fundus photography and artificial intelligence could support malaria diagnostics particularly in resource-poor regions.
Collapse
Affiliation(s)
- Hanna Faber
- Universitäts-Augenklinik Tübingen, Universitätsklinikum Tübingen, Tübingen, Deutschland. .,Department für Augenheilkunde, Universitätsklinikum Tübingen, Tübingen, Deutschland, Elfriede-Aulhorn-Str. 7, 72076.
| | - Philipp Berens
- Department für Augenheilkunde, Universitätsklinikum Tübingen, Tübingen, Deutschland, Elfriede-Aulhorn-Str. 7, 72076.,Tübingen AI Center, Tübingen, Deutschland
| | - Jens Martin Rohrbach
- Universitäts-Augenklinik Tübingen, Universitätsklinikum Tübingen, Tübingen, Deutschland
| |
Collapse
|