Clinician-driven artificial intelligence in ophthalmology: resources enabling democratization.
Journal
Current opinion in ophthalmology
ISSN: 1531-7021
Titre abrégé: Curr Opin Ophthalmol
Pays: United States
ID NLM: 9011108
Informations de publication
Date de publication:
01 Sep 2021
01 Sep 2021
Historique:
pubmed:
16
7
2021
medline:
18
9
2021
entrez:
15
7
2021
Statut:
ppublish
Résumé
This article aims to discuss the current state of resources enabling the democratization of artificial intelligence (AI) in ophthalmology. Open datasets, efficient labeling techniques, code-free automated machine learning (AutoML) and cloud-based platforms for deployment are resources that enable clinicians with scarce resources to drive their own AI projects. Clinicians are the use-case experts who are best suited to drive AI projects tackling patient-relevant outcome measures. Taken together, open datasets, efficient labeling techniques, code-free AutoML and cloud platforms break the barriers for clinician-driven AI. As AI becomes increasingly democratized through such tools, clinicians and patients stand to benefit greatly.
Identifiants
pubmed: 34265784
doi: 10.1097/ICU.0000000000000785
pii: 00055735-202109000-00009
doi:
Types de publication
Journal Article
Review
Langues
eng
Sous-ensembles de citation
IM
Pagination
445-451Subventions
Organisme : Medical Research Council
ID : MR/T000953/1
Pays : United Kingdom
Organisme : Medical Research Council
ID : MR/T019050/1
Pays : United Kingdom
Informations de copyright
Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.
Références
Najafabadi MM, Villanustre F, Khoshgoftaar TM, et al. Deep learning applications and challenges in big data analytics. J Big Data 2015; 2:1–21.
Khan SM, Liu X, Nath S, et al. A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability. Lancet Digit Health 2021; 3:e51–e66.
Organization WH, Others. Draft global strategy on digital health 2020-2024. Geneva: World Health Organization; 2019.
NHS and social care data: off-shoring and the use of public cloud services [Internet]. [cited 2021 Jun 4]. Available from: https://digital.nhs.uk/data-and-information/looking-after-information/data-security-and-information-governance/nhs-and-social-care-data-off-shoring-and-the-use-of-public-cloud-services
Korot E, Guan Z, Ferraz D, et al. Code-free deep learning for multimodality medical image classification. Nat Mach Intell 2021. 1–11.
Faes L, Wagner SK, Fu DJ, et al. Automated deep learning design for medical image classification by health-care professionals with no coding experience: a feasibility study. Lancet Digit Health 2019; 1:e232–e242.
Korot E, Pontikos N, Liu X, et al. Predicting sex from retinal fundus photographs using automated deep learning. Sci Rep 2021; 11:10286.
Altman ER. Big Data and Democratization. IEEE Micro 2014; 34:2–3.
Fahey S. The democratization of big data. J Natl Sec Law Policy 2014; 7:325.
dbGaP Study. [cited 2021 Jun 3]. Available from: https://www.ncbi.nlm.nih.gov/projects/gap/cgi-bin/study.cgi?study_id=phs000001.v3.p1 .
Chua SYL, Thomas D, Allen N, et al. Cohort profile: design and methods in the eye and vision consortium of UK Biobank. BMJ Open 2019; 9:e025077.
Decencière E, Zhang X, Cazuguel G, et al. Feedback on a publicly distributed image database: The Messidor database. Image Anal Stereol 2014; 33:231.
Dataset Search [Internet]. [cited 2021 Jun 3]. Available from: https://datasetsearch.research.google.com/help
Ophthalmology Imaging Datasets [Internet]. [cited 2021 Jun 4]. Available from: https://www.eyedatasets.com/ .
Futoma J, Simons M, Panch T, et al. The myth of generalisability in clinical research and machine learning in healthcare. Lancet Digit Health 2020; 2:e489–e492.
Vollmer S, Mateen BA, Bohner G, et al. Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness. BMJ 2020; 368:l6927.
Ibrahim H, Liu X, Zariffa N, et al. Health data poverty: an assailable barrier to equitable digital healthcare. Lancet Digit Health 2021; 3:e260–e265.
Willemink MJ, Koszek WA, Hardell C, et al. Preparing medical imaging data for machine learning. Radiology 2020; 295:4–15.
Guan MY, Gulshan V, Dai AM, Hinton GE. Who said what: modeling individual labelers improves classification. arXiv 2017.
Langlotz CP, Allen B, Erickson BJ, et al. A roadmap for foundational research on artificial intelligence in medical imaging: from the 2018 NIH/RSNA/ACR/The Academy Workshop. Radiology 2019; 291:781–791.
Rizos G, Schuller BW. Average Jane, where art thou? - recent avenues in efficient machine learning under subjectivity uncertainty. in: information processing and management of uncertainty in knowledge-based systems. 2020; London, UK: Springer International Publishing, p. 42–55.
Mongan J, Moy L, Kahn CE. Checklist for artificial intelligence in medical imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell 2020; 2:e200029.
Krause J, Gulshan V, Rahimy E, et al. Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy. Ophthalmology 2018; 125:1264–1272.
Schaekermann M, Hammel N, Terry M, et al. Remote tool-based adjudication for grading diabetic retinopathy. Transl Vis Sci Technol 2019; 8:40.
Gu L, Zhang X, You S, et al. Semi-supervised learning in medical images through graph-embedded random forest. Front Neuroinform 2020; 14:601829.
Enguehard J, O’Halloran P, Gholipour A. Semi supervised learning with deep embedded clustering for image classification and segmentation. IEEE Access 2019; 7:11093–11104.
Xue Y, Hauskrecht M. Efficient learning of classification models from soft-label information by binning and ranking.pdf. Proc Int Fla AI Res Soc Conf 2017. 164–169.
Bellemo V, Lim ZW, Lim G, et al. Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study. Lancet Digit Health 2019; 1:e35–e44.
Korot E, Wood E, Weiner A, et al. A renaissance of teleophthalmology through artificial intelligence. Eye 2019; 33:861–863.
Hsu J, Phene S, Mitani A, et al. Improving medical annotation quality to decrease labeling burden using stratified noisy cross-validation. arXiv 2020.
Fries JA, Varma P, Chen VS, et al. Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences. Nat Commun 2019; 10:3111.
Sucholutsky I, Schonlau M. ‘Less Than One’-shot learning: learning N classes from M<N samples. arXiv 2020.
Azary H, Abdoos M. A semi-supervised method for tumor segmentation in mammogram images. J Med Signals Sens 2020; 10:12–18.
Nartey OT, Yang G, Wu J, Asare SK. Semi-supervised learning for fine-grained classification with self-training. IEEE Access 2020; 8:2109–2121.
Li M, Zhou Z-H. SETRED: self-training with editing. Adv Knowl Discov Data Mining 2005; 3518:611–621.
Xie Q, Luong M-T, Hovy E, Le QV. Self-training with noisy student improves imagenet classification. 2020 IEEE/CVF Conf Comput Vis Pattern Recognit 2020.
Fazakis N, Kanas VG, Aridas CK, et al. Combination of active learning and semi-supervised learning under a self-training scheme. Entropy 2019; 21:988.
Ouali Y, Hudelot C, Tami M. An overview of deep semi-supervised learning. arXiv 2020.
Zhang Y, An M. An active learning classifier for further reducing diabetic retinopathy screening system cost. Comput Math Methods Med 2016; 2016:4345936.
Ahsan MA, Qayyum A, Qadir J, Razi A. An active learning method for diabetic retinopathy classification with uncertainty quantification. arXiv 2020.
Budd S, Robinson EC, Kainz B. A survey on active learning and human-in-the-loop deep learning for medical image analysis. Med Image Anal 2021; 71:102062.
Requesting data labeling [Internet]. [cited 2021 Jun 4]. Available from: https://cloud.google.com/vertex-ai/docs/datasets/data-labeling-job?hl=fa .
Farley P. Label images faster with Smart Labeler [Internet]. [cited 2021 Jun 4]. Available from: https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/suggested-tags .
Choo J, Liu S. Visual analytics for explainable deep learning. IEEE Comput Graph Appl 2018; 38:84–92.
Ribeiro MT, Singh S, Guestrin C. ‘Why Should I Trust You?’: explaining the predictions of any classifier [Internet]. arXiv 2016.
Vickers AJ, Cronin AM, Elkin EB, Gonen M. Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers. BMC Med Inform Decis Mak 2008; 8:53.
Shah NH, Milstein A, Bagley SC. Making machine learning models clinically useful. JAMA 2019.
Steyerberg EW, Harrell FE Jr. Prediction models need appropriate internal, internal-external, and external validation. J Clin Epidemiol 2016; 69:245–247.
Keane PA, Topol EJ. AI-facilitated healthcare requires education of clinicians. Lancet 2021; 397:1254.
Eyenuk Announces FDA Clearance for EyeArt Autonomous AI System for Diabetic Retinopathy Screening - Eyenuk, Inc. ∼ Artificial Intelligence Eye Screening [Internet]. [cited 2021 Jun 4]. Available from: https://www.eyenuk.com/us-en/articles/diabetic-retinopathy/eyenuk-announces-eyeart-fda-clearance/ .
2018; Office of the Commissioner. FDA permits marketing of artificial intelligence-based device to detect certain diabetes-related eye problems.
Lee AY, Campbell JP, Hwang TS, et al. American academy of ophthalmology. recommendations for standardization of images in ophthalmology. Ophthalmology 2021.
MLCube TM [Internet]. [cited 2021 Jun 4]. Available from: https://mlcommons.org/en/mlcube/ .
TensorFlow Lite [Internet]. [cited 2021 Jun 4]. Available from: https://www.tensorflow.org/lite .
PyTorch Mobile [Internet]. [cited 2021 Jun 4]. Available from: https://pytorch.org/mobile/home/ .
CheXphoto: A Dataset of Naturally and Synthetically Perturbed Chest X-Rays and Competition for Automated X-Ray Interpretation [Internet]. [cited 2021 Jun 4]. Available from: https://stanfordmlgroup.github.io/competitions/chexphoto/ .
Rajpurkar P, Joshi A, Pareek A, et al. CheXphotogenic: generalization of deep learning models for chest X-ray interpretation to photos of chest X-rays. arXiv 2020.
Beede E, Baylor E, Hersch F, et al. A human-centered evaluation of a deep learning system deployed in clinics for the detection of diabetic retinopathy. In: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. New York, NY, USA: Association for Computing Machinery; 2020. p. 1-12. (CHI ’20).
Citizen Data Science Augments Data Discovery and Simplifies Data Science [Internet]. [cited 2021 Jun 4]. Available from: https://www.gartner.com/en/documents/3534848 .