Otoscopic diagnosis using computer vision: An automated machine learning approach
- PMID: 31532858
- DOI: 10.1002/lary.28292
Otoscopic diagnosis using computer vision: An automated machine learning approach
Abstract
Objective: Access to otolaryngology is limited by lengthy wait lists and lack of specialists, especially in rural and remote areas. The objective of this study was to use an automated machine learning approach to build a computer vision algorithm for otoscopic diagnosis capable of greater accuracy than trained physicians. This algorithm could be used by primary care providers to facilitate timely referral, triage, and effective treatment.
Methods: Otoscopic images were obtained from Google Images (Google Inc., Mountain View, CA), from open access repositories, and within otolaryngology clinics associated with our institution. After preprocessing, 1,366 unique images were uploaded to the Google Cloud Vision AutoML platform (Google Inc.) and annotated with one or more of 14 otologic diagnoses. A consensus set of labels for each otoscopic image was attained, and a multilabel classifier architecture algorithm was trained. The performance of the algorithm on an 89-image test set was compared to the performance of physicians from pediatrics, emergency medicine, otolaryngology, and family medicine.
Results: For all diagnoses combined, the average precision (positive predictive value) of the algorithm was 90.9%, and the average recall (sensitivity) was 86.1%. The algorithm made 79 correct diagnoses with an accuracy of 88.7%. The average physician accuracy was 58.9%.
Conclusion: We have created a computer vision algorithm using automated machine learning that on average rivals the accuracy of the physicians we tested. Fourteen different otologic diagnoses were analyzed. The field of medicine will be changed dramatically by artificial intelligence within the next few decades, and physicians of all specialties must be prepared to guide that process.
Level of evidence: NA Laryngoscope, 130:1408-1413, 2020.
Keywords: Computer vision; artificial intelligence; diagnosis; machine learning; otoscopy.
© 2019 The American Laryngological, Rhinological and Otological Society, Inc.
Similar articles
-
Development of a Novel Scar Screening System with Machine Learning.Plast Reconstr Surg. 2022 Aug 1;150(2):465e-472e. doi: 10.1097/PRS.0000000000009312. Epub 2022 Jul 27. Plast Reconstr Surg. 2022. PMID: 35687417
-
An Artificial Intelligence Computer-vision Algorithm to Triage Otoscopic Images From Australian Aboriginal and Torres Strait Islander Children.Otol Neurotol. 2022 Apr 1;43(4):481-488. doi: 10.1097/MAO.0000000000003484. Otol Neurotol. 2022. PMID: 35239622
-
Building an Otoscopic screening prototype tool using deep learning.J Otolaryngol Head Neck Surg. 2019 Nov 26;48(1):66. doi: 10.1186/s40463-019-0389-9. J Otolaryngol Head Neck Surg. 2019. PMID: 31771647 Free PMC article.
-
Artificial intelligence and tele-otoscopy: A window into the future of pediatric otology.Int J Pediatr Otorhinolaryngol. 2022 Sep;160:111229. doi: 10.1016/j.ijporl.2022.111229. Epub 2022 Jul 6. Int J Pediatr Otorhinolaryngol. 2022. PMID: 35816971 Review.
-
A review of image analysis and machine learning techniques for automated cervical cancer screening from pap-smear images.Comput Methods Programs Biomed. 2018 Oct;164:15-22. doi: 10.1016/j.cmpb.2018.05.034. Epub 2018 Jun 26. Comput Methods Programs Biomed. 2018. PMID: 30195423 Review.
Cited by
-
Development and Validation of an Automated Classifier to Diagnose Acute Otitis Media in Children.JAMA Pediatr. 2024 Apr 1;178(4):401-407. doi: 10.1001/jamapediatrics.2024.0011. JAMA Pediatr. 2024. PMID: 38436941
-
Label-Free Optical Technologies for Middle-Ear Diseases.Bioengineering (Basel). 2024 Jan 23;11(2):104. doi: 10.3390/bioengineering11020104. Bioengineering (Basel). 2024. PMID: 38391590 Free PMC article. Review.
-
Enhancing paranasal sinus disease detection with AutoML: efficient AI development and evaluation via magnetic resonance imaging.Eur Arch Otorhinolaryngol. 2024 Apr;281(4):2153-2158. doi: 10.1007/s00405-023-08424-9. Epub 2024 Jan 10. Eur Arch Otorhinolaryngol. 2024. PMID: 38197934 Free PMC article.
-
Insight into Automatic Image Diagnosis of Ear Conditions Based on Optimized Deep Learning Approach.Ann Biomed Eng. 2024 Apr;52(4):865-876. doi: 10.1007/s10439-023-03422-8. Epub 2023 Dec 14. Ann Biomed Eng. 2024. PMID: 38097895 Free PMC article.
-
Deep Learning Techniques and Imaging in Otorhinolaryngology-A State-of-the-Art Review.J Clin Med. 2023 Nov 8;12(22):6973. doi: 10.3390/jcm12226973. J Clin Med. 2023. PMID: 38002588 Free PMC article. Review.
References
BIBLIOGRAPHY
-
- Buchanan CM, Pothier DD. Recognition of paediatric otopathology by General Practitioners. Int J Pediatr Otorhinolaryngol 2008;72:669-673.
-
- Asher E, Leibovitz E, Press J, Greenberg D, Bilenko N, Reuveni H. Accuracy of acute otitis media diagnosis in community and hospital settings. Acta Paediatr 2005;94:423-428.
-
- Legros JM, Hitoto H, Garnier F, Dagorne C, Parot-Schinkel E, Fanello S. Clinical qualitative evaluation of the diagnosis of acute otitis media in general practice. Int J Pediatr Otorhinolaryngol 2008;72:23-30.
-
- Pichichero ME, Poole MD. Comparison of performance by otolaryngologists, pediatricians, and general practitioners on an otoendoscopic diagnostic video examination. Int J Pediatr Otorhinolaryngol 2005;69:361-366.
-
- Pichichero ME, Poole MD. Assessing diagnostic accuracy and tympanocentesis skills in the management of otitis media. Arch Pediatr Adolesc Med 2001;155:1137-1142.
MeSH terms
LinkOut - more resources
Full Text Sources
Medical
Research Materials