AI-Based Decision-Support System for Diagnosing Acanthamoeba Keratitis Using In Vivo Confocal Microscopy Images

Overview

Journal Transl Vis Sci Technol

Specialties Biomedical Engineering
Ophthalmology

Date 2023 Nov 27

PMID 38010282

Authors

Alisa Lincke

Jenny Roth

Antonio Filipe Macedo

Patrick Bergman

Welf Lowe

Neil S Lagali

Affiliations

Soon will be listed here.

Abstract

Purpose: In vivo confocal microscopy (IVCM) of the cornea is a valuable tool for clinical assessment of the cornea but does not provide stand-alone diagnostic support. The aim of this work was to develop an artificial intelligence (AI)-based decision-support system (DSS) for automated diagnosis of Acanthamoeba keratitis (AK) using IVCM images.

Methods: The automated workflow for the AI-based DSS was defined and implemented using deep learning models, image processing techniques, rule-based decisions, and valuable input from domain experts. The models were evaluated with 5-fold-cross validation on a dataset of 85 patients (47,734 IVCM images from healthy, AK, and other disease cases) collected at a single eye clinic in Sweden. The developed DSS was validated on an additional 26 patients (21,236 images).

Results: Overall, the DSS uses as input raw unprocessed IVCM image data, successfully separates artefacts from true images (93% accuracy), then classifies the remaining images by their corneal layer (90% accuracy). The DSS subsequently predicts if the cornea is healthy or diseased (95% model accuracy). In disease cases, the DSS detects images with AK signs with 84% accuracy, and further localizes the regions of diagnostic value with 76.5% accuracy.

Conclusions: The proposed AI-based DSS can automatically and accurately preprocess IVCM images (separating artefacts and sorting images into corneal layers) which decreases screening time. The accuracy of AK detection using raw IVCM images must be further explored and improved.

Translational Relevance: The proposed automated DSS for experienced specialists assists in diagnosing AK using IVCM images.

Citing Articles

Use of in vivo confocal microscopy in suspected Acanthamoeba keratitis: a 12-year real-world data study at a Swedish regional referral center.

Toba B, Lagali N J Ophthalmic Inflamm Infect. 2024; 14(1):43.

PMID: 39254750 PMC: 11387576. DOI: 10.1186/s12348-024-00424-y.

Artificial-Intelligence-Enhanced Analysis of In Vivo Confocal Microscopy in Corneal Diseases: A Review.

Kryszan K, Wylegala A, Kijonka M, Potrawa P, Walasz M, Wylegala E Diagnostics (Basel). 2024; 14(7).

PMID: 38611606 PMC: 11011861. DOI: 10.3390/diagnostics14070694.

References

Ghosh A, Thammasudjarit R, Jongkhajornpong P, Attia J, Thakkinstian A . Deep Learning for Discrimination Between Fungal Keratitis and Bacterial Keratitis: DeepKeratitis. Cornea. 2021; 41(5):616-622. PMC: 8969839. DOI: 10.1097/ICO.0000000000002830. View

Tang N, Huang G, Lei D, Jiang L, Chen Q, He W . A Hybrid System for Automatic Identification of Corneal Layers on In Vivo Confocal Microscopy Images. Transl Vis Sci Technol. 2023; 12(4):8. PMC: 10108728. DOI: 10.1167/tvst.12.4.8. View

Trevethan R . Sensitivity, Specificity, and Predictive Values: Foundations, Pliabilities, and Pitfalls in Research and Practice. Front Public Health. 2017; 5:307. PMC: 5701930. DOI: 10.3389/fpubh.2017.00307. View

Won Y, Lee H, Kim Y, Han G, Chung T, Ro Y . Deep learning-based classification system of bacterial keratitis and fungal keratitis using anterior segment images. Front Med (Lausanne). 2023; 10:1162124. PMC: 10233039. DOI: 10.3389/fmed.2023.1162124. View

Cruzat A, Qazi Y, Hamrah P . In Vivo Confocal Microscopy of Corneal Nerves in Health and Disease. Ocul Surf. 2016; 15(1):15-47. PMC: 5512932. DOI: 10.1016/j.jtos.2016.09.004. View

Cabrera-Aguas M, Khoo P, Watson S . Infectious keratitis: A review. Clin Exp Ophthalmol. 2022; 50(5):543-562. PMC: 9542356. DOI: 10.1111/ceo.14113. View

Batawi H, Shalabi N, Joag M, Koru-Sengul T, Rodriguez J, Green P . Sub-basal Corneal Nerve Plexus Analysis Using a New Software Technology. Eye Contact Lens. 2017; 44 Suppl 1:S199-S205. PMC: 5373086. DOI: 10.1097/ICL.0000000000000375. View

Musa F, Tailor R, Gao A, Hutley E, Rauz S, Scott R . Contact lens-related microbial keratitis in deployed British military personnel. Br J Ophthalmol. 2010; 94(8):988-93. DOI: 10.1136/bjo.2009.161430. View

Recchioni A, Barua A, Dominguez-Vicent A . Enhancing Clinical Decision-Making in Complex Corneal Disorders: The Role of In-Vivo Confocal Microscopy. Life (Basel). 2023; 13(3). PMC: 10059758. DOI: 10.3390/life13030679. View

10.

Jedzierowska M, Koprowski R, Wilczynski S, Krysik K . A new method for detecting the outer corneal contour in images from an ultra-fast Scheimpflug camera. Biomed Eng Online. 2019; 18(1):115. PMC: 6888987. DOI: 10.1186/s12938-019-0735-1. View

11.

Xu F, Jiang L, He W, Huang G, Hong Y, Tang F . The Clinical Value of Explainable Deep Learning for Diagnosing Fungal Keratitis Using Confocal Microscopy Images. Front Med (Lausanne). 2021; 8:797616. PMC: 8712475. DOI: 10.3389/fmed.2021.797616. View

12.

Li S, Bian J, Wang Y, Wang S, Wang X, Shi W . Clinical features and serial changes of Acanthamoeba keratitis: an in vivo confocal microscopy study. Eye (Lond). 2019; 34(2):327-334. PMC: 7002551. DOI: 10.1038/s41433-019-0482-3. View

13.

De Craene S, Knoeri J, Georgeon C, Kestelyn P, Borderie V . Assessment of Confocal Microscopy for the Diagnosis of Polymerase Chain Reaction-Positive Acanthamoeba Keratitis: A Case-Control Study. Ophthalmology. 2017; 125(2):161-168. DOI: 10.1016/j.ophtha.2017.08.037. View

14.

Lorenzo-Morales J, Khan N, Walochnik J . An update on Acanthamoeba keratitis: diagnosis, pathogenesis and treatment. Parasite. 2015; 22:10. PMC: 4330640. DOI: 10.1051/parasite/2015010. View

15.

Essalat M, Abolhosseini M, Le T, Moshtaghion S, Kanavi M . Interpretable deep learning for diagnosis of fungal and acanthamoeba keratitis using in vivo confocal microscopy images. Sci Rep. 2023; 13(1):8953. PMC: 10238502. DOI: 10.1038/s41598-023-35085-9. View

16.

Lv J, Zhang K, Chen Q, Chen Q, Huang W, Cui L . Deep learning-based automated diagnosis of fungal keratitis with confocal microscopy images. Ann Transl Med. 2020; 8(11):706. PMC: 7327373. DOI: 10.21037/atm.2020.03.134. View

17.

Barsha N, Rahman A, Mahdy M . Automated detection and grading of Invasive Ductal Carcinoma breast cancer using ensemble of deep learning models. Comput Biol Med. 2021; 139:104931. DOI: 10.1016/j.compbiomed.2021.104931. View

18.

Zhang Z, Wang H, Wang S, Wei Z, Zhang Y, Wang Z . Deep learning-based classification of infectious keratitis on slit-lamp images. Ther Adv Chronic Dis. 2022; 13:20406223221136071. PMC: 9666706. DOI: 10.1177/20406223221136071. View