Artificial Intelligence and Corneal Diseases

Linda Kang; Dena Ballouz; Maria A. Woodward

Curr Opin Ophthalmol. 2022;33(5):407-417.

Abstract and Introduction

Abstract

Purpose of Review: Artificial intelligence has advanced rapidly in recent years and has provided powerful tools to aid with the diagnosis, management, and treatment of ophthalmic diseases. This article aims to review the most current clinical artificial intelligence applications in anterior segment diseases, with an emphasis on microbial keratitis, keratoconus, dry eye syndrome, and Fuchs endothelial dystrophy.

Recent Findings: Most current artificial intelligence approaches have focused on developing deep learning algorithms based on various imaging modalities. Algorithms have been developed to detect and differentiate microbial keratitis classes and quantify microbial keratitis features. Artificial intelligence may aid with early detection and staging of keratoconus. Many advances have been made to detect, segment, and quantify features of dry eye syndrome and Fuchs. There is significant variability in the reporting of methodology, patient population, and outcome metrics.

Summary: Artificial intelligence shows great promise in detecting, diagnosing, grading, and measuring diseases. There is a need for standardization of reporting to improve the transparency, validity, and comparability of algorithms.

Introduction

Advances in artificial intelligence have generated novel insights and are transforming screening, diagnosis, and treatment in various medical fields. Artificial intelligence in ophthalmology has expanded significantly in the last decade. The eye community is well positioned to create artificial intelligence strategies given the broad use of imaging tools in clinical practice and hence the availability of codified data from imaging to numeric clinical parameters (e.g., visual acuity, intraocular pressure, etc.). Image-based ophthalmic artificial intelligence began by focusing on eye diseases involving the posterior segment, such as macular degeneration, diabetic retinopathy, and glaucoma, due to the population prevalence and use of ophthalmic imaging in routine clinical practice.^[1–4] This led to advances in medicine – the first autonomous artificial intelligence-based diagnostic tool approved by the Food and Drug Administration was for detecting diabetic retinopathy.^[5]

These advances have inspired artificial intelligence development to address diagnostic and management concerns for diseases of the anterior segment. Artificial intelligence algorithms for anterior segment conditions have been reviewed in the past.^[6–14] This review article focuses on advancements in the past 18 months for the use of artificial intelligence for corneal diseases.

1 2 3

Next Section

Abstract and Introduction
Methods
Conclusion
References
Sidebar

Table 1. Summary of reviewed articles
References	AI method	Study population	Outcome measure	Imaging modality	Number of images	Number of patients	Demographics reported	Algorithm results
Microbial keratitis
Li et al. [15]	CNN	MK, controls	MK detection	SLP, external photography	13 557	7988	Complete	AUC 0.998, Sens 98%, Spec 98%^a
Tiwari et al. [16]	CNN	MK, controls	MK detection	External Photography	1445	1445	Partial	Internal set (India): AUC 0.973, Sens 94%, Spec 84% External set (US): AUC 0.947, Sens 78%, Spec 91%
Lv et al. [26]	CNN	FK, controls	FK detection	Confocal	2623	NR	NR	AUC 0.988, Acc 96%, Sens 92%, Spec 98%
Xu et al. [28]	CNN	BK, FK	FK detection	Confocal	1089	35	NR	AUROC 0.983, Acc 97%, Sens 94%, Spec 98%
Liu et al. [27]	CNN	FK, controls	FK detection	Confocal	1213	NR	NR	Acc 99.9%
Xu et al. [17]	CNN	MK, controls	MK detectionDifferentiate MK subtypes	SLP	2284	867	NR	Acc 80%, 53%, 83%, and 93% for overall, BK, FK, and HSK
Wang et al. [18]	CNN	MK, controls	MK detectionDifferentiate MK subtypes	SLP	5673	3320	Complete	AUC 0.959
Koyama et al. [20]	CNN	MK	Differentiate MK subtypes	SLP	4306	362	Complete	Acc 88%
Hung et al. [25]	CNN	BK, FK	Differentiate MK subtypes	SLP	1330	580	Complete	AUC 0.85, Sens range 26–66%, Spec range 80–96%, BK Acc range 80–96%, FK Acc range 26–66%
Redd et al. [21]	CNN	BK, FK	Differentiate MK subtypes	External photography	980	980	Complete	AUC 0.83
Ghosh et al. [22]	CNN	BK, FK	Differentiate MK subtypes	SLP	2167	194	NR	Sens 77%, F1 score 83%
Kuo et al. [24]	CNN	MK	Differentiate FK from other MK	SLP	288	288	NR	AUC 0.65
Kuo et al. [23]	CNN	MK	Differentiate BK from other MK	External photography	1512	1512	NR	Sens 74%, Spec 64%
Loo et al. [30]	CNN	MK	MK feature quantification	SLP	266	133	NR	DSC range 0.62–0.95
Loo et al. [31]	CNN	MK	Visual Acuity	SLP	152	76	Complete	r = 0.84
KCN
Kuo et al. [37]	CNN	KCN, ffKCN, controls	KCN detection	Corneal topography	354	206	NR	AUROC 0.995, Acc 96%, Sens 94%, Spec 97%
Cao et al. [39]	ML	ffKCN, controls	KCN detection	Corneal tomography	NR	88	Partial	AUC 0.96, Acc 87%, Sens 88%, Spec 85%
Castro-Luna et al. [38]	ML	ffKCN, controls	KCN detection	Corneal tomography, tonometry	NR	81	Partial	Acc 89%, Sens 86%, Spec 93%
Al-Timemy et al. [32]	Hybrid DL – CNN	KCN, controls	KCN detection	Corneal tomography	4844	365	Partial	Normal vs. KCN: AUC 0.99, Acc 92% Normal vs. KCN vs. suspected KCN: AUC 0.81, Acc 69%
Zéboulon et al. [35]	Hybrid ML – CNN	KCN, controls	KCN detection	Corneal topography	3000	3000	Complete	Overall Acc: 99.3% Detection of KCN: Sens 100%, Spec 100%
Aatila et al. [40]	ML	KCN, ffKCN, controls	KCN detection, staging	AS-OCT	12 242	NR	NR	Diagnostic Acc 98% Staging Acc 95%
Ghaderi et al. [42]	CNN	KCN, controls	KCN detection, staging	Corneal tomography	NR	450 eyes	Partial	Detection: Acc 98%, Sens 99%, Spec 96% Staging: Acc 98%, Sens 99%, Spec 99%
Feng et al. [34]	CNN	KCN, ffKCN, controls	KCN detection, staging	Corneal tomography	854	854	Complete	Acc 95%
Abdelmotaal et al. [33]	CNN	KCN, ffKCN, controls	KCN detection, staging	Corneal tomography	3218	1619	Partial	Normal: Acc 99%, Sens 99%, Spec 99% Subclinical KCN: Acc 99%, Sens 99%, Spec 99% KCN: Acc 100%, Sens 100%, Spec 100%
Shi et al. [36]	ML	KCN, ffKCN, controls	KCN detection, staging	Corneal tomography, OCT	NR	121 eyes	NR	Normal vs. ffKCN: AUC 0.93, Sens 99%, Spec 95% Normal vs. KCN: AUC 1.0, Sens 100%, Spec 100%
Kamiya et al. [43]	CNN	KCN, controls	KCN detection, staging	Corneal topography	519	519 eyes	Partial	Detection: Acc 97%, Sens 99%, Spec 94% Classification: AUC 0.888–0.997, Acc 79%
Chen et al. [44]	CNN	KCN, controls	KCN detection, staging	Corneal tomography	1926	1836	NR	AUC range 0.82–0.91, Acc rage 85 - 99%, Sens range 69–99%, Spec range 80–94%
Malyugin et al. [41]	ML	KCN, controls	KCN detection, staging	Corneal tomography	NR	852 eyes	NR	Overall AUC: 0.97 AUC by KCN stage: Normal 0.98, preclinical KCN 0.95, Stage 1 0.96, Stage 2 0.97, Stage 3 0.97, Stage 4 1.0
Kamiya et al. [45]	DL	KCN	KCN progression	AS-OCT	NR	218	NR	Acc 79%
Kato et al. [46]	CNN	KCN	KCN progression	Corneal tomography	274	158	Complete	AUC 0.81, Sens 78%, Spec 70%
Yousefi et al. [47]	ML	KCN, controls	KCN progression	AS-OCT	12 242	3162	Complete	Normalized likelihood of need for keratoplasty for clusters 1–5: 2%, 1%, 33%, 33%, 31%
Dry eye syndrome
Chase et al. [48]	CNN	DES, control	DES detection	AS-OCT	27 180	91	Partial	Acc 85%, Sens 86%, Spec 82%
Su et al. [50]	CNN	SPK, control	SPK detection, grading	SLP	10 468^b	101	NR	SPK detection: Acc 97% Grading threshold: Sens 97%, Spec 79%
Qu et al. [51]	CNN	SPK, control	SPK detection, grading	SLP	763	NR	NR	AUROC 0.940, Acc 77%
Stegmann et al. [52]	CNN	control	Tear meniscus segmentation	Custom OCT	6658	10	Complete	Sens 96%, Spec 99.9%
Deng et al. [53]	CNN	NR	Tear meniscus segmentation, quantification	Corneal topography	485	217	Complete	Segmentation: Sens 90%, F1 score 90% Quantification: r = 0.97 (P < 0.001)
Wei et al. [54]	CNN	NR	Corneal nerve fiber segmentation	Confocal	691	104	NR	AUC 0.96, Sens 96%, Spec 75%
Maruoka et al. [49]	CNN	MGD, control	MGD detection	Confocal	221	221	Complete	Single model: AUC 0.966, Sens 94%, Spec 82% Ensemble model: AUC 0.981, Sens 92%, Spec 99%
Yeh et al. [56]	ML	MGD, control	MGD quantification, grading	Corneal topography	706	576	Complete	Acc 81%
Wang et al. 2021 [57]	DL	NR	MGD segmentation	Corneal topography	1443	475	Complete	Segmenting MG (upper, lower): Sens 54%, Sens 74% Identifying ghost glands: Sens 84%, Spec 72%
Setu et al. [58]	CNN	NR	MGD segmentation	Corneal topography	728	NR	NR	AUROC 0.96, Sens 81%, F1 score 84%
Khan et al. [60]	CGAN	MGD	MGD segmentation	Corneal topography	112	112	Partial	MG segmentation: F1 score 83% MG dropout grading: r = 0.962, P < 0.001
Prabhu et al. [59]	CNN	MGD, control	MGD segmentation, quantification	Corneal Topography, Prototype handheld camera	800	NR	NR	P values >0.005 for all metrics between CNN and manual
FED
Eleiwa et al. [61]	CNN	FED, control	FED detection	AS-OCT	18 720	81	Complete	Early-stage FED: AUC 0.997, Sens 91%, Spec 97% Late-stage FED: AUC 0.974, Sens up to 100%, Spec 92% Healthy vs. all FED: AUC 0.998, Sens 99%, Spec 98%
Zéboulon et al. [62]	CNN	Edema, control	Edema detection	AS-OCT	806	110	Partial	AUROC 0.994, Acc 99%, Sens 96%, Spec 100%
Shilpashree et al. [63]	CNN	FED, control	FED segmentation, quantification	Specular microscopy	2246	130	Complete	AUROC 0.967, Acc of 88%, F1 score 82%
Vigueras-Guillén et al. [64]	CNN	FED, control	FED segmentation, quantification	Specular microscopy	783	141	Partial	CNN: able to estimate parameters in 98% of images; percentage error 2.5–5.7% Specular Microscopy: able to estimate parameters in in 31–72% of images; percentage error 7.5–18.3%
Multiple cornea conditions
Elsawy et al. [65]	DL	FED, KCN, controls	Multidisease diagnosis	AS-OCT	16 721	258	NR	FED: AUC 1.0, Sens 94%, Spec 100% KCN: AUC 0.95, Sens 94%, Spec 94% Healthy: AUC 0.93, Sens 91%, Spec 95%
Elsawy et al. [66]	CNN	FED, KCN, DES, controls	Multidisease diagnosis	AS-OCT	158 220	478	Complete	FED: AUC 1.0, F1 score 100% KCN: AUC 0.99, F1 score 98% DES: AUC 0.99, F1 score 90% Healthy: AUC 0.98, F1 score 93%
Gu et al. [67]	DL	MK, noninfectious keratitis, corneal dystrophy, surface neoplasm, cataract, controls	Multidisease diagnosis	SLP	5835	≥510^c	NR	Retrospective data set: AUC range 0.903–0.951 Prospective data set: AUC >0.91
Li et al. [68]	DL	Keratitis; pterygium; conjunctival hyperemia, hemorrhage, edema; cataract	Multidisease diagnosis	SLP	1772	NR	Partial	Acc range 79–99%, Sens range 53–99%, Spec range 85–99%

Acc, accuracy; AI, artificial intelligence; AK, acanthamoeba keratitis; ANN, artificial neural network; AS-OCT, anterior segment optical coherence tomography; AUC, area under the curve; AUROC, area under the receiver operating characteristic curve; BK, bacterial keratitis; CGAN, conditional generative adversarial network; CNN, convolutional neural network; DES, dry eye syndrome; DL, deep learning; DSC, dice similarity coefficient; ffKCN, forme fruste keratoconus; FK, fungal keratitis; HSV, herpes simplex virus keratitis; KCN, keratoconus; MGD meibomian glad dysfunction; MK, microbial keratitis; ML, machine learning; NR, not reported; r, Pearson correlation coefficient; Sens, sensitivity; SLP, slit lamp photography; Spec, specificity; SPK, superficial punctate keratitis; UHR-OCT, ultra-high-resolution optical coherence tomography; VK, viral keratitis.
^aMultiple algorithms testing different outcome measures and in different datasets.
^bNumber of original images, study augmented images to increase number for final data set.
^cNumber of patients partially reported.

processing....

Artificial Intelligence and Corneal Diseases

Abstract and Introduction

Abstract

Introduction

Tables

References

Authors and Disclosures

Authors and Disclosures

Sidebar

Sidebar

Key Points

Email This

Feedback