Figure - available from: Scientific Reports
This content is subject to copyright. Terms and conditions apply.
Representative images of each causative pathogens with 100% probability scores. Each pathogen probability score for single image was calculated using softmax with Ring loss in InceptionResNetV2 architecture (Fig. 1c) and is shown as confidence. Acanthamoeba image with high confidence shows ring filtrate which is located in the center of the cornea while unaffected corneal lesion is relatively clear and without edema. Image of bacterial keratitis with high confidence shows dense infiltrate with intense corneal edema surrounding the lesion. Fungal image with high confidence shows feathery infiltrate with satellite lesions while surrounding lesion are unaffected. HSV image with high confidence shows marginal ulcer with epithelial defect. ‘bac’, ‘aca’, ‘fun’, and ‘her’ represent bacteria, acanthamoeba, fungi, and herpes simplex virus (HSV), respectively.
Source publication
Corneal opacities are important causes of blindness, and their major etiology is infectious keratitis. Slit-lamp examinations are commonly used to determine the causative pathogen; however, their diagnostic accuracy is low even for experienced ophthalmologists. To characterize the “face” of an infected cornea, we have adapted a deep learning archit...
Citations
... Распространенность и многообразие патологий глазной поверхности, минимальные клинические изменения в начальных стади-ях ряда заболеваний, индивидуальные анатомические особенности капиллярной сети предъявляют высокие требования к квалификации врача-офтальмолога, проводящего осмотр. В последние годы развивается новое направление диагностики, связанное с компьютерной обработкой цифровых снимков глаза, полученных с помощью специализированного офтальмологического оборудования (цифровых фотощелевых ламп), основанной на методах машинного обучения [13][14][15][16][17]. ...
Justification and purpose of the study . Changes in the vessels of the ocular surface are often associated with the presence of various systemic or ocular diseases. Segmentation of the vessels of the ocular surface using artificial intelligence (AI) tools is highly relevant in terms of improving the quality of early diagnosis of pathology. Purpose: to develop a model of segmentation of the capillaries of the ocular surface based on images from an ophthalmic slit lamp using AI tools using Python.
Materials and methods . The study used a dataset (700 eyes), which is publicly available on the Internet and includes photos from an ophthalmological slit lamp, marked up manually. With the help of the augmentation method, this set for research has been increased several times. The system of segmentation of the capillaries of the eye in the images from the ophthalmological slit lamp is based on the trained neural network Unet.
Results . The main result of the study is the development of an algorithm for automatic segmentation of eye capillaries in images from an ophthalmic slit lamp. The metric reached 85% during the training of the neural network model.
Conclusion . The high efficiency and potential of all methods in the construction of an automatic segmentation system of the capillaries of the ocular surface in the images within the framework of the developed in the Helmholtz National Medical Research Center of Eye Diseases automated system of medical decision-making. In the future, this service can be used to improve the effectiveness of early diagnosis and monitoring of treatment of eye diseases in conditions of reduced availability of primary ophthalmological care in part of the territories of the Russian Federation, including at the pre-medical stage.
... We previously reported that the micro-organism causing infectious keratitis was identi ed in only 72% cases using culture tests or microscopy [6]. Even with the latest arti cial intelligence (AI) technology, the diagnosis of infectious keratitis is limited to differentiating between bacteria, fungi, herpes, and amoebae [7]. Therefore, in the context of infectious diseases, it is advantageous to narrow down the candidate causative microorganisms to select the drug to be administered. ...
This study aimed to investigate the seasonal trends in infectious keratitis by assessing the month of onset and causative microorganisms. Five hundred consecutive cases of infectious keratitis that were diagnosed and treated by a corneal specialist at the Department of Ophthalmology, Yamaguchi University Hospital between January 2009 and January 2021 in whom micro-organisms could be identified formed the study population. The month of onset of infectious keratitis was retrospectively examined based on the medical records. The causative microorganisms were bacteria in 249 eyes, fungi in 51 eyes, Acanthamoeba in 27 eyes, and viruses in 173 eyes. The top 10 causative microorganisms accounted for 402 of 500 eyes (80.4% of the total). The incidence of infectious keratitis was highest from January to March and lowest in June. The total number of bacterial-induced infections was high between October and March. Pseudomonas aeruginosa commonly caused infectious keratitis from August to September. Acanthamoeba-induced infection was common in summer from June to August. HSV infections were common between January and May. A seasonal trend was observed in the occurrence of infectious keratitis by examining the months of onset. We contemplate that these results will assist ophthalmologists in diagnosing infectious keratitis.
... and infectious keratitis, have been developed based on deep learning (DL). [6][7][8][9][10][11][12][13][14] Although these AI techniques have achieved good performance, their ability to differentiate multiple corneal diseases remains limited. 15 In this study, we sought to develop an AI-driven comprehensive diagnosis/triage system using anterior segment photographs. ...
... The high performance of AI for automated diagnosis in ophthalmology has been reported in single diseases, such as cataracts, age-related macular degeneration, diabetic retinopathy, glaucoma and corneal diseases, using fundus photographs, optical coherence tomography and anterior segment images. [8][9][10][11][12][13][14][15] These methods can successfully differentiate one disease from a normal condition. However, AI algorithms need to diagnose various diseases in the real world. ...
Aim
To develop an artificial intelligence (AI) algorithm that diagnoses cataracts/corneal diseases from multiple conditions using smartphone images.
Methods
This study included 6442 images that were captured using a slit-lamp microscope (6106 images) and smartphone (336 images). An AI algorithm was developed based on slit-lamp images to differentiate 36 major diseases (cataracts and corneal diseases) into 9 categories. To validate the AI model, smartphone images were used for the testing dataset. We evaluated AI performance that included sensitivity, specificity and receiver operating characteristic (ROC) curve for the diagnosis and triage of the diseases.
Results
The AI algorithm achieved an area under the ROC curve of 0.998 (95% CI, 0.992 to 0.999) for normal eyes, 0.986 (95% CI, 0.978 to 0.997) for infectious keratitis, 0.960 (95% CI, 0.925 to 0.994) for immunological keratitis, 0.987 (95% CI, 0.978 to 0.996) for cornea scars, 0.997 (95% CI, 0.992 to 1.000) for ocular surface tumours, 0.993 (95% CI, 0.984 to 1.000) for corneal deposits, 1.000 (95% CI, 1.000 to 1.000) for acute angle-closure glaucoma, 0.992 (95% CI, 0.985 to 0.999) for cataracts and 0.993 (95% CI, 0.985 to 1.000) for bullous keratopathy. The triage of referral suggestion using the smartphone images exhibited high performance, in which the sensitivity and specificity were 1.00 (95% CI, 0.478 to 1.00) and 1.00 (95% CI, 0.976 to 1.000) for ‘urgent’, 0.867 (95% CI, 0.683 to 0.962) and 1.00 (95% CI, 0.971 to 1.000) for ‘semi-urgent’, 0.853 (95% CI, 0.689 to 0.950) and 0.983 (95% CI, 0.942 to 0.998) for ‘routine’ and 1.00 (95% CI, 0.958 to 1.00) and 0.896 (95% CI, 0.797 to 0.957) for ‘observation’, respectively.
Conclusions
The AI system achieved promising performance in the diagnosis of cataracts and corneal diseases.
... A deep-learning algorithm to differentiate the origin of keratitis, CRI included, was also implemented but a statistical difference was found between artificial intelligence and an experienced ophthalmologist. The study involved a robust number (669) of slit-lamp photographs of bacterial and fungal corneal ulcers [52]. Thus, many authors underline the value of repeating scrapes when persistent non-healing corneal ulcer is present with no growth on the first corneal sample analysis. ...
Objective
Ring infiltrates usually accompany numerous infectious and sterile ocular disorders. Nevertheless, systemic conditions, drugs toxicity and contact lens wear may present with corneal ring infiltrate in substantial part. Considering its detrimental effect on vision, detailed knowledge on etiology, pathophysiology, differential diagnosis, and management should be considered essential for every ophthalmologist.
Methods
The PUBMED database was searched for “corneal ring infiltrate” and “ring infiltrate” phrases, “sterile corneal infiltrate” and “corneal infiltrate”. We analyzed articles written in English on risk factors, pathophysiology, clinical manifestation, morphological features, ancillary tests (anterior-segment optical coherence tomography, corneal scraping, in vivo confocal microscopy), differential diagnosis and management of corneal ring infiltrate.
Results
Available literature depicts multifactorial origin of corneal ring infiltrate. Dual immunological pathophysiology, involving both antibodies-dependent and -independent complement activation, is underlined. Furthermore, we found that the worldwide most prevalent among non-infectious and infectious ring infiltrates are ring infiltrates related to contact-lens wear and bacterial keratitis respectively. Despite low incidence of Acanthamoeba keratitis, it manifests with corneal ring infiltrate with the highest proportion of the affected patients (one third). However, similar ring infiltrate might appear as a first sign of general diseases manifestation and require targeted treatment. Every corneal ring infiltrate with compromised epithelium should be scraped and treat as an infectious infiltrate until not proven otherwise. Of note, microbiological ulcer might also lead to immunological ring and therefore require anti-inflammatory treatment.
Conclusion
Corneal ring infiltrate might be triggered not only by ocular infectious and non-infectious factors, but also by systemic conditions. Clinical assessment is crucial for empirical diagnosis. Furthermore, treatment is targeted towards the underlying condition but should begin with anti-infectious regimen until not proven otherwise.
... And, Koyoma et al. created an algorithm using a dataset of 4306 slit-lamp images with an accuracy/AUROC for Acanthamoeba of 97.9%/0.995 [73]. However, only a total of 19 cases of AK were included, possibly limiting the robustness of the model for AK diagnosis. ...
Acanthamoeba Keratitis (AK) is a severe corneal infection caused by the Acanthamoeba species of protozoa, potentially leading to permanent vision loss. AK requires prompt diagnosis and treatment to mitigate vision impairment. Diagnosing AK is challenging due to overlapping symptoms with other corneal infections, and treatment is made complicated by the organism’s dual forms and increasing virulence, and delayed diagnosis. In this review, new approaches in AK diagnostics and treatment within the last 5 years are discussed. The English-language literature on PubMed was reviewed using the search terms “Acanthamoeba keratitis” and “diagnosis” or “treatment” and focused on studies published between 2018 and 2023. Two hundred sixty-five publications were initially identified, of which eighty-seven met inclusion and exclusion criteria. This review highlights the findings of these studies. Notably, advances in PCR-based diagnostics may be clinically implemented in the near future, while antibody-based and machine-learning approaches hold promise for the future. Single-drug topical therapy (0.08% PHMB) may improve drug access and efficacy, while oral medication (i.e., miltefosine) may offer a treatment option for patients with recalcitrant disease.
... Furthermore, it may also assist ophthalmologists and even empower untrained clinicians to diagnose IK in resource-scarce regions and take the needed actions, therefore diminishing its progressivity to debilitating corneal-related blindness. Despite its promising potential and the number of studies demonstrating high accuracy of DL in IK diagnosis and recognizing IK apart from other ocular diseases (8,(15)(16)(17)(18)(19)(20), its diagnostic accuracy remains to be elucidated. ...
Background
Infectious keratitis (IK) is a sight-threatening condition requiring immediate definite treatment. The need for prompt treatment heavily depends on timely diagnosis. The diagnosis of IK, however, is challenged by the drawbacks of the current “gold standard.” The poorly differentiated clinical features, the possibility of low microbial culture yield, and the duration for culture are the culprits of delayed IK treatment. Deep learning (DL) is a recent artificial intelligence (AI) advancement that has been demonstrated to be highly promising in making automated diagnosis in IK with high accuracy. However, its exact accuracy is not yet elucidated. This article is the first systematic review and meta-analysis that aims to assess the accuracy of available DL models to correctly classify IK based on etiology compared to the current gold standards.
Methods
A systematic search was carried out in PubMed, Google Scholars, Proquest, ScienceDirect, Cochrane and Scopus. The used keywords are: “Keratitis,” “Corneal ulcer,” “Corneal diseases,” “Corneal lesions,” “Artificial intelligence,” “Deep learning,” and “Machine learning.” Studies including slit lamp photography of the cornea and validity study on DL performance were considered. The primary outcomes reviewed were the accuracy and classification capability of the AI machine learning/DL algorithm. We analyzed the extracted data with the MetaXL 5.2 Software.
Results
A total of eleven articles from 2002 to 2022 were included with a total dataset of 34,070 images. All studies used convolutional neural networks (CNNs), with ResNet and DenseNet models being the most used models across studies. Most AI models outperform the human counterparts with a pooled area under the curve (AUC) of 0.851 and accuracy of 96.6% in differentiating IK vs. non-IK and pooled AUC 0.895 and accuracy of 64.38% for classifying bacterial keratitis (BK) vs. fungal keratitis (FK).
Conclusion
This study demonstrated that DL algorithms have high potential in diagnosing and classifying IK with accuracy that, if not better, is comparable to trained corneal experts. However, various factors, such as the unique architecture of DL model, the problem with overfitting, image quality of the datasets, and the complex nature of IK itself, still hamper the universal applicability of DL in daily clinical practice.
... Researchers have found that the diagnostic accuracy of various models varied from 69 to 72% when using external eye photographs to evaluate deep learning frameworks in BK, which is similar to as determined by ophthalmologists (66 to 74%) [65]. The ability to diagnose and assess microbial keratitis through artificial intelligence using external ocular pictures, such as those that could be taken with a mobile phone, may allow for the immediate start of appropriate therapy in regions or situations where patients do not have access to ophthalmic care [4,69,70] ...
Infectious keratitis is the fifth most prevalent cause of blindness worldwide. The primary diagnostic test to identify the pathogenic organism is the culture of corneal scraping. However microbial culture positivity is low and varies widely due to many underlying factors. Therefore, there is a need to understand the prevalence of such cases and what modern tools can be employed to diagnose them.
Contact lens usage, ocular injuries, and ocular surface disease have been reported to be primary risk factors for keratitis with infection of pathogens such as Staphylococcus spp., Pseudomonas aeruginosa, Fusarium spp., Candida spp., and Acanthamoeba spp. Advanced imaging techniques, such as in vivo confocal microscopy and anterior segment optical coherence tomography (OCT), and polymerase chain reaction (PCR) and other molecular techniques have been used to identify the specific causative agents of infectious keratitis more rapidly and accurately than traditional culture methods. However, microbial culture positivity is low and varies widely due to many underlying factors.
In vivo confocal microscopy and polymerase chain reaction (PCR) testing can support the diagnosis of infectious keratitis. Initial treatment for bacterial keratitis (BK) is with antimicrobials primarily fluoroquinolones, while topical natamycin (an antifungal anti-protozoal) is the drug of choice for fungal keratitis. Additionally, PCR and other molecular methods are utilized to corroborate the initial diagnosis or where routine microbial cultures are negative. This review provides current information for diagnosing microbial culture negative keratitis patients. Earlier diagnosis with modern tools could decrease incidence of corneal opacity, vision loss, or even the loss of an eye in keratitis patients.
... Through deep learning, CNN can identify keratitis, 12 differentiate infectious and non-infectious keratitis, 13 and diagnose BK and fungal keratitis (FK). [14][15][16][17] This technique can also differentiate active corneal ulcers from healed scars in FK. 18 To explore a CNNbased approach applicable to monitor the ocular changes in patients with presumed MK, we aimed to develop and assess the model for rapidly and objectively identifying the progression of keratitis via comparing paired images from serial visits of the same episode. This developed deep learning system was expected to alert physicians of inadequate treatment or misdiagnosis for a presumed patient with MK. ...
... The accuracy for image diagnosis of BK and FK was around 70% by deep learning approach with a pure CNN architecture. 14,15 The performance can be further promoted near 80% accuracy by an ensemble approach, 17 hybrid learning, 16 corneal segmentation before deep learning, 26,27 and deep sequential feature learning. 28 Recently, Tiwari et al. reported that the CNN classified corneal ulcers and scars with very high accuracy (88%), where the CNN visualizations correlated with clinically relevant features, such as corneal infiltrate, hypopyon, and conjunctival injection. ...
Purpose:
For this study, we aimed to determine whether a convolutional neural network (CNN)-based method (based on a feature extractor and an identifier) can be applied to monitor the progression of keratitis while managing suspected microbial keratitis (MK).
Methods:
This multicenter longitudinal cohort study included patients with suspected MK undergoing serial external eye photography at the 5 branches of Chang Gung Memorial Hospital from August 20, 2000, to August 19, 2020. Data were primarily analyzed from January 1 to March 25, 2022. The CNN-based model was evaluated via F1 score and accuracy. The area under the receiver operating characteristic curve (AUROC) was used to measure the precision-recall trade-off.
Results:
The model was trained using 1456 image pairs from 468 patients. In comparing models via only training the identifier, statistically significant higher accuracy (P < 0.05) in models via training both the identifier and feature extractor (full training) was verified, with 408 image pairs from 117 patients. The full training EfficientNet b3-based model showed 90.2% (getting better) and 82.1% (becoming worse) F1 scores, 87.3% accuracy, and 94.2% AUROC for 505 getting better and 272 becoming worse test image pairs from 452 patients.
Conclusions:
A CNN-based approach via deep learning applied in suspected MK can monitor the progress/regress during treatment by comparing external eye image pairs.
Translational relevance:
The study bridges the gap between the investigation of the state-of-the-art CNN-based deep learning algorithm applied in ocular image analysis and the clinical care of suspected patients with MK.
... For infectious keratitis, the use of DL with CNNs has been shown to be a potentially more accessible diagnostic method via image recognition [4,54,55]. Many studies have evaluated DL methods for diagnosing IK using images taken with a handheld camera, a camera mounted on a slit lamp or confocal microscopy [51,[55][56][57][58][59][60][61][62][63][64]. Several extremely efficient DL algorithms include RestNet-152 [65], DenseNet-169 [66], Mobile-Net V2 [67] and VGG-19_BN [68]. ...
... This innovative CNN can extract the fine features of keratitis lesions, which are not easy for clinicians to identify [64]. Further, there is a wide range of causal organisms in keratitis and varied clinical presentations with regional differences in both [4,58,82,83]. Improving image resolution, increasing the number of images for the training models, and optimising the parameters of the algorithms may enhance the accuracy of the models [51,72,73]. Future studies will be needed to validate the findings of CNN approaches to the diagnosis of IK in a range of global settings with a variety of devices (slit lamp microscopy and camera) [73]. ...
Infectious keratitis (IK) is among the top five leading causes of blindness globally. Early diagnosis is needed to guide appropriate therapy to avoid complications such as vision impairment and blindness. Slit lamp microscopy and culture of corneal scrapes are key to diagnosing IK. Slit lamp photography was transformed when digital cameras and smartphones were invented. The digital camera or smartphone camera sensor’s resolution, the resolution of the slit lamp and the focal length of the smartphone camera system are key to a high-quality slit lamp image. Alternative diagnostic tools include imaging, such as optical coherence tomography (OCT) and in vivo confocal microscopy (IVCM). OCT’s advantage is its ability to accurately determine the depth and extent of the corneal ulceration, infiltrates and haze, therefore characterizing the severity and progression of the infection. However, OCT is not a preferred choice in the diagnostic tool package for infectious keratitis. Rather, IVCM is a great aid in the diagnosis of fungal and Acanthamoeba keratitis with overall sensitivities of 66–74% and 80–100% and specificity of 78–100% and 84–100%, respectively. Recently, deep learning (DL) models have been shown to be promising aids for the diagnosis of IK via image recognition. Most of the studies that have developed DL models to diagnose the different types of IK have utilised slit lamp photographs. Some studies have used extremely efficient single convolutional neural network algorithms to train their models, and others used ensemble approaches with variable results. Limitations of DL models include the need for large image datasets to train the models, the difficulty in finding special features of the different types of IK, the imbalance of training models, the lack of image protocols and misclassification bias, which need to be overcome to apply these models into real-world settings. Newer artificial intelligence technology that generates synthetic data, such as generative adversarial networks, may assist in overcoming some of these limitations of CNN models.
... [34] The AI can standardize the corneal epithelial defect and infiltrate measurement reducing the variability between examiners. In a retrospective study, [35] a DL algorithm was developed to identify the keratitis pathogen by analyzing slit-lamp photos. The system assessed 4300 images showing an accuracy of more than 90% for Acanthamoeba, bacterial, fungi, and herpes infections. ...
In modern ophthalmology, the advent of artificial intelligence (AI) is gradually showing promising results. The application of complex algorithms to machine and deep learning has the potential to improve the diagnosis of various corneal and ocular surface diseases, customize the treatment, and enhance patient outcomes. Moreover, the use of AI can ameliorate the efficiency of the health-care system by providing more accurate results, reducing the workload of ophthalmologists, allowing the analysis of a big amount of data, and reducing the time and resources required for manual image acquisition and analysis. In this article, we reviewed the most important and recently published applications of AI in the field of cornea and ocular surface diseases, with a particular focus on keratoconus, infectious keratitis, corneal transplants, and the use of in vivo confocal microscopy.
