Artificial intelligence and corneal diseases

Kang, Linda; Ballouz, Dena; Woodward, Maria A.

doi:10.1097/icu.0000000000000885

Cited by 10 publications

(12 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a spatially-resolved imaging method, future development could also take advantage of spatial distribution and morphological features in fluorescence images to aid in diagnosis. Morphological features in MK fluorescence images in particular may lend themselves well to machine learning techniques for ulcer classification that are currently under investigation using a variety of image sources (Kang et al, 2022); however, since the fluorescence images intrinsically contain chemistry information that is speciesdependent, further work will be needed to adapt these automated approaches to the proposed imaging technique.…”

Section: Discussionmentioning

confidence: 99%

Fluorescence imaging for the anterior segment of the eye

Herzog,

Sick

2024

Front. Photon.

View full text Add to dashboard Cite

Diagnostic technologies for the anterior segment of the eye, especially for hard-to-diagnose diseases such as microbial keratitis, are still lacking. Although in vivo confocal microscopy and optical coherence tomography are becoming more widely applicable to a variety of conditions, they are often prohibitively expensive, require specialized training and equipment, and are intrinsically insensitive to chemical changes. Here, ultraviolet-fluorescence imaging is proposed as a new technique to aid in investigation of the anterior segment. In this work, a novel two-color line-of-sight fluorescence imaging technique is described for imaging of the anterior segment. The technique is applied to seven ex vivo porcine eyes to illustrate the utility of the technique. The image data was used to estimate an effective fluorescence quantum yield of each eye at 370 nm. The eyes were then inoculated with bacteria to simulate microbial keratitis, a common sight-threatening infection, and the measurement was repeated. A simplified fluorescence-extinction model was developed to describe and analyze the relative intensities of the eye and biofilm fluorescence. Overall, the technique appears to have utility in clinical practice and with proper development may be suitable for detecting chemical changes in the eye, or the presence of foreign matter; however, further investigation is needed to develop the technique and analysis procedures into a quantitative diagnostic tool.

show abstract

Section: Discussionmentioning

confidence: 99%

Fluorescence imaging for the anterior segment of the eye

Herzog,

Sick

2024

Front. Photon.

View full text Add to dashboard Cite

show abstract

“…The United States Food and Drug Administration (FDA) also approved the first automatic diagnosis tool for diabetic retinopathy based on AI in 2018 (27). At the same time, AI has made remarkable achievements in the diagnosis, segmentation, and quantification of Frontiers in Medicine 07 frontiersin.org slit lamp images, anterior segment optical coherence tomography (A-S OCT), macular OCT, fundus fluorescein angiography (FFA), and other ophthalmic anterior and posterior segment images (11). IVCM photography and examination are well-established diagnostic imaging techniques for corneal diseases, while in clinical conditions, ophthalmologists mainly analyze images for multiple times to ensure accuracy of diagnosis.…”

Section: Discussionmentioning

confidence: 99%

“…Advances in artificial intelligence (AI) are transforming screening, diagnosis, and treatment in all areas of medicine (11), and the application of AI to ophthalmic diseases has also significantly evolved over the past decade. To date, AI has made significant breakthroughs in the segmentation, quantification, and identification of corneal epithelial cells, corneal nerves, corneal endothelial cells, fungal hyphae, dendritic cells, and inflammatory cells in IVCM images (9,(12)(13)(14)(15), and it has demonstrated an excellent performance in terms of speed and accuracy of film reading, which can make healthcare more accessible and cost-effective.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of a computer-aided diagnostic model for corneal diseases by analyzing in vivo confocal microscopy images

et al. 2023

View full text Add to dashboard Cite

ObjectiveIn order to automatically and rapidly recognize the layers of corneal images using in vivo confocal microscopy (IVCM) and classify them into normal and abnormal images, a computer-aided diagnostic model was developed and tested based on deep learning to reduce physicians’ workload.MethodsA total of 19,612 corneal images were retrospectively collected from 423 patients who underwent IVCM between January 2021 and August 2022 from Renmin Hospital of Wuhan University (Wuhan, China) and Zhongnan Hospital of Wuhan University (Wuhan, China). Images were then reviewed and categorized by three corneal specialists before training and testing the models, including the layer recognition model (epithelium, bowman’s membrane, stroma, and endothelium) and diagnostic model, to identify the layers of corneal images and distinguish normal images from abnormal images. Totally, 580 database-independent IVCM images were used in a human-machine competition to assess the speed and accuracy of image recognition by 4 ophthalmologists and artificial intelligence (AI). To evaluate the efficacy of the model, 8 trainees were employed to recognize these 580 images both with and without model assistance, and the results of the two evaluations were analyzed to explore the effects of model assistance.ResultsThe accuracy of the model reached 0.914, 0.957, 0.967, and 0.950 for the recognition of 4 layers of epithelium, bowman’s membrane, stroma, and endothelium in the internal test dataset, respectively, and it was 0.961, 0.932, 0.945, and 0.959 for the recognition of normal/abnormal images at each layer, respectively. In the external test dataset, the accuracy of the recognition of corneal layers was 0.960, 0.965, 0.966, and 0.964, respectively, and the accuracy of normal/abnormal image recognition was 0.983, 0.972, 0.940, and 0.982, respectively. In the human-machine competition, the model achieved an accuracy of 0.929, which was similar to that of specialists and higher than that of senior physicians, and the recognition speed was 237 times faster than that of specialists. With model assistance, the accuracy of trainees increased from 0.712 to 0.886.ConclusionA computer-aided diagnostic model was developed for IVCM images based on deep learning, which rapidly recognized the layers of corneal images and classified them as normal and abnormal. This model can increase the efficacy of clinical diagnosis and assist physicians in training and learning for clinical purposes.

show abstract

“…Another study confirmed that a DL algorithm could be useful to automatically screen for glaucoma via smartphone-based fundus photos. This algorithm showed a high diagnosis ability, especially in the eyes of advanced glaucoma patients [34].…”

Section: Detecting Glaucoma Via Aimentioning

confidence: 93%

Current roles of artificial intelligence in ophthalmology

Keskinbora

2023

Exploration of Medicine

View full text Add to dashboard Cite

Artificial intelligence (AI) studies are increasingly reporting successful results in the diagnosis and prognosis prediction of ophthalmological diseases as well as systemic disorders. The goal of this review is to detail how AI can be utilized in making diagnostic predictions to enhance the clinical setting. It is crucial to keep improving methods that emphasize clarity in AI models. This makes it possible to evaluate the information obtained from ocular imaging and easily incorporate it into therapeutic decision-making procedures. This will contribute to the wider acceptance and adoption of AI-based ocular imaging in healthcare settings combining advanced machine learning and deep learning techniques with new developments. Multiple studies were reviewed and evaluated, including AI-based algorithms, retinal images, fundus and optic nerve head (ONH) photographs, and extensive expert reviews. In these studies, carried out in various countries and laboratories of the world, it is seen those complex diagnoses, which can be detected systemic diseases from ophthalmological images, can be made much faster and with higher predictability, accuracy, sensitivity, and specificity, in addition to ophthalmological diseases, by comparing large numbers of images and teaching them to the computer. It is now clear that it can be taken advantage of AI to achieve diagnostic certainty. Collaboration between the fields of medicine and engineering foresees promising advances in improving the predictive accuracy and precision of future medical diagnoses achieved by training machines with this information. However, it is important to keep in mind that each new development requires new additions or updates to various social, psychological, ethical, and legal regulations.

show abstract

Artificial intelligence and corneal diseases

Cited by 10 publications

References 69 publications

Fluorescence imaging for the anterior segment of the eye

Fluorescence imaging for the anterior segment of the eye

Evaluation of a computer-aided diagnostic model for corneal diseases by analyzing in vivo confocal microscopy images

Current roles of artificial intelligence in ophthalmology

Contact Info

Product

Resources

About