Understanding the advent of artificial intelligence in ophthalmology

Ahuja, Abhimanyu S.; Halperin, Lawrence S.

doi:10.1016/j.joco.2019.05.001

Cited by 18 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This started a new subfield of ML called deep learning which employs algorithms such as DNN and convolutional neural networks (CNNs). The idea is “that a neural network, instead of just acting as a classifier as in the case of classic ML, can also function as the feature extractor as well” (Ahuja & Halperin, 2019). This allows for end-to-end training because a DNN learns to recognize an output category from the input signal directly (Schmidt-Erfurth et al., 2018).…”

Section: Artificial Intelligence Vs Machine Learning Vs Deep Learningmentioning

confidence: 99%

The impact of artificial intelligence in medicine on the future role of the physician

Ahuja

2019

PeerJ

Self Cite

526

255

View full text Add to dashboard Cite

The practice of medicine is changing with the development of new Artificial Intelligence (AI) methods of machine learning. Coupled with rapid improvements in computer processing, these AI-based systems are already improving the accuracy and efficiency of diagnosis and treatment across various specializations. The increasing focus of AI in radiology has led to some experts suggesting that someday AI may even replace radiologists. These suggestions raise the question of whether AI-based systems will eventually replace physicians in some specializations or will augment the role of physicians without actually replacing them. To assess the impact on physicians this research seeks to better understand this technology and how it is transforming medicine. To that end this paper researches the role of AI-based systems in performing medical work in specializations including radiology, pathology, ophthalmology, and cardiology. It concludes that AI-based systems will augment physicians and are unlikely to replace the traditional physician–patient relationship.

show abstract

Section: Artificial Intelligence Vs Machine Learning Vs Deep Learningmentioning

confidence: 99%

The impact of artificial intelligence in medicine on the future role of the physician

Ahuja

2019

PeerJ

Self Cite

526

255

View full text Add to dashboard Cite

show abstract

“…Machine learning techniques have been used for automated diagnosis and detection of different aspects of human diseases 8 . In ophthalmology, it has been used successfully in retinal and glaucomatous disease.…”

Section: Introductionmentioning

confidence: 99%

Foveal avascular zone segmentation in optical coherence tomography angiography images using a deep learning approach

Mirshahi

Anvari

Riazi-Esfahani

et al. 2021

Sci Rep

View full text Add to dashboard Cite

The purpose of this study was to introduce a new deep learning (DL) model for segmentation of the fovea avascular zone (FAZ) in en face optical coherence tomography angiography (OCTA) and compare the results with those of the device’s built-in software and manual measurements in healthy subjects and diabetic patients. In this retrospective study, FAZ borders were delineated in the inner retinal slab of 3 × 3 enface OCTA images of 131 eyes of 88 diabetic patients and 32 eyes of 18 healthy subjects. To train a deep convolutional neural network (CNN) model, 126 enface OCTA images (104 eyes with diabetic retinopathy and 22 normal eyes) were used as training/validation dataset. Then, the accuracy of the model was evaluated using a dataset consisting of OCTA images of 10 normal eyes and 27 eyes with diabetic retinopathy. The CNN model was based on Detectron2, an open-source modular object detection library. In addition, automated FAZ measurements were conducted using the device’s built-in commercial software, and manual FAZ delineation was performed using ImageJ software. Bland–Altman analysis was used to show 95% limit of agreement (95% LoA) between different methods. The mean dice similarity coefficient of the DL model was 0.94 ± 0.04 in the testing dataset. There was excellent agreement between automated, DL model and manual measurements of FAZ in healthy subjects (95% LoA of − 0.005 to 0.026 mm2 between automated and manual measurement and 0.000 to 0.009 mm2 between DL and manual FAZ area). In diabetic eyes, the agreement between DL and manual measurements was excellent (95% LoA of − 0.063 to 0.095), however, there was a poor agreement between the automated and manual method (95% LoA of − 0.186 to 0.331). The presence of diabetic macular edema and intraretinal cysts at the fovea were associated with erroneous FAZ measurements by the device’s built-in software. In conclusion, the DL model showed an excellent accuracy in detection of FAZ border in enfaces OCTA images of both diabetic patients and healthy subjects. The DL and manual measurements outperformed the automated measurements of the built-in software.

show abstract

“…44 A powerful tool such as AI could greatly aid one in their effort to diagnose CHRPE. The main limitation however is the quality of the evidence analysed; 11 of the 13 studies were case control studies.…”

Section: Limitations Of This Reviewmentioning

confidence: 99%

“…In almost every macular and retinal disease, AI has the power to identify, localize, and quantify pathological features. 44 A powerful tool such as AI could greatly aid one in their effort to diagnose CHRPE.…”

Section: Limitations Of This Reviewmentioning

confidence: 99%

In patients with a positive family history of familial adenomatous polyposis can the condition be diagnosed from the presence of congenital hypertrophy of the retinal pigment epithelium detected via an eye examination: A systematic review

Rehan

Aye

2019

Clinical Exper Ophthalmology

View full text Add to dashboard Cite

In classic familial adenomatous polyposis (FAP) adenomas become malignant. Congenital hypertrophy of the retinal pigment epithelium (CHRPE) is a retinal pigmented lesion and is the earliest and most common potential extraintestinal manifestation of FAP. This review aims to summarize and analyse all of the published data on CHRPE in patients with classic FAP and then ascertain whether these patients should undergo a relatively cheap and non‐invasive dilated fundus examination to screen for CHRPE. Adhering to Preferred Reporting Items for Systematic Reviews and Meta Analyses guidelines our database search identified 102 relevant articles of which 13 were selected for further analysis. The percentage of FAP patients with CHRPE was found to be 80.00%, whereas the percentage of at‐risk patients with CHRPE was 31.12%. Despite various statistically significant findings, CHRPE alone cannot be used as a surrogate for diagnosing FAP in those with a positive family history. The authors advocate a combined approach of eye examinations, colonoscopy and genetic testing.

show abstract

Understanding the advent of artificial intelligence in ophthalmology

Cited by 18 publications

References 12 publications

The impact of artificial intelligence in medicine on the future role of the physician

The impact of artificial intelligence in medicine on the future role of the physician

Foveal avascular zone segmentation in optical coherence tomography angiography images using a deep learning approach

In patients with a positive family history of familial adenomatous polyposis can the condition be diagnosed from the presence of congenital hypertrophy of the retinal pigment epithelium detected via an eye examination: A systematic review

Contact Info

Product

Resources

About