Automated OCT angiography image quality assessment using a deep learning algorithm

Lauermann, Jost Lennart; Treder, Maximilian; Alnawaiseh, Maged; Clemens, Christoph R.; Eter, Nicole; Alten, Florian

doi:10.1007/s00417-019-04338-7

Cited by 29 publications

(27 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previous studies have demonstrated the feasibility of automated image quality classifiers for other modalities, such as fundus photography and OCTA. [15][16][17] Interestingly, in en face OCTA, fewer training samples were needed to distinguish superficial vascular structures. The algorithm was trained on 200 OCTA images evaluated by a single image reader and achieved sensitivity, specificity, and accuracy of 90.0% each.…”

Section: Discussionmentioning

confidence: 99%

“…The algorithm was trained on 200 OCTA images evaluated by a single image reader and achieved sensitivity, specificity, and accuracy of 90.0% each. 17 Another application of automated image quality classification can be seen with an artificial intelligence fundus image assessment tool recently approved by the Food and Drug Administration. The fundus photograph quality assessment component measures multiple criteria, such as retinal area, focus, and exposures, and then appoints either an adequate or inadequate quality assignment to the image.…”

Section: Discussionmentioning

confidence: 99%

“…Previous studies have demonstrated the feasibility of automated image quality classifiers for other modalities, such as fundus photography and OCTA. 15 – 17 …”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Quality Assessment and Image Selection of Ultra-Widefield Fluorescein Angiography Images through Deep Learning

Abraham

Sevgi

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

Numerous angiographic images with high variability in quality are obtained during each ultra-widefield fluorescein angiography (UWFA) acquisition session. This study evaluated the feasibility of an automated system for image quality classification and selection using deep learning. Methods: The training set was comprised of 3543 UWFA images. Ground-truth image quality was assessed by expert image review and classified into one of four categories (ungradable, poor, good, or best) based on contrast, field of view, media opacity, and obscuration from external features. Two test sets, including randomly selected 392 images separated from the training set and an independent balanced image set composed of 50 ungradable/poor and 50 good/best images, assessed the model performance and bias. Results: In the randomly selected and balanced test sets, the automated quality assessment system showed overall accuracy of 89.0% and 94.0% for distinguishing between gradable and ungradable images, with sensitivity of 90.5% and 98.6% and specificity of 87.0% and 81.5%, respectively. The receiver operating characteristic curve measuring performance of two-class classification (ungradable and gradable) had an area under the curve of 0.920 in the randomly selected set and 0.980 in the balanced set. Conclusions: A deep learning classification model demonstrates the feasibility of automatic classification of UWFA image quality. Clinical application of this system might greatly reduce manual image grading workload, allow quality-based image presentation to clinicians, and provide near-instantaneous feedback on image quality during image acquisition for photographers. Translational Relevance: The UWFA image quality classification tool may significantly reduce manual grading for clinical-and research-related work, providing instantaneous and reliable feedback on image quality.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Quality Assessment and Image Selection of Ultra-Widefield Fluorescein Angiography Images through Deep Learning

Abraham

Sevgi

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

show abstract

“…Furthermore, AI methods have been developed to detect age-related macular degeneration, cataracts, and keratoconus, among others [ 17 , 18 ]. Aside from detection of diseases, deep learning has also been tested to assess OCTA image quality by accurately differentiating between sufficient and insufficient OCTA images based on criteria of motion artifact score, centered vs. decentered fovea, visibility of small capillaries, and segmentation accuracy score [ 19 ]. Thus, deep learning in retinal imaging is proving its potential not only in disease diagnosis, but in quality control purposes as well.…”

Section: Deep Learning Diagnosticsmentioning

confidence: 99%

Heart, Eye, and Artificial Intelligence: A Review

Gupta

Reddy

2021

Cardiol Res

View full text Add to dashboard Cite

Heart disease continues to be the leading cause of death in the USA. Deep learning-based artificial intelligence (AI) methods have become increasingly common in studying the various factors involved in cardiovascular disease. The usage of retinal scanning techniques to diagnose retinal diseases, such as diabetic retinopathy, age-related macular degeneration, glaucoma and others, using fundus photographs and optical coherence tomography angiography (OCTA) has been extensively documented. Researchers are now looking to combine the power of AI with the non-invasive ease of retinal scanning to examine the workings of the heart and predict changes in the macrovasculature based on microvascular features and function. In this review, we summarize the current state of the field in using retinal imaging to diagnose cardiovascular issues and other diseases.

show abstract

“…Künstliche Intelligenz kann einerseits dabei helfen, eine korrekte Segmentierung trotz vorhandener Pathologien zu erhalten [47 -49] sowie andererseits bei der Vorauswahl von zur Befundung geeigneten Bildern [50].…”

Section: Segmentierungunclassified

Chancen von künstlicher Intelligenz und Big Data für die Diagnostik und Behandlung der altersabhängigen Makuladegeneration

Treder

Eter

2019

Klin Monatsbl Augenheilkd

View full text Add to dashboard Cite

ZusammenfassungDie altersabhängige Makuladegeneration (AMD) ist der führende Grund für Erblindung in der westlichen Welt. Für die neovaskuläre Verlaufsform steht mit der intravitrealen Anti-VEGF-Injektion (VEGF: vascular endothelial growth factor) eine wirksame Therapie zur Verfügung. In den letzten Jahren haben die multimodale Bildgebung und die standardisierte elektronische Patientendokumentation geholfen, die Diagnostik und das Management der AMD-Patienten zu verbessern. Mit dem Aufkommen der künstlichen Intelligenz und Big Data ergeben sich in diesem Zusammenhang viele Chancen für die Zukunft. Dieser Artikel soll einen Überblick über mögliche Anwendungen geben.

show abstract

Automated OCT angiography image quality assessment using a deep learning algorithm

Cited by 29 publications

References 41 publications

Automated Quality Assessment and Image Selection of Ultra-Widefield Fluorescein Angiography Images through Deep Learning

Automated Quality Assessment and Image Selection of Ultra-Widefield Fluorescein Angiography Images through Deep Learning

Heart, Eye, and Artificial Intelligence: A Review

Chancen von künstlicher Intelligenz und Big Data für die Diagnostik und Behandlung der altersabhängigen Makuladegeneration

Contact Info

Product

Resources

About