Tags

Type your tag names separated by a space and hit enter

Automated OCT angiography image quality assessment using a deep learning algorithm.
Graefes Arch Clin Exp Ophthalmol. 2019 Aug; 257(8):1641-1648.GA

Abstract

PURPOSE

To expedite and to standardize the process of image quality assessment in optical coherence tomography angiography (OCTA) using a specialized deep learning algorithm (DLA).

METHODS

Two hundred randomly chosen en-face macular OCTA images of the central 3 × 3 mm2 superficial vascular plexus were evaluated retrospectively by an OCTA experienced reader. Images were defined either as sufficient (group 1, n = 100) or insufficient image quality (group 2, n = 100) based on Motion Artifact Score (MAS) and Segmentation Accuracy Score (SAS). Subsequently, a pre-trained multi-layer deep convolutional neural network (DCNN) was trained and validated with 160 of these en-face OCTA scans (group 1: 80; group 2: 80). Training accuracy, validation accuracy, and cross-entropy were computed. The DLA was tested in detecting 40 untrained OCTA images (group 1: 20; group 2: 20). An insufficient image quality probability score (IPS) and a sufficient image quality probability score (SPS) were calculated.

RESULTS

Training accuracy was 97%, validation accuracy 100%, and cross entropy 0.12. A total of 90% (18/20) of the OCTA images with insufficient image quality and 90% (18/20) with sufficient image quality were correctly classified by the DLA. Mean IPS was 0.88 ± 0.21, and mean SPS was 0.84 ± 0.19. Discrimination between both groups was highly significant (p < 0.001). Sensitivity of the DLA was 90.0%, specificity 90.0%, and accuracy 90.0%. Coefficients of variation were 0.96 ± 1.9% (insufficient quality) and 1.14 ± 1.6% (sufficient quality).

CONCLUSIONS

Deep learning (DL) appears to be a potential approach to automatically distinguish between sufficient and insufficient OCTA image quality. DL may contribute to establish image quality standards in this recent imaging modality.

Authors+Show Affiliations

Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany.Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany.Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany.Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany.Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany.Department of Ophthalmology, University of Muenster Medical Center, Domagkstrasse 15, 48149, Muenster, Germany. florian.alten@ukmuenster.de.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

31119426

Citation

Lauermann, J L., et al. "Automated OCT Angiography Image Quality Assessment Using a Deep Learning Algorithm." Graefe's Archive for Clinical and Experimental Ophthalmology = Albrecht Von Graefes Archiv Fur Klinische Und Experimentelle Ophthalmologie, vol. 257, no. 8, 2019, pp. 1641-1648.
Lauermann JL, Treder M, Alnawaiseh M, et al. Automated OCT angiography image quality assessment using a deep learning algorithm. Graefes Arch Clin Exp Ophthalmol. 2019;257(8):1641-1648.
Lauermann, J. L., Treder, M., Alnawaiseh, M., Clemens, C. R., Eter, N., & Alten, F. (2019). Automated OCT angiography image quality assessment using a deep learning algorithm. Graefe's Archive for Clinical and Experimental Ophthalmology = Albrecht Von Graefes Archiv Fur Klinische Und Experimentelle Ophthalmologie, 257(8), 1641-1648. https://doi.org/10.1007/s00417-019-04338-7
Lauermann JL, et al. Automated OCT Angiography Image Quality Assessment Using a Deep Learning Algorithm. Graefes Arch Clin Exp Ophthalmol. 2019;257(8):1641-1648. PubMed PMID: 31119426.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Automated OCT angiography image quality assessment using a deep learning algorithm. AU - Lauermann,J L, AU - Treder,M, AU - Alnawaiseh,M, AU - Clemens,C R, AU - Eter,N, AU - Alten,F, Y1 - 2019/05/22/ PY - 2018/09/12/received PY - 2019/04/22/accepted PY - 2019/03/06/revised PY - 2019/5/24/pubmed PY - 2019/8/7/medline PY - 2019/5/24/entrez KW - Artificial intelligence KW - Deep learning KW - Image analysis KW - Image artifacts KW - Optical coherence tomography angiography KW - Retina SP - 1641 EP - 1648 JF - Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie JO - Graefes Arch Clin Exp Ophthalmol VL - 257 IS - 8 N2 - PURPOSE: To expedite and to standardize the process of image quality assessment in optical coherence tomography angiography (OCTA) using a specialized deep learning algorithm (DLA). METHODS: Two hundred randomly chosen en-face macular OCTA images of the central 3 × 3 mm2 superficial vascular plexus were evaluated retrospectively by an OCTA experienced reader. Images were defined either as sufficient (group 1, n = 100) or insufficient image quality (group 2, n = 100) based on Motion Artifact Score (MAS) and Segmentation Accuracy Score (SAS). Subsequently, a pre-trained multi-layer deep convolutional neural network (DCNN) was trained and validated with 160 of these en-face OCTA scans (group 1: 80; group 2: 80). Training accuracy, validation accuracy, and cross-entropy were computed. The DLA was tested in detecting 40 untrained OCTA images (group 1: 20; group 2: 20). An insufficient image quality probability score (IPS) and a sufficient image quality probability score (SPS) were calculated. RESULTS: Training accuracy was 97%, validation accuracy 100%, and cross entropy 0.12. A total of 90% (18/20) of the OCTA images with insufficient image quality and 90% (18/20) with sufficient image quality were correctly classified by the DLA. Mean IPS was 0.88 ± 0.21, and mean SPS was 0.84 ± 0.19. Discrimination between both groups was highly significant (p < 0.001). Sensitivity of the DLA was 90.0%, specificity 90.0%, and accuracy 90.0%. Coefficients of variation were 0.96 ± 1.9% (insufficient quality) and 1.14 ± 1.6% (sufficient quality). CONCLUSIONS: Deep learning (DL) appears to be a potential approach to automatically distinguish between sufficient and insufficient OCTA image quality. DL may contribute to establish image quality standards in this recent imaging modality. SN - 1435-702X UR - https://www.unboundmedicine.com/medline/citation/31119426/Automated_OCT_angiography_image_quality_assessment_using_a_deep_learning_algorithm_ L2 - https://dx.doi.org/10.1007/s00417-019-04338-7 DB - PRIME DP - Unbound Medicine ER -