Automated OCT angiography image quality assessment using a deep learning algorithm
| Autor: | Jost Lennart Lauermann, C. R. Clemens, Florian Alten, Maximilian Treder, Nicole Eter, Maged Alnawaiseh |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Fundus Oculi
Computer science Image quality Convolutional neural network 03 medical and health sciences Cellular and Molecular Neuroscience Deep Learning 0302 clinical medicine Oct angiography Vascular plexus Humans Segmentation Fluorescein Angiography Retrospective Studies 030304 developmental biology 0303 health sciences Artifact (error) business.industry Deep learning Reproducibility of Results Retinal Vessels Optical coherence tomography angiography Sensory Systems Ophthalmology 030221 ophthalmology & optometry Neural Networks Computer Artificial intelligence Artifacts business Algorithm Algorithms Tomography Optical Coherence |
| Zdroj: | Graefe's Archive for Clinical and Experimental Ophthalmology. 257:1641-1648 |
| ISSN: | 1435-702X 0721-832X |
| DOI: | 10.1007/s00417-019-04338-7 |
| Popis: | To expedite and to standardize the process of image quality assessment in optical coherence tomography angiography (OCTA) using a specialized deep learning algorithm (DLA). 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. 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 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink