Artificial intelligence deep learning algorithm for discriminating ungradable optical coherence tomography three-dimensional volumetric optic disc scans

• Published in: Neurophotonics (Print) Vol. 6; no. 4; p. 041110
• Main Authors: Ran, An Ran, Shi, Jian, Ngai, Amanda K, Chan, Wai-Yin, Chan, Poemen P, Young, Alvin L, Yung, Hon-Wah, Tham, Clement C, Cheung, Carol Y
• Format: Journal Article
• Language: English
• Published: United States Society of Photo-Optical Instrumentation Engineers 01.10.2019; S P I E - International Society for
• Subjects: Artificial intelligence; Datasets; Deep learning; Gender; Glaucoma; Medical imaging; Neural networks; Optic nerve; Optics; Quality control; Quantitative analysis; Special Section on Advanced Retinal Imaging: Instrumentation, Methods, and Applications; Tomography; Hong Kong China; China; deep learning; image quality control; optical coherence tomography; artificial intelligence
• ISSN: 2329-423X; 2329-4248
• DOI: 10.1117/1.NPh.6.4.041110

Spectral-domain optical coherence tomography (SDOCT) is a noncontact and noninvasive imaging technology offering three-dimensional (3-D), objective, and quantitative assessment of optic nerve head (ONH) in human eyes in vivo. The image quality of SDOCT scans is crucial for an accurate and reliable interpretation of ONH structure and for further detection of diseases. Traditionally, signal strength (SS) is used as an index to include or exclude SDOCT scans for further analysis. However, it is insufficient to assess other image quality issues such as off-centration, out of registration, missing data, motion artifacts, mirror artifacts, or blurriness, which require specialized knowledge in SDOCT for such assessment. We proposed a deep learning system (DLS) as an automated tool for filtering out ungradable SDOCT volumes. In total, 5599 SDOCT ONH volumes were collected for training (80%) and primary validation (20%). Other 711 and 298 volumes from two independent datasets, respectively, were used for external validation. An SDOCT volume was labeled as ungradable when SS was <5 or when any artifacts influenced the measurement circle or >25  %   of the peripheral area. Artifacts included (1) off-centration, (2) out of registration, (3) missing signal, (4) motion artifacts, (5) mirror artifacts, and (6) blurriness. An SDOCT volume was labeled as gradable when SS was ≥5, and there was an absence of any artifacts or artifacts only influenced <25  %   peripheral area but not the retinal nerve fiber layer calculation circle. We developed and validated a 3-D DLS based on squeeze-and-excitation ResNeXt blocks and experimented with different training strategies. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy were calculated to evaluate the performance. Heatmaps were generated by gradient-weighted class activation map. Our findings show that the presented DLS achieved a good performance in both primary and external validations, which could potentially increase the efficiency and accuracy of SDOCT volumetric scans quality control by filtering out ungradable ones automatically.