Abstract
Optical coherence tomography (OCT) is a promising high-speed, non-invasive imaging modality providing high-resolution retinal scans. However, a variety of external factors such as light occlusion and patient movement can seriously degrade OCT image quality, which complicates manual retinopathy detection and computer-aided diagnosis. As such, this study first presents an OCT image quality assessment (OCT-IQA) system, capable of automatic classification based on signal completeness, location, and effectiveness. Four CNN architectures (VGG-16, Inception-V3, ResNet-18, and ResNet-50) from the ImageNet classification task were used to train the proposed OCT-IQA system via transfer learning. The ResNet-50 with the best performance was then integrated into the final OCT-IQA network. The usefulness of this approach was evaluated using retinopathy detection results. A retinopathy classification network was first trained by fine-tuning Inception-V3 model. The model was then applied to two test datasets, created randomly from the original dataset, one of which was screened by the OCT-IQA system and only included high quality images while the other was mixed by high and low quality images. Results showed that retinopathy detection accuracy and area under curve (AUC) were 3.75% and 1.56% higher, respectively, for the filtered data (compared with the unfiltered data). These experimental results demonstrate the effectiveness of the proposed OCT-IQA system and suggest that deep learning could be applied to the design of computer-aided systems (CADSs) for automatic retinopathy detection.
Highlights
Optical coherence tomography (OCT), which can image retinal structures in vivo [1], has been widely applied in diagnostic ophthalmology due to its ease-of-use, lack of ionizing radiation, and high resolution [2]
The mean (SD) area under curve (AUC) for VGG-16, ResNet-18, ResNet-50, and Inception-V3 were 0.99122 (0.0023), 0.9888 (0.0018), 0.9932 (0.0026), and 0.9983 (0.0008), respectively. These results indicate that the standard deviation (SD) of AUC values were small for each model, which demonstrate their stability and robustness
The retinopathy detection dataset was established by eliminating all images belonging to the ‘other’ category and some images in the signal-shielded and off-center categories, since retinopathies in these images could not be recognized during anomaly grading
Summary
Optical coherence tomography (OCT), which can image retinal structures in vivo [1], has been widely applied in diagnostic ophthalmology due to its ease-of-use, lack of ionizing radiation, and high resolution [2]. There are approximately 30 million OCT procedures performed worldwide each year [3], with hundreds of consecutive B-scans comprising the majority of each procedure. This produces large quantities of data and limits the manual evaluation of individual images. Recent developments in computer-aided diagnostic systems (CADSs) have aided in retinopathy diagnosis and reduced the workload for clinicians This has reduced processing times by accelerating image evaluation and improving diagnoses [4]. Farsiu et al assessed OCT scan quality by comparing results with manual evaluations performed by experts, excluding poor quality images from the dataset [5]. The use of an IQA in a CADS is critical for eliminating low quality images
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
