“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

In response to a perceived need in the vision community, an OSA taskforce was formed at the 1999 topical meeting on vision science and its applications (VSIA-99) and charged with developing consensus recommendations on definitions, conventions, and standards for reporting of optical aberrations of human eyes. Progress reports were presented at the 1999 OSA annual meeting and at VSIA-2000 by the chairs of three taskforce subcommittees on (1) reference axes, (2) describing functions, and (3) model eyes.

Standards for reporting the optical aberrations of eyes

Purpose: To assess whether a generative adversarial network (GAN) could synthesize realistic optical coherence tomography (OCT) images that satisfactorily serve as the educational images for retinal specialists, and the training datasets for the classification of various retinal disorders using deep learning (DL). Methods: The GANs architecture was adopted to synthesize high-resolution OCT images trained on a publicly available OCT dataset, including urgent referrals (37,206 OCT images from eyes with choroidal neovascularization, and 11,349 OCT images from eyes with diabetic macular edema) and nonurgent referrals (8617 OCT images from eyes with drusen, and 51,140 OCT images from normal eyes). Four hundred real and synthetic OCT images were evaluated by two retinal specialists (with over 10 years of clinical retinal experience) to assess image quality. We further trained two DL models on either real or synthetic datasets and compared the performance of urgent versus nonurgent referrals diagnosis tested on a local (1000 images from the public dataset) and clinical validation dataset (278 images from Shanghai Shibei Hospital). Results: The image quality of real versus synthetic OCT images was similar as assessed by two retinal specialists. The accuracy of discrimination of real versus synthetic OCT images was 59.50% for retinal specialist 1 and 53.67% for retinal specialist 2. For the local dataset, the DL model trained on real (DL_Model_R) and synthetic OCT images (DL_Model_S) had an area under the curve (AUC) of 0.99, and 0.98, respectively. For the clinical dataset, the AUC was 0.94 for DL_Model_R and 0.90 for DL_Model_S. Conclusions: The GAN synthetic OCT images can be used by clinicians for educational purposes and for developing DL algorithms. Translational Relevance: The medical image synthesis based on GANs is promising in humans and machines to fulfill clinical tasks.

Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders

Optical coherence tomography (OCT) is a powerful optical imaging technique capable of visualizing the internal structure of biological tissues at near cellular resolution. For years, OCT has been regarded as the standard of care in ophthalmology, acting as an invaluable tool for the assessment of retinal pathology. However, the costly nature of most current commercial OCT systems has limited its general accessibility, especially in low-resource environments. It is therefore timely to review the development of low-cost OCT systems as a route for applying this technology to population-scale disease screening. Low-cost, portable and easy to use OCT systems will be essential to facilitate widespread use at point of care settings while ensuring that they offer the necessary imaging performances needed for clinical detection of retinal pathology. The development of low-cost OCT also offers the potential to enable application in fields outside ophthalmology by lowering the barrier to entry. In this paper, we review the current development and applications of low-cost, portable and handheld OCT in both translational and research settings. Design and cost-reduction techniques are described for general low-cost OCT systems, including considerations regarding spectrometer-based detection, scanning optics, system control, signal processing, and the role of 3D printing technology. Lastly, a review of clinical applications enabled by low-cost OCT is presented, along with a detailed discussion of current limitations and outlook.

https://iopscience.iop.org/article/10.1088/2516-1091/abfeb7/pdf

A review of low-cost and portable optical coherence tomography

Optical coherence tomography (OCT) is being increasingly adopted as a label-free and non-invasive technique for biomedical applications such as cancer and ocular disease diagnosis. Diagnostic information for these tissues is manifest in textural and geometric features of the OCT images, which are used by human expertise to interpret and triage. However, it suffers delays due to the long process of the conventional diagnostic procedure and shortage of human expertise. Here, a custom deep learning architecture, LightOCT, is proposed for the classification of OCT images into diagnostically relevant classes. LightOCT is a convolutional neural network with only two convolutional layers and a fully connected layer, but it is shown to provide excellent training and test results for diverse OCT image datasets. We show that LightOCT provides 98.9% accuracy in classifying 44 normal and 44 malignant (invasive ductal carcinoma) breast tissue volumetric OCT images. Also, >96% accuracy in classifying public datasets of ocular OCT images as normal, age-related macular degeneration and diabetic macular edema. Additionally, we show ∼96% test accuracy for classifying retinal images as belonging to choroidal neovascularization, diabetic macular edema, drusen, and normal samples on a large public dataset of more than 100,000 images. The performance of the architecture is compared with transfer learning based deep neural networks. Through this, we show that LightOCT can provide significant diagnostic support for a variety of OCT images with sufficient training and minimal hyper-parameter tuning. The trained LightOCT networks for the three-classification problem will be released online to support transfer learning on other datasets.

Deep learning architecture "LightOCT" for diagnostic decision support using optical coherence tomography images of biological samples.

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.

Deep learning for quality assessment of retinal OCT images.

Fluorescein angiography can provide a map of retinal vascular structure and function, which is commonly used in ophthalmology diagnosis, however, this imaging modality may pose risks of harm to the patients. To help physicians reduce the potential risks of diagnosis, an image translation method is adopted. In this work, we proposed a conditional generative adversarial network(GAN) - based method to directly learn the mapping relationship between structure fundus images and fundus fluorescence angiography images. Moreover, local saliency maps, which define each pixel's importance, are used to define a novel saliency loss in the GAN cost function. This facilitates more accurate learning of small-vessel and fluorescein leakage features.

/pdf/generating-fundus-fluorescence-angiography-images-from-3c35fg5akv.pdf

Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks

We have designed, constructed and tested an adaptive optics scanning laser ophthalmoscope (AOSLO) using a bimorph mirror. The simulated AOSLO system achieves diffraction-limited criterion through all the raster scanning fields (6.4 mm pupil, 3° × 3° on pupil). The bimorph mirror-based AOSLO corrected ocular aberrations in model eyes to less than 0.1 μm RMS wavefront error with a closed-loop bandwidth of a few Hz. Facilitated with a bimorph mirror at a stroke of ±15 μm with 35 elements and an aperture of 20 mm, the new AOSLO system has a size only half that of the first-generation AOSLO system. The significant increase in stroke allows for large ocular aberrations such as defocus in the range of ±600° and astigmatism in the range of ±200°, thereby fully exploiting the AO correcting capabilities for diseased human eyes in the future.

Design of a Compact, Bimorph Deformable Mirror-Based Adaptive Optics Scanning Laser Ophthalmoscope

Fundus fluorescein angiography (FA) is an indispensable procedure that can investigate the integrity of retina vasculature. Fluorescein angiograms progress through five phases: pre-arterial, arterial, arteriovenous, venous, and late, and each phase could be an important diagnostic basis for retina-related disease. However, the FA imaging technique may provide risks of harm to the patients. To help physicians reduce the potential risks of diagnosis, we proposed “SequenceGAN”, a novel sequential generative adversarial network that aims to generate FA sequences of critical phases from a structure fundus image. Moreover, a feature-space loss is applied to ensure the generated FA sequences with a better visual effect. The proposed method was qualitatively and quantitatively compared with existing FA image generation methods and image translation methods. The experimental results indicate that the proposed model has better performance on the generation of retina vascular, leakage structures, and characteristics of each angiogram phase, and thus indicates potential value for application in clinical diagnosis.

SequenceGAN: Generating Fundus Fluorescence Angiography Sequences from Structure Fundus Image.

INTRODUCTION Evaluating the anterior chamber angle (ACA) is important for the early diagnosis and treatment of primary angle-closure glaucoma. The assessment of ultrasound biomicroscopy (UBM) images usually requires well-trained ophthalmologists and screening for patients with narrow ACA is usually time- and labor-intensive. Therefore, the automatic assessment of UBM could be cost-effective and valuable in daily practice. OBJECTIVE The objective of this study is to develop an automatic method for localizing and classifying ACA based on UBM images. METHODS UBM images were collected and a coarse-to-fine method was used to localize the apex of the angle recess. By analyzing the grayscale features around the angle recess, closed angles were identified, and the rest were then classified as open or narrow angles, based on the degree of ACA. Using manual classification as the reference standard, the overall accuracy (OAcc), sensitivity (Sen), specificity (Spe), and balanced accuracy of the automatic classification method were evaluated. RESULTS A total of 540 UBM images from 290 participants were analyzed. Using these UBM images and the proposed method, the ACA was classified as open, narrow, or closed. During processing, the method localized the angle recess with 95% accuracy. The OAcc of the ACA classification was 77.8%, and the Spe and Sen of our method were 85.8 and 81.7% for angle closure; 88.9 and 75.6% for open angles; 91.9 and 76.1% for narrow angles, respectively. CONCLUSIONS Our method of automatic angle localization and classification based on UBM images is feasible and reliable. The automatic classification of ACA provides a basis and reference for future studies.

/pdf/automatic-classification-of-anterior-chamber-angle-based-on-335gszt26b.pdf

Guohua Deng

Papers

Deep learning for quality assessment of retinal OCT images.

Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks

Design of a Compact, Bimorph Deformable Mirror-Based Adaptive Optics Scanning Laser Ophthalmoscope

SequenceGAN: Generating Fundus Fluorescence Angiography Sequences from Structure Fundus Image.

Automatic Classification of Anterior Chamber Angle Based on Ultrasound Biomicroscopy Images.