Optical Coherence Tomography Angiography (OCTA) is a non-invasive imaging technique that has been increasingly used to image the retinal vasculature at capillary level resolution. However, automated segmentation of retinal vessels in OCTA has been under-studied due to various challenges such as low capillary visibility and high vessel complexity, despite its significance in understanding many vision-related diseases. In addition, there is no publicly available OCTA dataset with manually graded vessels for training and validation of segmentation algorithms. To address these issues, for the first time in the field of retinal image analysis we construct a dedicated Retinal OCTA SEgmentation dataset (ROSE), which consists of 229 OCTA images with vessel annotations at either centerline-level or pixel level. This dataset with the source code has been released for public access to assist researchers in the community in undertaking research in related topics. Secondly, we introduce a novel split-based coarse-to-fine vessel segmentation network for OCTA images (OCTA-Net), with the ability to detect thick and thin vessels separately. In the OCTA-Net, a split-based coarse segmentation module is first utilized to produce a preliminary confidence map of vessels, and a split-based refined segmentation module is then used to optimize the shape/contour of the retinal microvasculature. We perform a thorough evaluation of the state-of-the-art vessel segmentation models and our OCTA-Net on the constructed ROSE dataset. The experimental results demonstrate that our OCTA-Net yields better vessel segmentation performance in OCTA than both traditional and other deep learning methods. In addition, we provide a fractal dimension analysis on the segmented microvasculature, and the statistical analysis demonstrates significant differences between the healthy control and Alzheimer’s Disease group. This consolidates that the analysis of retinal microvasculature may offer a new scheme to study various neurodegenerative diseases.
13 August 2021 in IEEE Transactions on Neural Networks and Learning Systems
This work focuses on image anomaly detection by leveraging only normal images in the training phase. Most previous methods tackle anomaly detection by reconstructing the input images with an autoencoder (AE)-based model, and an underlying assumption is that the reconstruction errors for the normal images are small, and those for the abnormal images are large. However, these AE-based methods, sometimes, even reconstruct the anomalies well; consequently, they are less sensitive to anomalies. To conquer this issue, we propose to reconstruct the image by leveraging the structure-texture correspondence. Specifically, we observe that, usually, for normal images, the texture can be inferred from its corresponding structure (e.g., the blood vessels in the fundus image and the structured anatomy in optical coherence tomography image), while it is hard to infer the texture from a destroyed structure for the abnormal images. Therefore, a structure-texture correspondence memory (STCM) module is proposed to reconstruct image texture from its structure, where a memory mechanism is used to characterize the mapping from the normal structure to its corresponding normal texture. As the correspondence between destroyed structure and texture cannot be characterized by the memory, the abnormal images would have a larger reconstruction error, facilitating anomaly detection. In this work, we utilize two kinds of complementary structures (i.e., the semantic structure with human-labeled category information and the low-level structure with abundant details), which are extracted by two structure extractors. The reconstructions from the two kinds of structures are fused together by a learned attention weight to get the final reconstructed image. We further feed the reconstructed image into the two aforementioned structure extractors to extract structures. On the one hand, constraining the consistency between the structures extracted from the original input and that from the reconstructed image would regularize the network training; on the other hand, the error between the structures extracted from the original input and that from the reconstructed image can also be used as a supplement measurement to identify the anomaly. Extensive experiments validate the effectiveness of our method for image anomaly detection on both industrial inspection images and medical images.
28 January 2020 in Translational Vision Science & Technology
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.
13 October 2021 in IEEE Transactions on Medical Imaging
Anomaly detection in medical images refers to the identification of abnormal images with only normal images in the training set. Most existing methods solve this problem with a self-reconstruction framework, which tends to learn an identity mapping and reduces the sensitivity to anomalies. To mitigate this problem, in this paper, we propose a novel Proxy-bridged Image Reconstruction Network (ProxyAno) for anomaly detection in medical images. Specifically, we use an intermediate proxy to bridge the input image and the reconstructed image. We study different proxy types, and we find that the superpixel-image (SI) is the best one. We set all pixels’ intensities within each superpixel as their average intensity, and denote this image as SI. The proposed ProxyAno consists of two modules, a Proxy Extraction Module and an Image Reconstruction Module. In the Proxy Extraction Module, a memory is introduced to memorize the feature correspondence for normal image to its corresponding SI, while the memorized correspondence does not apply to the abnormal images, which leads to the information loss for abnormal image and facilitates the anomaly detection. In the Image Reconstruction Module, we map an SI to its reconstructed image. Further, we crop a patch from the image and paste it on the normal SI to mimic the anomalies, and enforce the network to reconstruct the normal image even with the pseudo abnormal SI. In this way, our network enlarges the reconstruction error for anomalies. Extensive experiments on brain MR images, retinal OCT images and retinal fundus images verify the effectiveness of our method for both image-level and pixel-level anomaly detection.
10 September 2020 in IEEE Journal of Biomedical and Health Informatics
The choroid provides oxygen and nourishment to the outer retina thus is related to the pathology of various ocular diseases. Optical coherence tomography (OCT) is advantageous in visualizing and quantifying the choroid in vivo, because it does not suffer from the information contamination of the inner retina in fundus photography and scanning laser ophthalmoscopy, and the resolution deficiency in ocular ultrasound. However, its application in the study of the choroid is still limited for two reasons. (1) The lower boundary of the choroid (choroid-sclera interface) in OCT is fuzzy, which makes the automatic segmentation difficult and inaccurate. (2) The visualization of the choroid is hindered by the vessel shadows from the superficial layers of the inner retina. In this paper, we propose to incorporate medical and imaging prior knowledge with deep learning to address these two problems. We propose a biomarker infused global-to-local network, for the choroid segmentation. It leverages the thickness of the choroid layer, which is a primary biomarker in clinic, as a constraint to improve the segmentation accuracy. We also design a global-to-local strategy in the choroid segmentation: a global module is used to segment all the retinal and choroidal layers simultaneously for suppressing overfitting and providing global structure information, then a local module is used to refine the segmentation with the biomarker infusion. For eliminating the retinal vessel shadows, we propose a deep learning pipeline, which firstly use anatomical and OCT imaging knowledge to locate the shadows using their projection on the retinal pigment epthelium layer, then the contents of the choroidal vasculature at the shadow locations are predicted with an edge-to-texture two-stage generative adversarial inpainting network. The experiments shows the proposed method outperforms the existing methods on both the segmentation and shadow elimination tasks. We further apply the proposed method in a clinical prospective study for understanding the pathology of glaucoma, which demonstrates its capacity in detecting the structure and vascular changes of the choroid related to the elevation of intra-ocular pressure.
Since the invention of graphene, two-dimensional (2D) materials have attracted great interest in both fundamental science and potential applications. Here, we report the saturable absorption features of 2D (multilayered structure) molybdenum disulfide (MoS 2 ) in the mid-infrared (mid-IR) wavelength region, and use it to passively Q -switch an Er 3+ -doped ZBLAN fiber laser at 2.8 µ m. This MoS 2 saturable absorber has a moderate modulation depth of 5% at 2.8 µ m, making it an appropriate candidate for light modulating in the mid-IR spectral range. In stable Q -switching, the Er 3+ -doped ZBLAN fiber laser is widely tuned in both repetition rate and pulse width. Through increasing pump power, the repetition rate and pulse duration are monotonically tuned from 36 to 70 kHz and from 1.84 µ s to 806 ns, respectively. The maximum average power is 140 mW (at 70 kHz), giving a pulse energy of 2 µ J and peak power of ~2.48 W. Successful Q -switching operation of this 2.8 µ m fiber laser confirms that 2D MoS 2 has great potentials as efficient light modulating elements in mid-IR regions.