Primary angle closure glaucoma (PACG) is the leading cause of irreversible blindness among Asian people. Early detection of PACG is essential, so as to provide timely treatment and minimize the vision loss. In the clinical practice, PACG is diagnosed by analyzing the angle between the cornea and iris with anterior segment optical coherence tomography (AS-OCT). The rapid development of deep learning technologies provides the feasibility of building a computer-aided system for the fast and accurate segmentation of cornea and iris tissues. However, the application of deep learning methods in the medical imaging field is still restricted by the lack of enough fully-annotated samples. In this paper, we propose a novel framework to segment the target tissues accurately for the AS-OCT images, by using the combination of weakly-annotated images (majority) and fully-annotated images (minority). The proposed framework consists of two models which provide reliable guidance for each other. In addition, uncertainty guided strategies are adopted to increase the accuracy and stability of the guidance. Detailed experiments on the publicly available AGE dataset demonstrate that the proposed framework outperforms the state-of-the-art semi-/weakly-supervised methods and has a comparable performance as the fully-supervised method. Therefore, the proposed method is demonstrated to be effective in exploiting information contained in the weakly-annotated images and has the capability to substantively relieve the annotation workload.
Assignment Flow for Order-Constrained OCT Segmentation
Heidelberg University（海德堡大学）
目前，光学相干断层扫描（OCT）是最常用的非侵入性成像方法之一，用于采集人体视网膜组织和血管的大体积扫描。为了从提取的OCT体积中解析决定性信息并使其适用于进一步的诊断分析，视网膜层厚度的准确识别是为每个患者单独完成的重要任务。然而，连续多次OCT扫描的手动检查是一项要求很高且耗时的任务，这导致了冗长的鉴定过程，并且在存在组织相关散斑噪声的情况下经常混淆。因此，自动分割模型的阐述已成为医学图像处理领域的一项重要任务。我们提出了一种新的，纯数据驱动的\textit{geometric approach to order-constrained 3D OCT retinal cell layer segmentation}，它需要作为输入数据在任何度量空间，并伴随着基本的操作，可以有效地并行计算。相对于许多已建立的视网膜检测方法，我们提出的配方避免了使用任何形状之前，并完成了视网膜的自然顺序在一个纯粹的几何方式。这使得该方法是无偏的，因此适合于检测视网膜组织结构的局部解剖变化。为了证明所提出的方法的鲁棒性，我们比较了两种不同的选择功能的数据集上的手动注释的3D OCT卷的健康人的视网膜。计算分割的质量进行比较，以平均绝对误差和骰子相似系数方面的最先进的。结果表明，一个巨大的潜力，将我们的方法应用于疾病视网膜的分类，并打开了一个新的研究方向，关于联合分割视网膜细胞层和血管结构。
Are Macula or Optic Nerve Head Structures better at Diagnosing Glaucoma? An Answer using AI and Wide-Field Optical Coherence Tomography
National University of Singapore（新加坡国立大学）；Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Centre（新加坡国家眼科中心）；Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工学院研究与技术联盟）；Yong Loo Lin School of Medicine, National University of Singapore（新加坡国立大学杨潞龄医学院）；Duke-NUS Graduate Medical School（杜克-新加坡国立大学医学院）；Nanyang Technological University Singapore（新加坡南洋理工大学）；Medical University of Vienna（维也纳医科大学）；Institute of Molecular and Clinical Ophthalmology, Basel（巴塞尔分子与临床眼科研究所）；Abyss Processing Pte Ltd（深渊处理私人有限公司）
A Deep Learning Approach to Denoise Optical Coherence Tomography Images of the Optic Nerve Head
National University of Singapore（新加坡国立大学）；Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Centre（新加坡国家眼科中心）；Beihang University（北京航空航天大学）；Duke-NUS Graduate Medical School（杜克-新加坡国立大学医学院）；Nanyang Technological University（南洋理工大学）
DRUNET: A Dilated-Residual U-Net Deep Learning Network to Digitally Stain Optic Nerve Head Tissues in Optical Coherence Tomography Images
National University of Singapore（新加坡国立大学）；Duke-NUS, Graduate Medical School（杜克-新加坡国立大学医学院）；Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Centre（新加坡全国眼科中心）；Université de la Polynésie francaise（法属波利尼西亚大学）；Moorfields Eye Hospital NHS Foundation Trust（Moorfields眼科医院NHS基金会信托）；UCL Institute of Ophthalmol（伦敦大学学院眼科研究所）
Towards Label-Free 3D Segmentation of Optical Coherence Tomography Images of the Optic Nerve Head Using Deep Learning
Ophthalmic Engineering and Innovation Laboratory, Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore（新加坡国立大学工程学院生物医学工程系眼科工程与创新实验室）；Singapore Eye Research Institute, Singapore National Eye Centre（新加坡国立眼科中心新加坡眼科研究所）；Rajan Eye Care Hospital（拉詹眼科护理医院）
O2CTA: Introducing Annotations from OCT to CCTA in Coronary Plaque Analysis
Dushu Lake Hospital Affiliated to Soochow University（苏州大学附属独墅湖医院）；Institution for Hypertension of Soochow University（苏州大学高血压研究所）；University of Science and Technology of China（中国科学技术大学）
Physics-based generation of multilayer corneal OCT data via Gaussian modeling and MCML for AI-driven diagnostic and surgical guidance applications
Department of Electrical and Computer Engineering, Johns Hopkins University（电气与计算机工程系，约翰霍普金斯大学）；Johns Hopkins University（约翰霍普金斯大学）；Wilmer Eye Institute, Johns Hopkins University（威尔默眼科研究所，约翰霍普金斯大学）；Vision Institute, Sorbonne University, INSERM, CNRS（视觉研究所，索邦大学，INSERM，CNRS）
Institute of Medical Technology and Intelligent Sys.（医学技术与智能系统研究所）；Hamburg University of Technology（汉堡理工大学）；Faculty of Electrical and Electronics Eng.（电气与电子工程系）；Kaunas University of Technology（卡斯图技术大学）；Interdisciplinary Competence Center for Interface Research（界面研究跨学科能力中心）；SustAInLivWork Center of Excellence（SustAInLivWork卓越研究中心）
3D Structural Analysis of the Optic Nerve Head to Robustly Discriminate Between Papilledema and Optic Disc Drusen
Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Centre（新加坡国家眼科中心）；Duke-NUS Graduate Medical School（杜克-新加坡国立大学研究生医学院）；Institute for Molecular and Clinical Ophthalmology（分子与临床眼科研究所）；Rigshospitalet（丹麦国家医院）；University of Copenhagen（哥本哈根大学）；Yong Loo Lin School of Medicine（杨潞龄医学院）；National University of Singapore（新加坡国立大学）；Save Sight Institute（拯救视力研究所）；The University of Sydney（悉尼大学）
OCT-GAN: Single Step Shadow and Noise Removal from Optical Coherence Tomography Images of the Human Optic Nerve Head
Singapore Eye Research Institute（新加坡眼科研究所）；National University of Singapore（新加坡国立大学）；Beihang University（北京航空航天大学）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）
