Advancing UWF-SLO Vessel Segmentation with Source-Free Active Domain Adaptation and a Novel Multi-Center Dataset
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Electronic Science and Technology of China（电子科技大学）；West China Hospital, Sichuan University（四川大学华西医院）；Chengdu First People’s Hospital（成都市第一人民医院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；The Hong Kong University of Science and Technology（香港科技大学）
Hongqiu Wang, Xiangde Luo, Wu Chen, Qingqing Tang, Mei Xin, Qiong Wang, Lei Zhu
Accurate vessel segmentation in Ultra-Wide-Field Scanning Laser Ophthalmoscopy (UWF-SLO) images is crucial for diagnosing retinal diseases. Although recent techniques have shown encouraging outcomes in vessel segmentation, models trained on one medical dataset often underperform on others due to domain shifts. Meanwhile, manually labeling high-resolution UWF-SLO images is an extremely challenging, time-consuming and expensive task. In response, this study introduces a pioneering framework that leverages a patch-based active domain adaptation approach. By actively recommending a few valuable image patches by the devised Cascade Uncertainty-Predominance (CUP) selection strategy for labeling and model-finetuning, our method significantly improves the accuracy of UWF-SLO vessel segmentation across diverse medical centers. In addition, we annotate and construct the first Multi-center UWF-SLO Vessel Segmentation (MU-VS) dataset to promote this topic research, comprising data from multiple institutions. This dataset serves as a valuable resource for cross-center evaluation, verifying the effectiveness and robustness of our approach. Experimental results demonstrate that our approach surpasses existing domain adaptation and active learning methods, considerably reducing the gap between the Upper and Lower bounds with minimal annotations, highlighting our method's practical clinical value. We will release our dataset and code to facilitate relevant research: https://github.com/whq-xxh/SFADA-UWF-SLO.
Choroidal Vessel Segmentation on Indocyanine Green Angiography Images via Human-in-the-Loop Labeling
School of Optometry, The Hong Kong Polytechnic University（香港理工大学眼科视光学院）；Research Centre for SHARP Vision, The Hong Kong Polytechnic University（香港理工大学SHARP视觉研究中心）；Centre for Eye and Vision Research (CEVR)（眼科与视觉研究中心）；Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital（澳大利亚眼科研究中心，皇家维多利亚眼耳医院）；Department of Surgery (Ophthalmology), The University of Melbourne（墨尔本大学外科学系（眼科学））
UWAFA-GAN: Ultra-Wide-Angle Fluorescein Angiography Transformation via Multi-scale Generation and Registration Enhancement
Hangzhou Dianzi University（杭州电子科技大学）；Southern University of Science and Technology（南方科技大学）；Shenzhen University（深圳大学）；Misr Higher Institute for Commerce and Computers（米斯尔高等商务与计算机学院）
University of Bournemouth（伯恩茅斯大学）；IDIAP Research Institute（IDIAP研究所）；École de Technolgie Superieure de Montréal（蒙特利尔高等技术学院）；Diagnos Inc.（Diagnos公司）；CRCHUM University of Montreal Hospital Centre（蒙特利尔大学医院研究中心）
The segmentation of the retinal vasculature from eye fundus images represents one of the most fundamental tasks in retinal image analysis. Over recent years, increasingly complex approaches based on sophisticated Convolutional Neural Network architectures have been slowly pushing performance on well-established benchmark datasets. In this paper, we take a step back and analyze the real need of such complexity. Specifically, we demonstrate that a minimalistic version of a standard U-Net with several orders of magnitude less parameters, carefully trained and rigorously evaluated, closely approxi…
Hull First, Wake Second: Wake-Reliance Suppression for Robust Maritime Vessel Detection
University of Shanghai for Science and Technology（上海理工大学）；University of Science and Technology Liaoning（辽宁科技大学）；The Australian National University（澳大利亚国立大学）；Fujian University of Technology（福建理工大学）
State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs. In this paper, we introduce a novel recurrent U-Net architecture that preserves the compactness of the original U-Net, while substantially increasing its performance to the point where it outperforms the state of the art on several benchmarks. We will demonstrate its effectiveness for several tasks, including hand segmentation, retina vessel segmentation, and road segmentation. We also introduce a large-s…
Budapest University of Technology and Economics（布达佩斯技术与经济大学）；Jiangxi Normal University（江西师范大学）；Eötvös Loránd University（厄特沃什·罗兰大学）；Shenyang Aerospace University（沈阳航空航天大学）
Retinal vessel segmentation plays an imaportant role in the field of retinal image analysis because changes in retinal vascular structure can aid in the diagnosis of diseases such as hypertension and diabetes. In recent research, numerous successful segmentation methods for fundus images have been proposed. But for other retinal imaging modalities, more research is needed to explore vascular extraction. In this work, we propose an efficient method to segment blood vessels in Scanning Laser Ophthalmoscopy (SLO) retinal images. Inspired by U-Net, "feature map reuse" and residual learning, we pro…
Deakin University（迪肯大学）；COMSATS University Islamabad（伊斯兰堡通信卫星大学）
Over recent years, increasingly complex approaches based on sophisticated convolutional neural network architectures have been slowly pushing performance on well-established benchmark datasets. In this paper, we take a step back to examine the real need for such complexity. We present RC-Net, a fully convolutional network, where the number of filters per layer is optimized to reduce feature overlapping and complexity. We also used skip connections to keep spatial information loss to a minimum by keeping the number of pooling operations in the network to a minimum. Two publicly available retina…
Queen Mary University of London（伦敦玛丽女王大学）；Barts Health NHS Trust（巴特国民保健信托基金会）
X-ray coronary angiography (XCA) is used to assess coronary artery disease and provides valuable information on lesion morphology and severity. However, XCA images are 2D and therefore limit visualisation of the vessel. 3D reconstruction of coronary vessels is possible using multiple views, however lumen border detection in current software is performed manually resulting in limited reproducibility and slow processing time. In this study we propose 3DAngioNet, a novel deep learning (DL) system that enables rapid 3D vessel mesh reconstruction using 2D XCA images from two views. Our approach lea…
Explainable Convolutional Neural Networks for Retinal Fundus Classification and Cutting-Edge Segmentation Models for Retinal Blood Vessels from Fundus Images
Ahsanullah University of Science and Technology（阿萨努拉科技大学）
The Computer-Assisted Diagnosis systems could save workloads and give objective diagnostic to ophthalmologists. At first, feature extraction is a fundamental step. One of these retinal features is the fovea. The fovea is a small fossa on the fundus. The main vessels diverge from the optic nerve head and follow a specific course that can be geometrically modeled as a parabola, with a common vertex inside the optic nerve head and the fovea located along the apex of this parabola curve. Therefore, based on this assumption, the main retinal blood vessels are segmented and fitted to a parabolic mod…
SLOctolyzer: Fully automatic analysis toolkit for segmentation and feature extracting in scanning laser ophthalmoscopy images
University of Edinburgh（爱丁堡大学）；Institute for Regeneration and Repair, University of Edinburgh（爱丁堡大学再生与修复研究所）；Centre for Medical Informatics, University of Edinburgh（爱丁堡大学医学信息学中心）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）；Clinical Research Facility and Imaging, University of Edinburgh（爱丁堡大学临床研究设施与影像中心）；School of Mathematics, University of Edinburgh（爱丁堡大学数学学院）；Institute for Adaptive and Neural Computation, School of Informatics, University of Edinburgh（爱丁堡大学信息学院自适应与神经计算研究所）；Centre for Clinical Brain Sciences, University of Edinburgh（爱丁堡大学临床脑科学中心）
OCTolyzer: Fully automatic toolkit for segmentation and feature extracting in optical coherence tomography and scanning laser ophthalmoscopy data
University of Edinburgh（爱丁堡大学）；Institute for Regeneration and Repair（再生与修复研究所）；Glasgow Caledonian University（格拉斯哥卡利多尼亚大学）；British Heart Foundation Centre for Cardiovascular Science（英国心脏基金会心血管科学中心）；Clinical Research Facility and Imaging（临床研究设施与影像中心）；Centre for Clinical Brain Sciences（临床脑科学中心）；School of Informatics（信息学院）；Institute for Adaptive and Neural Computation（自适应与神经计算研究所）；School of Mathematics（数学学院）
Robust Real-time Segmentation of Bio-Morphological Features in Human Cherenkov Imaging during Radiotherapy via Deep Learning
Dartmouth College（达特茅斯学院）；Dartmouth Health（达特茅斯医疗）；NVIDIA Corporation（英伟达公司）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；University of Missouri-Columbia（密苏里大学哥伦比亚分校）
