Vessel-CAPTCHA: an efficient learning framework for vessel annotation and segmentation
EURECOM（法国通信系统工程师学校与研究中心）；Universitat de Barcelona（巴塞罗那大学）；University College London（伦敦大学学院）；Politecnico di Torino（都灵理工大学）；Université Côte d’Azur（蔚蓝海岸大学）；Inria（法国国家信息与自动化研究所）；National Institute for Health Research（英国国家卫生研究院）；University College London Hospitals（伦敦大学学院医院）
Vien Ngoc Dang, Francesco Galati, Rosa Cortese, Giuseppe Di Giacomo, Viola Marconetto, Prateek Mathur, Karim Lekadir, Marco Lorenzi, Ferran Prados, Maria A. Zuluaga
Deep learning techniques for 3D brain vessel image segmentation have not been as successful as in the segmentation of other organs and tissues. This can be explained by two factors. First, deep learning techniques tend to show poor performances at the segmentation of relatively small objects compared to the size of the full image. Second, due to the complexity of vascular trees and the small size of vessels, it is challenging to obtain the amount of annotated training data typically needed by deep learning methods. To address these problems, we propose a novel annotation-efficient deep learning vessel segmentation framework. The framework avoids pixel-wise annotations, only requiring weak patch-level labels to discriminate between vessel and non-vessel 2D patches in the training set, in a setup similar to the CAPTCHAs used to differentiate humans from bots in web applications. The user-provided weak annotations are used for two tasks: 1) to synthesize pixel-wise pseudo-labels for vessels and background in each patch, which are used to train a segmentation network, and 2) to train a classifier network. The classifier network allows to generate additional weak patch labels, further reducing the annotation burden, and it acts as a noise filter for poor quality images. We use this framework for the segmentation of the cerebrovascular tree in Time-of-Flight angiography (TOF) and Susceptibility-Weighted Images (SWI). The results show that the framework achieves state-of-the-art accuracy, while reducing the annotation time by ~77% w.r.t. learning-based segmentation methods using pixel-wise labels for training.
Availability of domain-specific datasets is an essential problem in object detection. Maritime vessel detection of inshore and offshore datasets is no exception, there is a limited number of studies addressing this need. For that reason, we collected a dataset of images of maritime vessels taking into account different factors: background variation, atmospheric conditions, illumination, visible proportion, occlusion and scale variation. Vessel instances (including 9 types of vessels), seamarks and miscellaneous floaters were precisely annotated: we employed a first round of labelling and subse…
Carotid vessel wall segmentation is a crucial yet challenging task in the computer-aided diagnosis of atherosclerosis. Although numerous deep learning models have achieved remarkable success in many medical image segmentation tasks, accurate segmentation of carotid vessel wall on magnetic resonance (MR) images remains challenging, due to limited annotations and heterogeneous arteries. In this paper, we propose a semi-supervised label propagation framework to segment lumen, normal vessel walls, and atherosclerotic vessel wall on 3D MR images. By interpolating the provided annotations, we get 3D…
University of Maryland, College Park（马里兰大学帕克分校）；Intuitive Surgical, Inc（直观外科公司）
Semantic image segmentation plays an important role in modeling patient-specific anatomy. We propose a convolution neural network, called Kid-Net, along with a training schema to segment kidney vessels: artery, vein and collecting system. Such segmentation is vital during the surgical planning phase in which medical decisions are made before surgical incision. Our main contribution is developing a training schema that handles unbalanced data, reduces false positives and enables high-resolution segmentation with a limited memory budget. These objectives are attained using dynamic weighting, ran…
Hessian-Based Lightweight Neural Network HessNet for State-of-the-Art Brain Vessel Segmentation on a Minimal Training Dataset
Institute of Artificial Intelligence, M.V.Lomonosov Moscow State University（人工智能研究所，莫斯科国立大学）；Laboratory of Analysis of Semantics, Centre for Language and Semantics Technologies, Faculty of Computer Science, HSE University（语义分析实验室，语言与语义技术中心，计算机科学系，高等经济大学）；Neurosputnik LLC（Neurosputnik公司）；Mechanics and Mathematics Faculty, M.V.Lomonosov Moscow State University（力学与数学系，莫斯科国立大学）；International Laboratory of Algebraic Topology and Its Applications, Faculty of Computer Science, HSE University（国际拓扑学及其应用实验室，计算机科学系，高等经济大学）
Technical University of Munich（慕尼黑工业大学）；Imperial College London（帝国理工学院）；University of Zurich（苏黎世大学）
Optical coherence tomography angiography (OCTA) can non-invasively image the eye's circulatory system. In order to reliably characterize the retinal vasculature, there is a need to automatically extract quantitative metrics from these images. The calculation of such biomarkers requires a precise semantic segmentation of the blood vessels. However, deep-learning-based methods for segmentation mostly rely on supervised training with voxel-level annotations, which are costly to obtain. In this work, we present a pipeline to synthesize large amounts of realistic OCTA images with intrinsically matc…
YoloCurvSeg: You Only Label One Noisy Skeleton for Vessel-style Curvilinear Structure Segmentation
Southern University of Science and Technology（南方科技大学）；the University of Hong Kong（香港大学）；Jiaxing Research Institute, Southern University of Science and Technology（南方科技大学嘉兴研究院）
In interventional radiology, short video sequences of vein structure in motion are captured in order to help medical personnel identify vascular issues or plan intervention. Semantic segmentation can greatly improve the usefulness of these videos by indicating exact position of vessels and instruments, thus reducing the ambiguity. We propose a real-time segmentation method for these tasks, based on U-Net network trained in a Siamese architecture from automatically generated annotations. We make use of noisy low level binary segmentation and optical flow to generate multi class annotations that…
Shanghai Jiao Tong University（上海交通大学）；University of Electronic Science and Technology of China（电子科技大学）；SenseTime Research（商汤科技研究院）；Peking Union Medical College Hospital（北京协和医院）
The segmentation of coronary arteries in X-ray angiograms by convolutional neural networks (CNNs) is promising yet limited by the requirement of precisely annotating all pixels in a large number of training images, which is extremely labor-intensive especially for complex coronary trees. To alleviate the burden on the annotator, we propose a novel weakly supervised training framework that learns from noisy pseudo labels generated from automatic vessel enhancement, rather than accurate labels obtained by fully manual annotation. A typical self-paced learning scheme is used to make the training …
Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）
Contemporary deep learning based medical image segmentation algorithms require hours of annotation labor by domain experts. These data hungry deep models perform sub-optimally in the presence of limited amount of labeled data. In this paper, we present a data efficient learning framework using the recent concept of Generative Adversarial Networks; this allows a deep neural network to perform significantly better than its fully supervised counterpart in low annotation regime. The proposed method is an extension of our previous work with the addition of a new unsupervised adversarial loss and a …
Plant root research can provide a way to attain stress-tolerant crops that produce greater yield in a diverse array of conditions. Phenotyping roots in soil is often challenging due to the roots being difficult to access and the use of time consuming manual methods. Rhizotrons allow visual inspection of root growth through transparent surfaces. Agronomists currently manually label photographs of roots obtained from rhizotrons using a line-intersect method to obtain root length density and rooting depth measurements which are essential for their experiments. We investigate the effectiveness of …
Delineating 3D blood vessels is essential for clinical diagnosis and treatment, however, is challenging due to complex structure variations and varied imaging conditions. Supervised deep learning has demonstrated its superior capacity in automatic 3D vessel segmentation. However, the reliance on expensive 3D manual annotations and limited capacity for annotation reuse hinder the clinical applications of supervised models. To avoid the repetitive and laborious annotating and make full use of existing vascular annotations, this paper proposes a novel 3D shape-guided local discrimination model fo…
Learning Wall Segmentation in 3D Vessel Trees using Sparse Annotations
Institute of Computer-Assisted Cardiovascular Medicine, Charité - Universitätsmedizin Berlin（柏林夏里特医学院计算机辅助心血管医学研究所）；Fraunhofer MEVIS（弗劳恩霍夫梅维斯研究所）；DZHK (German Centre for Cardiovascular Research)（德国心血管研究中心）；Physikalisch-Technische Bundesanstalt（德国联邦物理技术研究院）；Medical Center—University of Freiburg, University of Freiburg（弗莱堡大学医学中心、弗莱堡大学）
Zhejiang University（浙江大学）；University of Alberta（阿尔伯塔大学）
Topological and geometrical analysis of retinal blood vessel is a cost-effective way for early detection of many common diseases. Meanwhile, automated vessel segmentation and vascular tree analysis are still lacking in terms of generalization capability. In this work, we construct a novel benchmark RETA with 81 labeled vessel masks aiming to facilitate retinal vessel analysis. A semi-automated coarse-to-fine workflow is proposed to annotating vessel pixels. During dataset construction, we strived to control inter-annotator variability and intra-annotator variability by performing multi-stage a…
Adversarial Vessel-Unveiling Semi-Supervised Segmentation for Retinopathy of Prematurity Diagnosis
Graduate Center, CUNY（纽约城市大学研究生中心）；Stony Brook University, SUNY（纽约州立大学石溪分校）；Harvard Medical School, Harvard University（哈佛大学医学院）；Chang Gung Memorial Hospital（长庚纪念医院）；Queens College, CUNY（纽约城市大学皇后学院）
VesselSim: learning 3D blood vessel segmentation without expert annotations
Department of Computer Science and Software Engineering, Concordia University, Montreal, Canada（计算机科学与软件工程系，康科迪亚大学，蒙特利尔，加拿大）；Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada（电气与计算机工程系，康科迪亚大学，蒙特利尔，加拿大）
Peking University（北京大学）；Peking University First Hospital（北京大学第一医院）；MGH/BWH Center for Clinical Data Science（麻省总医院/布莱根妇女医院临床数据科学中心）
Segmenting coronary arteries is challenging, as classic unsupervised methods fail to produce satisfactory results and modern supervised learning (deep learning) requires manual annotation which is often time-consuming and can some time be infeasible. To solve this problem, we propose a knowledge transfer based shape-consistent generative adversarial network (SC-GAN), which is an annotation-free approach that uses the knowledge from publicly available annotated fundus dataset to segment coronary arteries. The proposed network is trained in an end-to-end fashion, generating and segmenting synthe…
Simulation-Based Segmentation of Blood Vessels in Cerebral 3D OCTA Images
University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Imperial College London（伦敦帝国学院）；Technical University of Munich（慕尼黑工业大学）；University Hospital Zurich（苏黎世大学医院）；Toronto Western Hospital（多伦多西部医院）；Krembil Research Institute（克雷比尔研究所）
Scaling up fine-grained intracranial vessel annotations in computed tomography angiography
Brigham and Women’s Hospital Harvard Medical School（哈佛医学院布莱尔妇女医院）；Khoury College of Computer Sciences Northeastern University（东北大学计算机科学学院）；Washington University in St. Louis（圣路易斯华盛顿大学）；Dana-Farber Cancer Institute Harvard Medical School（哈佛医学院丹娜-法伯癌症研究院）
Robust automatic brain vessel segmentation in 3D CTA scans using dynamic 4D-CTA data
Northeastern University, Boston, USA（东北大学）；Washington University in St. Louis, St, Louis, USA（华盛顿大学）；Dana-Farber Cancer Institute, Boston, USA（达纳-法伯癌症研究所）；Brigham and Women's Hospital, Boston, USA（布里奇曼和妇女医院）；Harvard Medical School, Boston, USA（哈佛医学院）
Xiamen University（厦门大学）；Chinese PLA General Hospital（中国人民解放军总医院）；Deepwise AI Laboratory（深睿智慧人工智能实验室）
The analysis of organ vessels is essential for computer-aided diagnosis and surgical planning. But it is not a easy task since the fine-detailed connected regions of organ vessel bring a lot of ambiguity in vessel segmentation and sub-type recognition, especially for the low-contrast capillary regions. Furthermore, recent two-staged approaches would accumulate and even amplify these inaccuracies from the first-stage whole vessel segmentation into the second-stage sub-type vessel pixel-wise classification. Moreover, the scarcity of manual annotation in organ vessels poses another challenge. In …
Disconnect to Connect: A Data Augmentation Method for Improving Topology Accuracy in Image Segmentation
DTU Compute, Technical University of Denmark（丹麦技术大学DTU计算学院）；A.I. Virtanen Institute, University of Eastern Finland（东芬兰大学人工智能维尔塔宁研究所）；Aarhus University（奥胡斯大学）
Shanghai Jiao Tong University（上海交通大学）；Peking Union Medical College Hospital（北京协和医院）
The segmentation of coronary arteries by convolutional neural network is promising yet requires a large amount of labor-intensive manual annotations. Transferring knowledge from retinal vessels in widely-available public labeled fundus images (FIs) has a potential to reduce the annotation requirement for coronary artery segmentation in X-ray angiograms (XAs) due to their common tubular structures. However, it is challenged by the cross-anatomy domain shift due to the intrinsically different vesselness characteristics in different anatomical regions under even different imaging protocols. To so…
Synthetic optical coherence tomography angiographs for detailed retinal vessel segmentation without human annotations
Technical University of Munich（慕尼黑工业大学）；Imperial College London（帝国理工学院）；Helmholtz Zentrum Muenchen（亥姆霍兹慕尼黑中心）；University of Innsbruck（因斯布鲁克大学）；University of Oxford（牛津大学）；Moorfields Eye Hospital NHS Foundation Trust（摩尔菲尔德眼科医院国民保健服务基金会信托）；Boehringer Ingelheim Limited（勃林格殷格翰有限公司）；University College London（伦敦大学学院）；Cairo University（开罗大学）；Watany Eye Hospital（瓦塔尼眼科医院）；Heidelberg Engineering GmbH（海德堡工程有限公司）；University of Zurich（苏黎世大学）
University Medical Center Mannheim, Heidelberg University（海德堡大学曼海姆医学院）；Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University（海德堡大学跨学科科学计算中心（IWR））；Volume Graphics GmbH（Volume Graphics有限公司）
We address the vessel segmentation problem by building upon the multiscale feature learning method of Kiros et al., which achieves the current top score in the VESSEL12 MICCAI challenge. Following their idea of feature learning instead of hand-crafted filters, we have extended the method to learn 3D features. The features are learned in an unsupervised manner in a multi-scale scheme using dictionary learning via least angle regression. The 3D feature kernels are further convolved with the input volumes in order to create feature maps. Those maps are used to train a supervised classifier with t…
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Brigham and Women’s Hospital, Harvard Medical School（哈佛医学院布莱根妇女医院）；Tencent Jarvis Lab（腾讯天衍实验室）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Manually segmenting the hepatic vessels from Computer Tomography (CT) is far more expertise-demanding and laborious than other structures due to the low-contrast and complex morphology of vessels, resulting in the extreme lack of high-quality labeled data. Without sufficient high-quality annotations, the usual data-driven learning-based approaches struggle with deficient training. On the other hand, directly introducing additional data with low-quality annotations may confuse the network, leading to undesirable performance degradation. To address this issue, we propose a novel mean-teacher-ass…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
The difficulty of obtaining annotations to build training databases still slows down the adoption of recent deep learning approaches for biomedical image analysis. In this paper, we show that we can train a Deep Net to perform 3D volumetric delineation given only 2D annotations in Maximum Intensity Projections (MIP). As a consequence, we can decrease the amount of time spent annotating by a factor of two while maintaining similar performance. Our approach is inspired by space carving, a classical technique of reconstructing complex 3D shapes from arbitrarily-positioned cameras. We will demonst…
Convolutional neural networks have emerged as the leading method for the classification and segmentation of images. In some cases, it is desirable to focus the attention of the net on a specific region in the image; one such case is the recognition of the contents of transparent vessels, where the vessel region in the image is already known. This work presents a valve filter approach for focusing the attention of the net on a region of interest (ROI). In this approach, the ROI is inserted into the net as a binary map. The net uses a different set of convolution filters for the ROI and backgrou…
University of Rochester（罗切斯特大学）；University of Rochester Medical Center（罗切斯特大学医学中心）；Houston Methodist Hospital（休斯顿卫理公会医院）；Weill Cornell Medical College（威尔康奈尔医学院）；Retina Consultants of Houston（休斯顿视网膜顾问中心）；Blanton Eye Institute（布兰顿眼科研究所）
While recent advances in deep learning have significantly advanced the state of the art for vessel detection in color fundus (CF) images, the success for detecting vessels in fluorescein angiography (FA) has been stymied due to the lack of labeled ground truth datasets. We propose a novel pipeline to detect retinal vessels in FA images using deep neural networks that reduces the effort required for generating labeled ground truth data by combining two key components: cross-modality transfer and human-in-the-loop learning. The cross-modality transfer exploits concurrently captured CF and fundus…
RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation
The University of Queensland（昆士兰大学）；University of Technology Sydney（悉尼科技大学）；Australian National University（澳大利亚国立大学）；University of New South Wales（新南威尔士大学）；Victoria University（维多利亚大学）；Deakin University（迪肯大学）
PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation
Data and Knowledge Engineering Group, Faculty of Computer Science, Otto von Guericke University Magdeburg, Germany（数据与知识工程组，计算机科学系，奥托·冯·格里克大学马格德堡分校）；Genomics Research Centre, Human Technopole, Milan, Italy（基因组研究中心，人类技术pole，米兰，意大利）；Laboratory of Fluid Dynamics and Technical Flows, Otto von Guericke University Magdeburg, Germany（流体动力学与技术流动实验室，奥托·冯·格里克大学马格德堡分校）；Department of Biomedical Magnetic Resonance, Faculty of Natural Sciences, Otto von Guericke University Magdeburg, Germany（生物医学磁共振部门，自然科学系，奥托·冯·格里克大学马格德堡分校）；MedDigit, Department of Neurology, Medical Faculty, University Hospital, Magdeburg, Germany（MedDigit，神经病学部门，医学学院，大学医院，马格德堡，德国）；German Centre for Neurodegenerative Disease, Magdeburg, Germany（德国神经退行性疾病中心，马格德堡，德国）；Centre for Behavioural Brain Sciences, Magdeburg, Germany（行为脑科学中心，马格德堡，德国）；School of Mathematics & Statistics, UNSW Sydney and UNSW Data Science Hub（数学与统计学学院，悉尼大学和UNSW数据科学中心）
本文提出 PULASki，在 Probabilistic UNet 中引入基于统计距离的损失以建模专家标注差异，并在颅内血管和 MS 病灶任务上显著优于四种基线。
Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM)（慕尼黑工业大学医疗保健与医学人工智能教席）；TUM University Hospital（慕尼黑工业大学医院）；School of Computation, Information and Technology, TUM（慕尼黑工业大学计算、信息与技术学院）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Department of Computing, Imperial College London（伦敦帝国理工学院计算机系）；Weill Cornell Medicine, Cornell University（康奈尔大学威尔医学院）
We present TransProteus, a dataset, and methods for predicting the 3D structure, masks, and properties of materials, liquids, and objects inside transparent vessels from a single image without prior knowledge of the image source and camera parameters. Manipulating materials in transparent containers is essential in many fields and depends heavily on vision. This work supplies a new procedurally generated dataset consisting of 50k images of liquids and solid objects inside transparent containers. The image annotations include 3D models, material properties (color/transparency/roughness...), and…
RBAD: A Dataset and Benchmark for Retinal Vessels Branching Angle Detection
School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学计算与增强智能学院）；Mayo Clinic（梅奥诊所）；School of Computing, Clemson University（克莱姆森大学计算学院）；Department of Electrical and Computer Engineering, Stevens Institute of Technology（史蒂文斯理工学院电气与计算机工程系）
Accurate visualization of liver tumors and their surrounding blood vessels is essential for noninvasive diagnosis and prognosis prediction of tumors. In medical image segmentation, there is still a lack of in-depth research on the simultaneous segmentation of liver tumors and peritumoral blood vessels. To this end, we collect the first liver tumor, and vessel segmentation benchmark datasets containing 52 portal vein phase computed tomography images with liver, liver tumor, and vessel annotations. In this case, we propose a 3D U-shaped Cross-Attention Network (UCA-Net) that utilizes a tailored …
