UCS: A Universal Model for Curvilinear Structure Segmentation
School of Computer Science and Technology, Wuhan University of Science and Technology(武汉理工大学计算机科学与技术学院);Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology(湖北省智能信息处理与实时工业系统重点实验室);Institute for Infocomm Research (I 2 R), Agency for Science, Technology and Research (A*STAR)(信息与通信研究所以及科技研究局)
Kai Zhu, Li Chen, Dianshuo Li, Yunxiang Cao, Jun Cheng
Curvilinear structure segmentation (CSS) is essential in various domains, including medical imaging, landscape analysis, industrial surface inspection, and plant analysis. While existing methods achieve high performance within specific domains, their generalizability is limited. On the other hand, large-scale models such as Segment Anything Model (SAM) exhibit strong generalization but are not optimized for curvilinear structures. Existing adaptations of SAM primarily focus on general object segmentation and lack specialized design for CSS tasks. To bridge this gap, we propose the Universal Curvilinear structure Segmentation (UCS) model, which adapts SAM to CSS tasks while further enhancing its cross-domain generalization. UCS features a novel encoder architecture integrating a pretrained SAM encoder with two innovations: a Sparse Adapter, strategically inserted to inherit the pre-trained SAM encoder's generalization capability while minimizing the number of fine-tuning parameters, and a Prompt Generation module, which leverages Fast Fourier Transform with a high-pass filter to generate curve-specific prompts. Furthermore, the UCS incorporates a mask decoder that eliminates reliance on manual interaction through a dual-compression module: a Hierarchical Feature Compression module, which aggregates the outputs of the sampled encoder to enhance detail preservation, and a Guidance Feature Compression module, which extracts and compresses image-driven guidance features. Evaluated on a comprehensive multi-domain dataset, including an in-house dataset covering eight natural curvilinear structures, UCS demonstrates state-of-the-art generalization and open-set segmentation performance across medical, engineering, natural, and plant imagery, establishing a new benchmark for universal CSS. The source code is available at https://github.com/kylechuuuuu/UCS.
CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging
Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences(中国科学院宁波材料技术与工程研究所慈溪生物医学工程研究所);Inception Institute of Artificial Intelligence(起源人工智能研究院);Edge Hill University(边山大学);UBTech Research, UBTech Robotics Corp Ltd(优必选机器人有限公司优必选研究院);University of Liverpool(利物浦大学);Wuhan University of Science and Technology(武汉科技大学)
Curvilinear object segmentation in medical images based on ODoS filter and deep learning network
School of Electrical and Automation Engineering, East China Jiaotong University(华东交通大学电气与自动化工程学院);School of Computer Science, Northwestern Polytechnical University(西北工业大学计算机学院);School of Software, East China Jiaotong University(华东交通大学软件学院)
Detection of curved lines with B-COSFIRE filters: A case study on crack delineation
Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen(格罗宁根大学约翰·伯努利数学与计算机科学研究所);Intelligent Computer Systems, University of Malta(马耳他大学智能计算机系统研究所)
From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation
Center for Big Data and Intelligent Medicine, The First Affiliated Hospital of Chongqing Medical University(重庆医科大学附属第一医院大数据与智能医学中心);Key Laboratory of Digital Health and Intelligent Medicine, Chongqing Municipal Health Commission(重庆市卫生健康委员会数字健康与智能医学重点实验室);Chongqing Translational Medicine Center(重庆市转化医学中心);College of Computer Science, Chongqing University(重庆大学计算机学院)
Uncertainty-aware Cross-training for Semi-supervised Medical Image Segmentation
School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院);Institute of High Performance Computing, A*STAR(A*STAR高性能计算研究所);School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);School of Artificial Intelligence and Computer Science, Jiangnan University(江南大学人工智能与计算机科学学院)
A novel attention mechanism for noise-adaptive and robust segmentation of microtubules in microscopy images
CNRS, Univ. Rennes, IGDR (Institut de Génétique et Développement de Rennes), UMR6290(法国里昂大学CNRS、里昂大学、里昂遗传与发育研究所(Institut de Génétique et Développement de Rennes));TIAD Laboratory, Sciences and Technology Faculty, Sultan Moulay Slimane Univ.(摩洛哥苏丹穆莱·斯利曼大学科技与科学学院TIAD实验室);IRMAR – UMR 6625(法国里昂大学IRMAR研究所(UMR 6625))
Frenet-Serret Frame-based Decomposition for Part Segmentation of 3D Curvilinear Structures
John A. Paulson School of Engineering and Applied Sciences, Harvard University(哈佛大学约翰·A·保罗森工程与应用科学学院);Boston College(波士顿学院);Université de Montréal(蒙特利尔大学);Swiss Federal Institute of Technology Lausanne(瑞士洛桑联邦理工学院);Carnegie Mellon University(卡内基梅隆大学);Department of Molecular and Cellular Biology, Harvard University(哈佛大学分子与细胞生物学系)
John Hopkins University(约翰霍普金斯大学);University of Bologna(博洛尼亚大学);Italian Institute of Technology(意大利技术研究院);University of California, San Francisco(旧金山大学);University of California, Berkeley(伯克利大学);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)
CurvSegFlow: Time-Conditioned Flow Matching for Robust Segmentation of Curvilinear Structures in Noisy Biomedical Images
CNRS, Univ. Rennes, Institute of Genetics and Development of Rennes (IGDR)(法国国家科学研究中心、雷恩大学、雷恩遗传与发育研究所);TIAD Laboratory, Sciences and Technology Faculty, Sultan Moulay Slimane Univ(苏丹穆莱·斯利曼大学科学与技术学院TIAD实验室);Institute of Biotechnology, Czech Academy of Sciences(捷克科学院生物技术研究所)
Segmentation of 3D pore space from CT images using curvilinear skeleton: application to numerical simulation of microbial decomposition
IRD(法国发展研究院);UMMISCO(复杂系统数学与信息建模单元);Cadi Ayyad University(卡迪·阿亚德大学);Faculty of Sciences Semlalia(塞姆拉利亚科学学院);LIB(自由研究所);UFR Sciences et Techniques(科学与技术培训与研究单位);University of Burgundy(勃艮第大学);INRA(法国国家农业研究院)
OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation
Vidyasirimedhi Institute of Science & Technology(维迪亚西里梅迪科技学院);Kamnoetvidya Science Academy(卡姆诺维迪亚科学学院);Ningbo Institute of Industrial Technology, Chinese Academy of Sciences(中国科学院宁波工业技术研究院);Cixi Institute of Biomedical Engineering(慈溪生物医学工程研究所);Kasetsart University(泰国农业大学);Nanyang Technological University(南洋理工大学)
虽然已经有越来越多的研究使用深度学习技术从2D en face OCTA中提取血管结构,但对于这种方法,已知在曲线结构(如视网膜血管系统)上的数据注释过程非常昂贵和耗时,尽管很少有人尝试解决注释问题。在这项工作中,我们提出了应用基于涂鸦的弱监督学习方法来自动化像素级注释。所提出的方法称为OCTAve,它将弱监督学习与对抗性和新颖的自监督深度监督相结合,使用涂鸦注释的地面实况增强。我们的新机制被设计为利用来自UNet类架构的鉴别层的鉴别输出,其中聚合鉴别输出和分割图谓词之间的Kullback-Liebler分歧在训练期间被最小化。实验结果表明,这种组合方法可以更好地定位血管结构。我们在大型公共数据集上验证了我们提出的方法,即,玫瑰,OCTA-500。的分割性能进行比较,对两个国家的最先进的全监督和基于涂鸦的弱监督的方法。我们在实验中使用的工作的实现位于[LINK]。
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)
DeepBranchTracer: A Generally-Applicable Approach to Curvilinear Structure Reconstruction Using Multi-Feature Learning
Qiushi Academy for Advanced Studies, Zhejiang University(浙江大学求是高等研究院);College of Computer Science and Techology, Zhejiang University(浙江大学计算机科学与技术学院);State Key Lab of Brain-Machine Intelligence, Zhejiang University(浙江大学脑机智能国家重点实验室);CCAI by MOE and Zhejiang Provincial Government(ZJU)(教育部与浙江省政府共建人工智能协同创新中心(浙江大学))
Curvature Integration in a 5D Kernel for Extracting Vessel Connections in Retinal Images
Eindhoven University of Technology(埃因霍温理工大学);École des Hautes Études en Sciences Sociales(社会科学高等学院);University of Bologna(博洛尼亚大学);Northeastern University(东北大学)
Improving Generalization of Deep Learning for Brain Metastases Segmentation Across Institutions
Peking University Health Science Center(北京大学医学部);Beijing Key Laboratory of Intelligent Neuromodulation and Brain Disorder Treatment(北京智能神经调控与脑疾病治疗重点实验室);University Hospital Erlangen(埃尔朗根大学医院)