Institut de Robotica i Informatica Industrial, UPC(加泰罗尼亚理工大学工业机器人与计算机研究所);Universitat Pompeu Fabra(庞培法布拉大学);MPI-CBG(马克斯·普朗克分子细胞生物学与遗传学研究所);Janelia Research Campus(珍妮利亚研究园区)
Jan Funke, Chong Zhang, Tobias Pietzsch, Stephan Saalfeld
Two successful approaches for the segmentation of biomedical images are (1) the selection of segment candidates from a merge-tree, and (2) the clustering of small superpixels by solving a Multi-Cut problem. In this paper, we introduce a model that unifies both approaches. Our model, the Candidate Multi-Cut (CMC), allows joint selection and clustering of segment candidates from a merge-tree. This way, we overcome the respective limitations of the individual methods: (1) the space of possible segmentations is not constrained to candidates of a merge-tree, and (2) the decision for clustering can be made on candidates larger than superpixels, using features over larger contexts. We solve the optimization problem of selecting and clustering of candidates using an integer linear program. On datasets of 2D light microscopy of cell populations and 3D electron microscopy of neurons, we show that our method generalizes well and generates more accurate segmentations than merge-tree or Multi-Cut methods alone.
CellTrack R-CNN: A Novel End-To-End Deep Neural Network for Cell Segmentation and Tracking in Microscopy Images
University of Sydney(悉尼大学);University of New South Wales(新南威尔士大学);Brigham and Women’s Hospital(布莱根妇女医院);Harvard Medical School(哈佛医学院);Sydney Nano Institute(悉尼纳米研究所)
Neural Cellular Automata for Weakly Supervised Segmentation of White Blood Cells
Institute of AI for Health, Helmholtz Zentrum München – German Research Center for Environmental Health(人工智能与健康研究所,慕尼黑德国环境健康研究中心);TUM School of Computation, Information and Technology, Technical University Munich(技术大学慕尼黑计算、信息与技术学院);Institute of Chemical Epigenetics, Faculty of Chemistry and Pharmacy, Ludwig Maximilian University(化学表观遗传学研究所,路德维希-马克西米利安大学);Computer Aided Medical Procedures, Technical University of Munich(医学辅助程序研究所,技术大学慕尼黑)
CellPilot: A unified approach to automatic and interactive segmentation in histopathology
School of Computation and Information Technology, Technical University of Munich(慕尼黑工业大学计算与信息技术学院);Helmholtz Zentrum München - German Research Center for Environmental Health(亥姆霍兹慕尼黑中心——德国环境健康研究中心);School of Biomedical Engineering and Imaging Sciences, King’s College London(伦敦国王学院生物医学工程与影像科学学院)
CellGenNet: A Knowledge-Distilled Framework for Robust Cell Segmentation in Cancer Tissues
a College of Computing, Georgia Institute of Technology, Atlanta, GA, USA b Department of Pediatrics, Emory University, Atlanta, GA, USA c Departments of Radiology \& Imaging Sciences, Emory University, Atlanta, GA, USA d Department of Biomedical Engineering, Emory University \& Georgia Institute of Technology, Atlanta, GA, USA e School of Electrical
Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized Proteins
University of Freiburg(弗莱堡大学);Signalling Research Centres BIOSS and CIBSS(BIOSS与CIBSS信号研究中心);Heidelberg Biosciences International Graduate School (HBIGS)(海德堡生物科学国际研究生院(HBIGS))
Cyto R-CNN and CytoNuke Dataset: Towards reliable whole-cell segmentation in bright-field histological images
University Hospital RWTH Aachen(亚琛工业大学医院);Institute of Medical Informatics, University Hospital RWTH Aachen(亚琛工业大学医院医学信息学研究所);Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen (AöR)(埃森大学医院(公法法人)医学人工智能研究所);Cancer Research Center Cologne Essen (CCCE), West German Cancer Center Essen, University Hospital Essen (AöR)(埃森大学医院(公法法人)科隆埃森癌症研究中心(CCCE)、西德埃森癌症中心);Institute of Pathology, University Hospital RWTH Aachen(亚琛工业大学医院病理学研究所);Institute of Pathology, Ludwig Maximilian University of Munich(慕尼黑大学病理学研究所)
IRNet: Instance Relation Network for Overlapping Cervical Cell Segmentation
The Chinese University of Hong Kong(香港中文大学);Imsight Medical Technology, Co., Ltd.(视见医疗科技有限公司);Imperial College London(帝国理工学院);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
InstanSeg: an embedding-based instance segmentation algorithm optimized for accurate, efficient and portable cell segmentation
School of Informatics, University of Edinburgh(爱丁堡大学信息学院);Centre for Genomic and Experimental Medicine, Institute of Genetics and Cancer, University of Edinburgh(爱丁堡大学遗传学与癌症研究所基因组与实验医学中心);Flow Cytometry Core Facility, Newcastle University(纽卡斯尔大学流式细胞术核心实验室);Edinburgh Pathology and CRUK Scotland Centre, Institute of Genetics and Cancer, The University of Edinburgh(爱丁堡大学遗传学与癌症研究所爱丁堡病理与英国癌症研究中心苏格兰分部)
CellMixer: Annotation-free Semantic Cell Segmentation of Heterogeneous Cell Populations
University of Freiburg(弗赖堡大学);Collaborative Research Institute Intelligent Oncology (CRIION)(智能肿瘤学合作研究所(CRIION));University Medical Center Freiburg(弗赖堡大学医学中心);University of Buenos Aires(布宜诺斯艾利斯大学);BrainLinks-BrainTools(脑连接-脑工具研究所)
EmbedTrack -- Simultaneous Cell Segmentation and Tracking Through Learning Offsets and Clustering Bandwidths
Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院自动化与应用信息研究所);Institute of Biological and Chemical Systems - Biological Information Processing, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院生物与化学系统研究所——生物信息处理分部)
CellVTA: Enhancing Vision Foundation Models for Accurate Cell Segmentation and Classification
ShanghaiTech University(上海科技大学);Shanghai Ocean University(上海海洋大学);Shanghai Engineering Research Center of Intelligent Vision and Imaging(上海智能视觉与成像工程技术研究中心)
Unsupervised cell segmentation by fast Gaussian Processes
Department of Statistics and Applied Probability, University of California, Santa Barbara, CA(统计与应用概率系,加州大学圣芭芭拉分校);Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA(电气与计算机工程系,加州大学圣芭芭拉分校)
CellViT++: Energy-Efficient and Adaptive Cell Segmentation and Classification Using Foundation Models
Institute for AI in Medicine (IKIM), University Hospital Essen (AöR)(埃森大学医院AI医学研究所(IKIM));Cancer Research Center Cologne Essen (CCCE), West German Cancer Center Essen, University Hospital Essen (AöR)(埃森大学医院德国西部癌症中心科隆-埃森癌症研究中心(CCCE));TU Dortmund University(多特蒙德工业大学);Institute of Pathology, University Hospital Essen (AöR)(埃森大学医院病理学研究所);German Cancer Consortium (DKTK, Partner site Essen)(德国癌症联盟(DKTK,埃森合作站点))
Learning with minimal effort: leveraging in silico labeling for cell and nucleus segmentation
PSL University(巴黎文理研究大学);Mines Paris(巴黎矿业学院);Centre for Computational Biology(计算生物学中心);Institut Curie(居里研究所);INSERM(法国国家健康与医学研究院);University of Montpellier(蒙彼利埃大学);IGH(人类遗传学研究所);CNRS(法国国家科学研究中心)
CNN-based Preprocessing to Optimize Watershed-based Cell Segmentation in 3D Confocal Microscopy Images
RWTH Aachen University(亚琛工业大学);Brazilian Center for Research in Energy and Materials(巴西能源与材料研究中心);Brazilian Synchrotron Light Laboratory(巴西同步加速器光实验室);Howard Hughes Medical Institute(霍华德·休斯医学研究所)
Practical Guidelines for Cell Segmentation Models Under Optical Aberrations in Microscopy
The Fifth Affiliated Hospital of Wenzhou Medical University(温州医科大学附属第五医院);Tsinghua University(清华大学);Hangzhou Dianzi University(杭州电子科技大学);Shandong University(山东大学)
Single Tensor Cell Segmentation using Scalar Field Representations
Centro de Informática, Universidade Federal de Pernambuco, Brazil(巴西佩鲁巴伦斯联邦大学计算机中心);Center for Image Analysis, Beckman Institute, California Institute of Technology, USA(美国加利福尼亚理工学院图像分析中心)
Glioma C6: A Novel Dataset for Training and Benchmarking Cell Segmentation
Pavlov Institute of Physiology, Russian academy of science(俄罗斯科学院帕夫洛夫生理研究所);Saint-Petersburg State University of Aerospace Instrumentation(圣彼得堡航空航天仪器州大学);Institute of Physiology, NAS of Belarus(白俄罗斯国家科学院生理研究所)
Med-NCA: Robust and Lightweight Segmentation with Neural Cellular Automata
Darmstadt University of Technology(达姆施塔特工业大学)
在使用深度学习执行医学图像分割时,访问适当的基础设施至关重要。这一要求使得在资源有限的情况下,如农村地区和危机期间的初级保健设施,很难运行最先进的细分模型。最近新兴的神经元胞自动机(NCA)领域已经表明,局部相互作用的单细胞模型可以在低分辨率输入的图像生成或分割等任务中取得有竞争力的结果。然而,它们受到高VRAM要求和难以达到高分辨率图像的收敛的限制。为了克服这些限制,我们提出了Med-NCA,一个用于高分辨率图像分割的端到端NCA训练管道。我们的方法遵循两个步骤的过程。全局知识首先在缩小的图像中的细胞之间进行通信。之后,执行基于块的分割。我们提出的Med-NCA在海马和前列腺分割方面分别比经典的UNet好2%和3%,同时也小了500倍。我们还表明,Med-NCA是通过设计不变的图像尺度,形状和平移,经历只有轻微的性能下降,即使有很强的转变,是强大的MRI采集伪影。Med-NCA甚至可以在Raspberry Pi B+上实现高分辨率医学图像分割,Raspberry Pi B+可以说是能够运行PyTorch的最小设备,并且可以由标准电源供电。
Search for temporal cell segmentation robustness in phase-contrast microscopy videos
Universidad Carlos III de Madrid(马德里卡洛斯三世大学);AtlasXomics Inc.(AtlasXomics 公司);Albert-Ludwigs-University(阿尔伯特-路德维希大学);The Johns Hopkins University(约翰斯·霍普金斯大学)