Annotating multiple organs in 3D medical images is time-consuming and costly. Meanwhile, there exist many single-organ datasets with one specific organ annotated. This paper investigates how to learn a multi-organ segmentation model leveraging a set of binary-labeled datasets. A novel Multi-teacher Single-student Knowledge Distillation (MS-KD) framework is proposed, where the teacher models are pre-trained single-organ segmentation networks, and the student model is a multi-organ segmentation network. Considering that each teacher focuses on different organs, a region-based supervision method, consisting of logits-wise supervision and feature-wise supervision, is proposed. Each teacher supervises the student in two regions, the organ region where the teacher is considered as an expert and the background region where all teachers agree. Extensive experiments on three public single-organ datasets and a multi-organ dataset have demonstrated the effectiveness of the proposed MS-KD framework.
Deep Mutual Learning among Partially Labeled Datasets for Multi-Organ Segmentation
Digital Medical Research Center, School of Basic Medical Science, Fudan University(复旦大学基础医学院数字医学研究中心);Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention(上海市医学影像计算与计算机辅助介入重点实验室)
Multi-organ Segmentation via Co-training Weight-averaged Models from Few-organ Datasets
SenseTime Research(商汤科技研究院);School of Information Science and Engineering at Shandong Normal University(山东师范大学信息科学与工程学院);CUHK-SenseTime Joint Laboratory, The Chinese University of Hong Kong(香港中文大学-商汤科技联合实验室)
Continual Segment: Towards a Single, Unified and Accessible Continual Segmentation Model of 143 Whole-body Organs in CT Scans
DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);Hupan Lab(湖畔实验室);University at Buffalo(布法罗大学);Sichuan Cancer Hospital(四川省肿瘤医院);The First Affiliated Hospital of Zhejiang University(浙江大学医学院附属第一医院)
Rethinking Barely-Supervised Volumetric Medical Image Segmentation from an Unsupervised Domain Adaptation Perspective
School of Computer Science and Engineering, Northeastern University(东北大学计算机科学与工程学院);Alberta Machine Intelligence Institute, University of Alberta(阿尔伯塔大学阿尔伯塔机器智能研究所)
A Knowledge Distillation framework for Multi-Organ Segmentation of Medaka Fish in Tomographic Image
RPTU Kaiserslautern-Landau(莱茵兰-普法尔茨州凯泽斯劳滕-兰道应用技术大学);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Heidelberg University(海德堡大学);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI))
Unsupervised Adversarial Domain Adaptation for Uterine layer Segmentation: From Labeled Cine to Unlabeled Dynamic EPI MRI
Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg(埃尔朗根-纽伦堡大学弗里德里希-亚历山大分校埃尔朗根大学医院放射学研究所);CAIMED(CAIMED机构);L3S(L3S机构);Institut für Informationsverarbeitung, Leibniz University Hannover(汉诺威莱布尼茨大学信息处理研究所)
A Labeled Array Distance Metric for Measuring Image Segmentation Quality
SEE-Insight Research Lab, Michigan State University, East Lansing, MI, USA(密歇根州立大学SEE-Insight研究实验室);University of Wisconsin–Madison(威斯康星大学麦迪逊分校);Smith College(史密斯学院)
Foundation Model-guided Iteratively Prompting and Pseudo-Labeling for Partially Labeled Medical Image Segmentation
Department of Biomedical Engineering, Columbia University(哥伦比亚大学生物医学工程系);Department of Radiation Oncology, Columbia University Irving Medical Center(哥伦比亚大学欧文医学中心放射肿瘤科);Data Science Institute, Columbia University(哥伦比亚大学数据科学研究所);Herbert Irving Comprehensive Cancer Center, Columbia University(哥伦比亚大学赫伯特·欧文综合癌症中心);Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院放射肿瘤科)
GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference
Shenzhen Microbt Electronics Technology Co., Ltd(深圳比特微电子科技有限公司);Tencent Jarvis Lab(腾讯贾维斯实验室);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Xiamen University(厦门大学);National Center for Artificial Intelligence, Saudi Data and Artificial Intelligence Authority(沙特数据和人工智能管理局国家人工智能中心)
Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos
University of Texas at Arlington(德克萨斯大学阿灵顿分校)
本文重点关注弱标记教学视频中的任务识别和动作分割,其中在训练期间仅提供视频级动作的有序序列。我们提出了一个双流框架,它利用语义和时间层次结构来识别教学视频中的顶级任务。此外,我们提出了一种新的自上而下的弱监督动作分割方法,其中预测任务用于约束细粒度动作序列的推理。在流行的Breakfast and Cooking 2数据集上的实验结果表明,我们的双流分层任务建模在所有数据集和指标的顶级任务识别中显着优于现有方法。此外,在所提出的自上而下的动作分割方法中使用我们的任务识别框架,始终提高了最新技术水平,同时还将分割推理时间减少了80- 90%。
ThreshGuide: Class-Aware Labeled-Guided Thresholding for Semi-Supervised 3D Abdominal Multi-Organ Segmentation
School of Intelligent Science and Technology, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(中国科学院大学杭州高等研究院智能科学与技术学院)
Tailored Multi-Organ Segmentation with Model Adaptation and Ensemble
Zhejiang University(浙江大学);Suzhou Institute for Advanced Research, University of Science and Technology of China(中国科学技术大学苏州高等研究院);Ritsumeikan University(立命馆大学);University of Science and Technology of China(中国科学技术大学)
GuidedNet: Semi-Supervised Multi-Organ Segmentation via Labeled Data Guide Unlabeled Data
Beihang University(北京航空航天大学);University of Chinese Academy of Sciences(中国科学院大学);Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(中国科学院大学杭州高等研究院);University of Science and Technology Beijing(北京科技大学)
EventSSEG: Event-driven Self-Supervised Segmentation with Probabilistic Attention
Defence Research and Development Organization, Bangalore and Indian Institute of Science, Bangalore(国防研究与发展组织、班加罗尔和印度科学学院,班加罗尔);Department of Electronics Systems Engineering, Indian Institute of Science, Bangalore(电子系统工程系,印度科学学院,班加罗尔)
Multi-site Organ Segmentation with Federated Partial Supervision and Site Adaptation
Beijing UCAS Space Technology Co., Ltd.(北京国科大空间技术有限公司);University of Science and Technology of China(中国科学技术大学);Institute of Computing Technology, CAS(中国科学院计算技术研究所)
Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation
School of Computer Science, Wuhan University(武汉大学计算机学院);School of Artificial Intelligence, Wuhan University(武汉大学人工智能学院);School of Computer Science and Technology, Hainan University(海南大学计算机科学与技术学院);School of Electronic Information, Wuhan University(武汉大学电子信息学院);State Key Lab. of LIESMARS, Wuhan University(武汉大学LIESMARS国家重点实验室);Institute for Math & AI, Wuhan University(武汉大学数学与人工智能研究院)
The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation
NAVER Cloud(NAVER云);KAIST(韩国科学技术院);NAVER AI Lab(NAVER人工智能实验室)
在本文中,我们介绍了一种新的学习计划命名为弱半监督实例分割(WSSIS)与点标签的高效和高性能的实例分割。也就是说,我们考虑一个数据集设置由一些完全标记的图像和大量的点标记的图像。半监督方法的主要挑战主要来自假阴性和假阳性实例建议之间的权衡,我们提出了一种WSSIS方法,可以有效地利用对数据库友好的点标签作为强大的弱监督源来解决这一挑战。此外,为了处理完全标记的数据量非常有限的困难情况,我们提出了一个MaskRefineNet,它可以细化粗糙掩码中的噪声。我们在COCO和BDD100K数据集上进行了广泛的实验,所提出的方法取得了与完全监督模型相当的有希望的结果,即使有50%的完全标记的COCO数据(38.8% vs. 39.7%)。此外,当使用低至5%的完全标记的COCO数据时,我们的方法显示出比最先进的半监督学习方法(33.7% vs. 24.9%)显著优越的性能。该代码可在https://github.com/clovaai/PointWSSIS上获得。