Contrastive learning has shown great promise over annotation scarcity problems in the context of medical image segmentation. Existing approaches typically assume a balanced class distribution for both labeled and unlabeled medical images. However, medical image data in reality is commonly imbalanced (i.e., multi-class label imbalance), which naturally yields blurry contours and usually incorrectly labels rare objects. Moreover, it remains unclear whether all negative samples are equally negative. In this work, we present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation. Specifically, we first develop an iterative contrastive distillation algorithm by softly labeling the negatives rather than binary supervision between positive and negative pairs. We also capture more semantically similar features from the randomly chosen negative set compared to the positives to enforce the diversity of the sampled data. Second, we raise a more important question: Can we really handle imbalanced samples to yield better performance? Hence, the key innovation in ACTION is to learn global semantic relationship across the entire dataset and local anatomical features among the neighbouring pixels with minimal additional memory footprint. During the training, we introduce anatomical contrast by actively sampling a sparse set of hard negative pixels, which can generate smoother segmentation boundaries and more accurate predictions. Extensive experiments across two benchmark datasets and different unlabeled settings show that ACTION significantly outperforms the current state-of-the-art semi-supervised methods.
TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation
Department of Data Science and AI, Monash University（蒙纳士大学数据科学与人工智能系）；College of Computer Science, Chongqing University（重庆大学计算机学院）；Chongqing University Central Hospital, School of Medicine（重庆大学附属中心医院医学院）
Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
Department of Engineering Science, University of Oxford（工程科学系，牛津大学）；Nuffield Department of Women’s and Reproductive Health, University of Oxford（妇女与生殖健康系，牛津大学）；Fundamental AI Lab, University of Technology Nuremberg（基础人工智能实验室，纽伦堡技术大学）；University of Amsterdam（阿姆斯特丹大学）
Magnification-Aware Distillation (MAD): A Self-Supervised Framework for Unified Representation Learning in Gigapixel Whole-Slide Images
Center for Applied Artificial Intelligence, University of Kentucky（应用人工智能中心，肯塔基大学）；Sanders-Brown Center on Aging, University of Kentucky（老龄化桑德斯-布朗中心，肯塔基大学）；Department of Electrical and Computer Engineering, University of Kentucky（电气与计算机工程系，肯塔基大学）；Division of Neuropathology, University of Pittsburgh（神经病理学部，匹兹堡大学）；Department of Biomedical Informatics, Emory University（生物医学信息学系，埃默里大学）；Department of Pathology and Laboratory Medicine, University of California Davis（病理学与实验室医学系，加州大学戴维斯分校）；Department of Laboratory Medicine and Pathology, University of Texas Health（实验室医学与病理学系，德克萨斯大学健康科学中心）
Anatomical Consistency Distillation and Inconsistency Synthesis for Brain Tumor Segmentation with Missing Modalities
University of Science and Technology of China（中国科学技术大学）；Tianjin University（天津大学）；Beijing Tiantan Hospital, Capital Medical University（首都医科大学附属北京天坛医院）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
University of Notre Dame（圣母大学）；First Affiliated Hospital of Anhui Medical University（安徽医科大学第一附属医院）
With rising male infertility, sperm head morphology classification becomes critical for accurate and timely clinical diagnosis. Recent deep learning (DL) morphology analysis methods achieve promising benchmark results, but leave performance and robustness on the table by relying on limited and possibly noisy class labels. To address this, we introduce a new DL training framework that leverages anatomical and image priors from human sperm microscopy crops to extract useful features without additional labeling cost. Our core idea is to distill sperm head information with reliably-generated pseud…
ContiLNN: Mitigating Slice Sampling Discontinuity with Liquid Neural Networks for Medical Image Restoration
Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；Academy of Artificial Intelligence and Advanced Technology, Xi’an Jiaotong-Liverpool University（西交利物浦大学人工智能与先进技术研究院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
Displacement Preserving Relational Distillation for Robust Medical Segmentation
Bowling Green State University（鲍灵格林州立大学）；The University of Findlay（芬德利大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；University of Toronto（多伦多大学）；University of Houston - Clear Lake（休斯顿大学清水湖分校）；UTHealth Houston（德克萨斯大学健康科学中心休斯顿分校）
VIBESegmentator: Full Body MRI Segmentation for the NAKO and UK Biobank
TUM University Hospital（慕尼黑工业大学附属医院）；Technical University of Munich（慕尼黑工业大学）；University Medicine Greifswald（格赖夫斯瓦尔德大学医学中心）；University Medical Center Freiburg（弗赖堡大学医学中心）；University of Freiburg（弗赖堡大学）；Weill Cornell Medicine（威尔康奈尔医学院）；Imperial College London（伦敦帝国理工学院）
Low-Level Dataset Distillation for Medical Image Enhancement
School of Cyber Science and Engineering, Sichuan University（四川大学计算机科学与工程学院）；The Chinese University of Hong Kong（香港中文大学）；Agency for Science, Technology and Research (A*STAR)（科技研究局）
REACT-KD: Region-Aware Cross-modal Topological Knowledge Distillation for Interpretable Medical Image Classification
Department of Health Technology and Informatics, Hong Kong Polytechnic University（健康科技与信息技术系，香港理工大学）；Department of Nuclear Medicine and PET, Hong Kong Sanatorium and Hospital（核医学与PET部门，香港疗养院及医院）
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；University of Adelaide（阿德莱德大学）；Centre for Vision, Speech and Signal Processing（视觉、语音与信号处理中心）；University of Surrey（萨里大学）
Many state-of-the-art noisy-label learning methods rely on learning mechanisms that estimate the samples' clean labels during training and discard their original noisy labels. However, this approach prevents the learning of the relationship between images, noisy labels and clean labels, which has been shown to be useful when dealing with instance-dependent label noise problems. Furthermore, methods that do aim to learn this relationship require cleanly annotated subsets of data, as well as distillation or multi-faceted models for training. In this paper, we propose a new training algorithm tha…
Distillation Learning Guided by Image Reconstruction for One-Shot Medical Image Segmentation
School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；Peking University Third Hospital（北京大学第三医院）；Beijing Children’s Hospital, Capital Medical University（首都医科大学附属北京儿童医院）；Duke University（杜克大学）
Weighted Knowledge Distillation for Semi-Supervised Segmentation of Maxillary Sinus in Panoramic X-ray Images
Division of Electronics and Information Engineering, College of Engineering, Jeonbuk National University（全罗国立大学电子与信息工程系）；Manufacturing AI Research Center, Korea Institute of Industrial Technology (KITECH)（韩国工业技术研究院制造人工智能研究中心）；KITECH School, University of Science and Technology, Cheonan（科技大学校KITECH学院）；The Graduate School of Advanced Imaging Science, Multimedia & Film, Chung-Ang University（Chung-Ang大学高级影像科学研究生院，多媒体与电影）；Department of Oral and Maxillofacial Radiology and Wonkwang Dental Research Institute, College of Dentistry, Wonkwang University（Wonkwang大学口腔颌面放射科及Wonkwang牙科研究所）
Knowledge Distillation Approach for SOS Fusion Staging: Towards Fully Automated Skeletal Maturity Assessment
Department of Electrical and Computer Engineering, University of Illinois Chicago（伊利诺伊大学芝加哥分校电气与计算机工程系）；Department of Orthodontics, College of Dentistry, University of Illinois Chicago（伊利诺伊大学芝加哥分校牙科学院正畸学系）；University of Orleans（奥尔良大学）
ReCo-KD: Region- and Context-Aware Knowledge Distillation for Efficient 3D Medical Image Segmentation
McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston (UTHealth Houston)（麦威廉生物医学信息学学院，德克萨斯大学健康科学中心休斯顿分校（UTHealth休斯顿））
CT-based Subchondral Bone Microstructural Analysis in Knee Osteoarthritis via MR-Guided Distillation Learning
School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）；Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属第九人民医院）
Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models
DAMO Academy, Alibaba Group（阿里巴巴达摩院）；University of Science and Technology of China（中国科学技术大学）；Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences（中国科学院苏州生物医学工程技术研究所）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；The First Affiliated Hospital of College of Medicine, Zhejiang University（浙江大学医学院附属第一医院）
针对胸部 CT 缺乏大规模多病种标注数据的问题，本文提出从预训练 2D X-ray 专家模型蒸馏诊断知识，并结合语言引导检索与鲁棒对比学习，提升 3D CT 理解和报告生成能力。
SlideGCD: Slide-based Graph Collaborative Training with Knowledge Distillation for Whole Slide Image Classification
School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）；School of Software, Hefei University of Technology（合肥工业大学软件学院）；Image Processing Center, School of Astronautics, Beihang University（北京航空航天大学宇航学院图像处理中心）；Beijing Advanced Innovation Center on Biomedical Engineering（北京生物医学工程高精尖创新中心）
Siemens Healthineers（西门子医疗）；University of Michigan（密歇根大学）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
The interpretation of medical images is a challenging task, often complicated by the presence of artifacts, occlusions, limited contrast and more. Most notable is the case of chest radiography, where there is a high inter-rater variability in the detection and classification of abnormalities. This is largely due to inconclusive evidence in the data or subjective definitions of disease appearance. An additional example is the classification of anatomical views based on 2D Ultrasound images. Often, the anatomical context captured in a frame is not sufficient to recognize the underlying anatomy. …
Enhancing and Adapting in the Clinic: Source-free Unsupervised Domain Adaptation for Medical Image Enhancement
Southern University of Science and Technology（南方科技大学）；Agency for Science, Technology and Research（新加坡科技研究局）；Beijing Information Science and Technology University（北京信息科技大学）；University of Science and Technology Beijing（北京科技大学）
Unified and Semantically Grounded Domain Adaptation for Medical Image Segmentation
Department of Electrical and Computer Engineering, University of Washington（电气与计算机工程系，华盛顿大学）；Department of Bioengineering, University of Washington（生物工程系，华盛顿大学）；Department of Radiology, University of Washington（放射学系，华盛顿大学）；Department of Electrical and Computer Engineering and Paul G. Allen School of Computer Science and Engineering, University of Washington（电气与计算机工程系及保罗·G·阿伦计算机科学与工程学院，华盛顿大学）；Department of Radiology and Imaging Sciences, University of Utah（放射学与影像科学系，犹他大学）
RWTH Aachen University（亚琛工业大学）；Iran University of Science and Technology（伊朗科技大学）；University of Montreal（蒙特利尔大学）；Polytechnique Montreal（蒙特利尔综合理工学院）；Mila, Quebec AI Institute（魁北克人工智能研究所Mila）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学研究所MEVIS）
Dealing with missing modalities in Magnetic Resonance Imaging (MRI) and overcoming their negative repercussions is considered a hurdle in biomedical imaging. The combination of a specified set of modalities, which is selected depending on the scenario and anatomical part being scanned, will provide medical practitioners with full information about the region of interest in the human body, hence the missing MRI sequences should be reimbursed. The compensation of the adverse impact of losing useful information owing to the lack of one or more modalities is a well-known challenge in the field of …
REHRSeg: Unleashing the Power of Self-Supervised Super-Resolution for Resource-Efficient 3D MRI Segmentation
School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）；Monash University（莫纳什大学）；Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属第九人民医院）；School of Biomedical Engineering, ShanghaiTech University（上海科技大学生物医学工程学院）
Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images
The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）；Institute of Medical Intelligence and XR, The Chinese University of Hong Kong（香港中文大学医学智能与扩展现实研究所）
SpikeReg: Energy-Efficient 3D Deformable Medical Image Registration with Spiking Neural Networks
School of Electrical and Computer Engineering, College of Engineering, University of Tehran（德黑兰大学电气与计算机工程学院）；Max Planck Institute for Brain Research（马克斯·普朗克脑科学研究所）；School of Computer Engineering, Iran University of Science and Technology (IUST)（伊朗科学技术大学计算机工程学院）；Department of Electrical and Computer Engineering, University of Waterloo（滑铁卢大学电气与计算机工程系）
