Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets
King’s College London（伦敦国王学院）；School of Biomedical Engineering & Imaging Sciences（生物医学工程与成像科学学院）；King’s College Hospital NHS Foundation Trust（国王学院医院国民健康服务基金会信托）；NVIDIA（英伟达）；Dementia Research Centre, UCL Institute of Neurology, UCL（伦敦大学学院痴呆研究中心、伦敦大学学院神经学研究所、伦敦大学学院）；Department of Medical Physics, UCL（伦敦大学学院医学物理系）；Department of Neuroradiology（神经放射科）；St. Thomas’ Hospital（圣托马斯医院）
Reuben Dorent, Thomas Booth, Wenqi Li, Carole H. Sudre, Sina Kafiabadi, Jorge Cardoso, Sebastien Ourselin, Tom Vercauteren
Brain tissue segmentation from multimodal MRI is a key building block of many neuroimaging analysis pipelines. Established tissue segmentation approaches have, however, not been developed to cope with large anatomical changes resulting from pathology, such as white matter lesions or tumours, and often fail in these cases. In the meantime, with the advent of deep neural networks (DNNs), segmentation of brain lesions has matured significantly. However, few existing approaches allow for the joint segmentation of normal tissue and brain lesions. Developing a DNN for such a joint task is currently hampered by the fact that annotated datasets typically address only one specific task and rely on task-specific imaging protocols including a task-specific set of imaging modalities. In this work, we propose a novel approach to build a joint tissue and lesion segmentation model from aggregated task-specific hetero-modal domain-shifted and partially-annotated datasets. Starting from a variational formulation of the joint problem, we show how the expected risk can be decomposed and optimised empirically. We exploit an upper bound of the risk to deal with heterogeneous imaging modalities across datasets. To deal with potential domain shift, we integrated and tested three conventional techniques based on data augmentation, adversarial learning and pseudo-healthy generation. For each individual task, our joint approach reaches comparable performance to task-specific and fully-supervised models. The proposed framework is assessed on two different types of brain lesions: White matter lesions and gliomas. In the latter case, lacking a joint ground-truth for quantitative assessment purposes, we propose and use a novel clinically-relevant qualitative assessment methodology.
SegHeD: Segmentation of Heterogeneous Data for Multiple Sclerosis Lesions with Anatomical Constraints
Imperial College London（伦敦帝国学院）；Data Science Institute, Imperial College London（伦敦帝国学院数据科学研究所）；Beijing Institute of Technology（北京理工大学）；UK Dementia Research Institute（英国痴呆症研究所）；Rosalind Franklin Institute（罗莎琳德·富兰克林研究所）
School of Advanced Technology, Xi’an Jiaotong-Liverpool University（西交利物浦大学先进技术学院）；School of Electronics and Information Engineering, Beihang University（北京航空航天大学电子信息工程学院）；Cambridge University（剑桥大学）；Beijing Shijitan Hospital, Capital Medical University（首都医科大学附属北京世纪坛医院）；University of Liverpool（利物浦大学）
Privileged Lesion-Context Relational Distillation for Mask-Free Skin Lesion Classification
Victoria University（维多利亚大学）；Bangaldesh University of Business and Technology（孟加拉国商业与技术大学）；Daffodil Institute of Information Technology（达芙妮信息技术学院）；American International University-Bangladesh (AIUB)（孟加拉国美国国际大学）；Multimedia University（多媒体大学）
Uncertainty-Aware Multimodal Fusion for Oral Lesion Classification
1 School of Medical Science \& Technology, IIT Kharagpur, India 2 Department of Electrical Engineering, IIT Kharagpur, India 3 Dr. B.C. Roy Multispeciality Medical Research Centre, IIT Kharagpur, India
COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（人工智能学院，南京航空航天大学）；ByteDance Inc.（字节跳动公司）；Tsinghua University（清华大学）；Shanghai Jiaotong University（上海交通大学）
Mitigating the Influence of Domain Shift in Skin Lesion Classification: A Benchmark Study of Unsupervised Domain Adaptation Methods on Dermoscopic Images
German Aerospace Center (DLR)（德国航空航天中心）；German Cancer Research Center (DKFZ)（德国癌症研究中心）
Domain Adaptive Skin Lesion Classification via Conformal Ensemble of Vision Transformers
Faculty of Mechanical Engineering（机械工程学院）；University of Victoria（维多利亚大学）；Faculty of Electrical and Computer Engineering（电气与计算机工程学院）；Faculty of Mechanical, Electrical, and Computer Engineering（机械、电气和计算机工程学院）
Domain Adaptation for Deviating Acquisition Protocols in CNN-based Lesion Classification on Diffusion-Weighted MR Images
German Cancer Research Center (DKFZ)（德国癌症研究中心）；University Hospital Erlangen（埃尔兰根大学医院）；Radiological Practice at the ATOS Clinic（ATOS诊所放射科诊所）；Radiology Center Mannheim (RZM)（曼海姆放射中心）
Benchmarking Foundation Models for Renal Lesion Stratification in CT
Charité - Universitätsmedizin Berlin, Department of Radiology（柏林夏里特大学医学院放射科）；Radboudumc, Diagnostic Image Analysis Group（拉德堡德大学医学中心影像分析组）；Klinikum rechts der Isar, TUM University Hospital, Technical University of Munich（慕尼黑技术大学慕尼黑大学医院克林克姆右岸诊所）；Charité - Universitätsmedizin Berlin, Institute of Neuroradiology（柏林夏里特大学医学院神经放射科）；German Heart Center, TUM University Hospital, Technical University of Munich（德国心脏中心，慕尼黑技术大学慕尼黑大学医院）
LIDIA: Precise Liver Tumor Diagnosis on Multi-Phase Contrast-Enhanced CT via Iterative Fusion and Asymmetric Contrastive Learning
College of Computer Science, Sichuan University（四川大学计算机学院）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；Hupan Lab（湖畔实验室）；Shengjing Hospital of China Medical University（中国医科大学附属盛京医院）；First Affiliated Hospital of Zhejiang University（浙江大学附属第一医院）
Ischemic Stroke Segmentation and Net Water Uptake Quantification on Multicenter Non-Contrast CT Using Supervised Target-Domain Adaptation
University Medical Center Hamburg-Eppendorf（汉堡-埃彭多夫大学医学中心）；University Hospital Marburg（马尔堡大学医院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；HELIOS Medical Center Schwerin（HELIOS什未林医疗中心）；MSH Medical School Hamburg（汉堡MSH医学院）；MSH Research, Development and Innovation GmbH（MSH研究开发与创新有限公司）；MSH Medical University of Applied Sciences and Medical University（MSH应用科学医科大学与医科大学）
SYNAPSE-Net: A Unified Framework with Lesion-Aware Hierarchical Gating for Robust Segmentation of Heterogeneous Brain Lesions
Department of Biomedical Engineering, Bangladesh University of Engineering and Technology（生物医学工程系，孟加拉国工程与技术大学）；Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology（计算机科学与工程系，孟加拉国工程与技术大学）；Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology（电气与电子工程系，孟加拉国工程与技术大学）
LiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT
College of Biomedical Engineering, Fudan University（复旦大学生物医学工程学院）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；Hupan Lab（湖畔实验室）；First Affiliated Hospital of Zhejiang University（浙江大学附属第一医院）；Shengjing Hospital of China Medical University（中国医科大学附属盛京医院）
Deep Unsupervised Anomaly Detection in Brain Imaging: Large-Scale Benchmarking and Bias Analysis
Department of Psychiatry and Psychotherapy, University Hospital Tübingen（图宾根大学精神病学与心理学系）；Cluster of Excellence – Machine Learning for Science, University of Tübingen（图宾根大学机器学习科学卓越中心）；Department of Psychology, Friedrich Schiller University of Jena（耶拿弗里德里希·席勒大学心理学系）；German Center for Mental Health (DZPG), partner site Halle/Jena/Magdeburg（德国心理健康中心（DZPG）哈勒/耶拿/马格德堡分部）；University of Lucerne（卢塞恩大学）
Hetero-modal learning and corruption-resistant hetero-modal inference for joint segmentation of white matter hyperintensities and ischaemic stroke lesions in MRI
University of Edinburgh（爱丁堡大学）；Canon Medical Research Europe（佳能医疗研究欧洲）；UK Dementia Research Institute, Centre at The University of Edinburgh（英国痴呆症研究所爱丁堡中心）；Usher Institute, University of Edinburgh（爱丁堡大学厄舍研究所）
FedGS: Federated Gradient Scaling for Heterogeneous Medical Image Segmentation
University of Amsterdam（阿姆斯特丹大学）；The Netherlands Cancer Institute（荷兰癌症研究所）；Utrecht University（乌得勒支大学）；Maastricht University Medical Center（马斯特里赫特大学医学中心）
TAFM-Net: A Novel Approach to Skin Lesion Segmentation Using Transformer Attention and Focal Modulation
School of Computer Science and Engineering, UNSW（新南威尔士大学计算机科学与工程学院）；Abasyn University Islamabad Campus（阿巴辛大学伊斯兰堡校区）；School of Computer Science（计算机学院）；Department of Computing, Abasyn University Islamabad Campus（阿巴辛大学伊斯兰堡校区计算机系）
Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data
Department of Imaging Neuroscience, University College London（影像神经科学系，伦敦大学学院）；Institute of Cognitive Neuroscience, University College London（认知神经科学研究所，伦敦大学学院）
Towards AI Lesion Tracking in PET/CT Imaging: A Siamese-based CNN Pipeline applied on PSMA PET/CT Scans
Technical University of Munich（慕尼黑工业大学）；TUM School of Natural Sciences（慕尼黑工业大学自然科学学院）；Johns Hopkins University School of Medicine（约翰霍普金斯大学医学院）；Munich Institute of Biomedical Engineering（慕尼黑生物医学工程研究所）
Generalizable automated ischaemic stroke lesion segmentation with vision transformers
University College London（伦敦大学学院）；UCL Queen Square Institute of Neurology（伦敦大学学院女王广场神经病学研究所）；National Hospital for Neurology and Neurosurgery（国家神经病学与神经外科医院）；King’s College London（伦敦国王学院）；Institut des Maladies Neurodégénératives（神经退行性疾病研究所）；CNRS（法国国家科学研究中心）；CEA（法国原子能和替代能源委员会）；University of Bordeaux（波尔多大学）
A comparative study of 2D image segmentation algorithms for traumatic brain lesions using CT data from the ProTECTIII multicenter clinical trial
Warren Alpert Medical School of Brown University（布朗大学沃伦·阿尔珀特医学院）；Emory University School of Medicine（埃默里大学医学院）；University of Florida School of Medicine（佛罗里达大学医学院）；Brown University（布朗大学）
A Dual-Task Synergy-Driven Generalization Framework for Pancreatic Cancer Segmentation in CT Scans
Southwest Jiaotong University（西南交通大学）；Shanghai Jiao Tong University（上海交通大学）；The Second Affiliated Hospital of Guangzhou Medical University（广州医科大学附属第二医院）
MEDPSeg: Hierarchical polymorphic multitask learning for the segmentation of ground-glass opacities, consolidation, and pulmonary structures on computed tomography
School of Electrical and Computer Engineering, Universidade Estadual de Campinas（坎皮纳斯州立大学电气与计算机工程学院）；University of Iowa（爱荷华大学）
Learning from spatially inhomogenous data: resolution-adaptive convolutions for multiple sclerosis lesion segmentation
University Institute of Diagnostic and Interventional Neuroradiology（诊断与介入神经放射学大学研究所）；Inselspital, Bern University Hospital and University of Bern（伯尔尼大学医院因塞尔spital与伯尔尼大学）；Centre for Artificial Intelligence in Medicine（医学人工智能中心）；University of Bern（伯尔尼大学）
ProstAttention-Net: A deep attention model for prostate cancer segmentation by aggressiveness in MRI scans
Univ Lyon（里昂大学）；CNRS（法国国家科学研究中心）；Inserm（法国国家健康与医学研究院）；INSA Lyon（里昂国立应用科学学院）；UCBL（里昂第一大学）；CREATIS（里昂影像与信息处理研究中心）；Hospices Civils de Lyon（里昂民用医院集团）；Hôpital Edouard Herriot（爱德华·埃里奥医院）；University of Sherbrooke（舍布鲁克大学）
Precise Liver Tumor Segmentation in CT Using a Hybrid Deep Learning-Radiomics Framework
School of Information Science & Engineering, Shandong Normal University（信息科学与工程学院，山东师范大学）；Tajik State University of Law, Business and Politics（塔吉克国立法律、商业与政治大学）
Quantification of pulmonary involvement in COVID-19 pneumonia by means of a cascade oftwo U-nets: training and assessment on multipledatasets using different annotation criteria
Scuola Normale Superiore（比萨高等师范学校）；National Institute of Nuclear Physics (INFN)（国家核物理研究所）；University of Pavia（帕维亚大学）；University of Pisa（比萨大学）；University of Sassari（萨萨里大学）；University of Florence（佛罗伦萨大学）
