Using additional training data is known to improve the results, especially for medical image 3D segmentation where there is a lack of training material and the model needs to generalize well from few available data. However, the new data could have been acquired using other instruments and preprocessed such its distribution is significantly different from the original training data. Therefore, we study techniques which ameliorate domain shift during training so that the additional data becomes better usable for preprocessing and training together with the original data. Our results show that transforming the additional data using histogram matching has better results than using simple normalization.
Confidence intervals uncovered: Are we ready for real-world medical imaging AI?
German Cancer Research Center (DKFZ)（德国癌症研究中心（DKFZ））；AI Health Innovation Cluster（AI健康创新集群）；National Center for Tumor Diseases (NCT)（国家肿瘤疾病中心（NCT））；Heidelberg University Hospital（海德堡大学医院）；Helmholtz Imaging（亥姆霍兹成像）；HIDSS4Health - Helmholtz Information and Data Science School for Health（HIDSS4Health——亥姆霍兹健康信息与数据科学学院）；MRC Unit for Lifelong Health and Ageing at UCL（伦敦大学学院医学研究理事会终身健康与老龄化研究组）
STS MICCAI 2023 Challenge: Grand challenge on 2D and 3D semi-supervised tooth segmentation
Communication University of Zhejiang（浙江传媒学院）；West China Hospital of Stomatology, Sichuan University（四川大学华西口腔医院）；Lishui University（丽水学院）；Hangzhou Geriatric Stomatology Hospital（杭州老年口腔医院）；Hangzhou Dental Hospital Group（杭州市口腔医院集团）；Hangzhou Dianzi University（杭州电子科技大学）；Suzhou Research Institute of Shandong University（山东大学苏州研究院）；Shanghai Jiao Tong University（上海交通大学）；Shenzhen University（深圳大学）；Queen Mary University of London（伦敦大学玛丽皇后学院）；Shandong University（山东大学）；Sichuan Provincial People’s Hospital（四川省人民医院）；University of Electronic Science and Technology of China（电子科技大学）
本文介绍了 STS MICCAI 2023 挑战赛，旨在利用半监督算法解决 2D 全景 X 射线和 3D CBCT 牙齿分割问题，并总结了排名靠前队伍的方法，以推动牙科自动分析发展。
Standardized Evaluation of Automatic Methods for Perivascular Spaces Segmentation in MRI -- MICCAI 2024 Challenge Results
National University of Singapore（新加坡国立大学）；National University Hospital（国立大学医院）；Harvard Medical School（哈佛医学院）；Technical University of Munich（慕尼黑工业大学）；The University of Edinburgh（爱丁堡大学）；German Centre for Neurodegenerative Diseases (DZNE)（德国神经退行性疾病中心）；Australian e-Health Research Centre, CSIRO Health and Biosecurity（澳大利亚联邦科学与工业研究组织健康与生物安全部澳大利亚电子健康研究中心）；Central China Normal University（华中师范大学）；Fealinx；University of Bordeaux（波尔多大学）；Hankuk University（韩国大学）
Mitosis domain generalization in histopathology images -- The MIDOG challenge
Technische Hochschule Ingolstadt（因戈尔施塔特应用技术大学）；UMC Utrecht（乌得勒支大学医学中心）；Freie Universität Berlin（柏林自由大学）；Radboud UMC Nijmegen（奈梅亨拉德堡德大学医学中心）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Schwarzman Animal Medical Center（施瓦茨曼动物医学中心）；University of Leeds（利兹大学）；Korea Advanced Institute of Science and Technology（韩国科学技术院）
Analyzing the Domain Shift Immunity of Deep Homography Estimation
Kahlert School of Computing, University of Utah（犹他大学卡勒特计算学院）；Scientific Computing and Imaging Institute, University of Utah（犹他大学科学计算与成像研究所）；Department of Electrical & Computer Engineering, University of Utah（犹他大学电气与计算机工程系）；Department of Biomedical Engineering, University of Utah（犹他大学生物医学工程系）
Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomena
BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究院）；Department of Electrical Engineering and Computer Science, Technische Universität Berlin（技术大学柏林电气工程与计算机科学系）；Institute for AI in Medicine, Charité – Universitätsmedizin Berlin（柏林夏里特医学院人工智能医学研究所）
