Deep learning motivated by convolutional neural networks has been highly successful in a range of medical imaging problems like image classification, image segmentation, image synthesis etc. However for validation and interpretability, not only do we need the predictions made by the model but also how confident it is while making those predictions. This is important in safety critical applications for the people to accept it. In this work, we used an encoder decoder architecture based on variational inference techniques for segmenting brain tumour images. We evaluate our work on the publicly available BRATS dataset using Dice Similarity Coefficient (DSC) and Intersection Over Union (IOU) as the evaluation metrics. Our model is able to segment brain tumours while taking into account both aleatoric uncertainty and epistemic uncertainty in a principled bayesian manner.
QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge
Technical University of Munich（慕尼黑工业大学）；Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School（哈佛大学医学院麻省总医院阿西诺拉·A.马蒂诺斯生物医学成像中心）；University of Zurich（苏黎世大学）；Klinikum rechts der Isar, Technical University of Munich（慕尼黑工业大学右岸医院）；TranslaTUM - Central Institute for Translational Cancer Research, Technical University of Munich（慕尼黑工业大学TranslaTUM转化癌症研究中心）；McGovern Institute, Massachusetts Institute of Technology（麻省理工学院麦戈文研究所）；Helmholtz AI, Helmholtz Zentrum München（慕尼黑亥姆霍兹中心亥姆霍兹AI）
Alpha-VI DeepONet: A prior-robust variational Bayesian approach for enhancing DeepONets with uncertainty quantification
Department of Applied Mechanics（应用力学系）；Indian Institute of Technology Delhi（印度理工学院德里）；Department of Mechanical Engineering（机械工程系）；Northern Arizona University（北亚利桑那大学）
Multiple Imputation for Biomedical Data using Monte Carlo Dropout Autoencoders
West University of Timisoara（蒂米什瓦拉西部大学）；University of Ljubljana（卢布尔雅那大学）
由于复杂的实验设置，缺失值在生物医学数据中很常见。为了处理这个问题，已经提出了许多方法，从忽略不完整的实例到各种数据填补方法。随着最近深度神经网络的兴起，缺失数据填补的领域已经面向数据分布的建模。本文提出了一种基于Monte Carlo dropout的方法（变分）Autoencoders，它不仅提供了非常好的适应数据的分布，而且还允许生成新的数据，适应每个特定的实例。实验结果表明，该方法可以有效地提高插补误差和预测相似度。
alpha-Deep Probabilistic Inference (alpha-DPI): efficient uncertainty quantification from exoplanet astrometry to black hole feature extraction
California Institute of Technology（加州理工学院）；Perimeter Institute for Theoretical Physics（圆周理论物理研究所）；University of Waterloo（滑铁卢大学）；Harvard University（哈佛大学）；Center for Astrophysics — Harvard & Smithsonian（哈佛-史密森尼天体物理中心）
Microstructure-based Variational Neural Networks for Robust Uncertainty Quantification in Materials Digital Twins
Center for Integrated Nanotechnologies（集成纳米技术中心）；Sandia National Laboratories（桑塔纳国家实验室）；Theoretical Division（理论 division）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Department of Mechanical Engineering（机械工程系）；Pohang University of Science and Technology（釜山科学技术大学）
Uncertainty-Error correlations in Evidential Deep Learning models for biomedical segmentation
Gryphon Center for Artificial Intelligence and Theoretical Sciences, Singapore University of Pennsylvania, Perelman School of Medicine, Department of Radiation Oncology（格雷芬人工智能与理论科学中心，新加坡大学匹兹堡大学，佩尔曼医学学院，放射肿瘤学系）；Georgia Institute of Technology（佐治亚理工学院）；University of Pennsylvania, Perelman School of Medicine, Department of Radiation Oncology（宾夕法尼亚大学，佩尔曼医学学院，放射肿瘤学系）
A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors
具有gamma超先验的分层模型提供了一个灵活的稀疏提升框架，用于将贝叶斯公式中的$L^1$和$L^2$正则化与逆问题联系起来。尽管这些模型的贝叶斯动机，现有的方法仅限于\textit{maximum a posteriori}估计。执行不确定性量化的潜力尚未实现。本文提出了一种求解具有Gamma超先验的递阶反问题的变分迭代交替格式。建议的变分推断方法产生准确的重建，提供有意义的不确定性量化，并且易于实现。此外，它还可以很自然地进行超参数选择的模型选择。我们说明了我们的方法的性能在几个计算的例子，包括反卷积问题和稀疏识别动态系统的时间序列数据。
The Hong Kong University of Science and Technology（香港科技大学）；Tencent AI Lab（腾讯AI实验室）；Imsight AI Research Lab（依图AI研究院）；Xiamen University（厦门大学）；HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（香港科技大学深圳－香港产学研协同创新研究院）
Variational Inference for Uncertainty Quantification: an Analysis of Trade-offs
Department of Statistics University of British Columbia（统计学系大学哥伦比亚大学）；CERMICS Laboratory Ecole des Ponts ParisTech（巴黎高等理工学院CERMICS实验室）；Center for Computational Mathematics Flatiron Institute（Flatiron研究所计算数学中心）
Variational Inference and Bayesian CNNs for Uncertainty Estimation in Multi-Factorial Bone Age Prediction
Institute of Computer Graphics and Vision（计算机图形与视觉研究所）；Graz University of Technology（格拉茨理工大学）；School of Computer Science（计算机科学学院）；University of Auckland（奥克兰大学）
VENI, VINDy, VICI: a generative reduced-order modeling framework with uncertainty quantification
MOX -- Department of Mathematics, Politecnico di Milano, Milan, Italy（米兰理工学院数学系）；Institute of Engineering and Computational Mechanics, University of Stuttgart, Stuttgart, Germany（斯图加特大学工程与计算力学研究所）；Department of Civil Engineering, Politecnico di Milano, Milan, Italy（米兰理工学院土木工程系）；Department of Mechanical Engineering, University of Washington, Seattle, USA（华盛顿大学机械工程系）；Department of Applied Mathematics and Electrical and Computer Engineering, University of Washington, Seattle, USA（华盛顿大学应用数学与电气与计算机工程系）
A Primer on Variational Inference for Physics-Informed Deep Generative Modelling
University of Cambridge（剑桥大学）；Imperial College London（伦敦帝国理工学院）；London School of Economics and Political Science（伦敦政治经济学院）；The Alan Turing Institute（阿兰·图灵研究所）
