The COVID-19 pandemic has triggered an urgent need to contribute to the fight against an immense threat to the human population. Computer Vision, as a subfield of Artificial Intelligence, has enjoyed recent success in solving various complex problems in health care and has the potential to contribute to the fight of controlling COVID-19. In response to this call, computer vision researchers are putting their knowledge base at work to devise effective ways to counter COVID-19 challenge and serve the global community. New contributions are being shared with every passing day. It motivated us to review the recent work, collect information about available research resources and an indication of future research directions. We want to make it available to computer vision researchers to save precious time. This survey paper is intended to provide a preliminary review of the available literature on the computer vision efforts against COVID-19 pandemic.
CNN-based Local Vision Transformer for COVID-19 Diagnosis
the University of New South Wales(新南威尔士大学);the University of Sydney(悉尼大学);Data61, The Commonwealth Scientific and Industrial Research Organisation (CSIRO)(联邦科学与工业研究组织(CSIRO)Data61)
深度学习技术可以作为辅助技术,帮助医生快速准确地识别COVID-19感染。近年来,Vision Transformer(ViT)由于其全局感受野特性,在图像分类领域显示出了巨大的潜力。然而,由于缺乏CNN固有的归纳偏差,基于ViT的结构导致有限的特征丰富度和模型训练的困难。在本文中,我们提出了一种新的结构,称为Transformer for COVID-19(COVT),以提高基于ViT的架构在小型COVID-19数据集上的性能。它使用CNN作为特征提取器来有效地提取局部结构信息,并将平均池化引入ViT的多层感知(MLP)模块以获得全局信息。实验表明,我们的方法在两个COVID-19数据集和ImageNet数据集上的有效性。
SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detection
School of Electronic Engineering & Computer Science, Queen Mary University of London(伦敦玛丽女王大学电子工程与计算机科学学院);National Technical University Athens(雅典国立技术大学)
COVID-19 Computer-aided Diagnosis through AI-assisted CT Imaging Analysis: Deploying a Medical AI System
University of Ioannina(约阿尼纳大学);AIandMe SMPC(AIandMe SMPC公司);National Technical University of Athens(雅典国立技术大学);Queen Mary University of London(伦敦大学玛丽皇后学院)
A two-step explainable approach for COVID-19 computer-aided diagnosis from chest x-ray images
University of Turin(都灵大学);Azienda Ospedaliera Città della Salute e della Scienza Presidio Molinette(健康与科学城医院莫利内特分院);AOU San Luigi Gonzaga(圣路易吉·贡扎加大学医院)
Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus
Korea Advanced Institute of Science and Technology(韩国科学技术院);Asan Medical Center(峨山医院);University of Ulsan College of Medicine(蔚山大学医学院);College of Medicine, Yeungnam University(岭南大学医学院);School of Medicine, Kyungpook National University(庆北国立大学医学院)
A Survey on Computer Vision based Human Analysis in the COVID-19 Era
Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Istanbul Technical University(伊斯坦布尔理工大学);Fraunhofer Institute for Computer Graphics Research IGD(弗劳恩霍夫计算机图形学研究所);TU Darmstadt(达姆施塔特工业大学);Qatar Computing Research Institute(卡塔尔计算研究所);HBKU(哈马德·本·哈利法大学);University of Ljubljana(卢布尔雅那大学);Utrecht University(乌得勒支大学);Boğaziçi University(博阿齐奇大学);Carnegie Mellon University(卡内基梅隆大学)
Identification of images of COVID-19 from Chest X-rays using Deep Learning: Comparing COGNEX VisionPro Deep Learning 1.0 Software with Open Source Convolutional Neural Networks
COVID-19大流行对人类造成严重及灾难性影响,并被视为本世纪最严重的健康灾难。检测COVID-19的最佳方法之一是放射学图像,即X射线和计算机断层扫描或CT扫描图像。许多公司和教育机构在这场危机中走到了一起,创建了各种深度学习模型,用于从胸部X光摄影图像中有效诊断COVID-19。例如,滑铁卢大学与Darwin AI一起设计了深度学习模型COVID-Net,并创建了一个名为COVIDx的数据集,由13,975张图像组成。在这项研究中,COGNEX的深度学习软件-VisionPro Deep Learning用于对COVIDx数据集中的这些胸部X射线进行分类。将结果与COVID-Net和开源社区的各种其他最先进的深度学习模型的结果进行比较。深度学习工具通常被称为黑盒,因为人类无法解释模型如何或为什么将图像分类到特定类别。这个问题通过使用两种设置测试VisionPro深度学习来解决,首先选择整个图像,即选择整个图像作为ROI区域,其次在第一步中分割肺部,然后仅对分割的肺部进行分类步骤,而不是使用整个图像。VisionPro深度学习的结果-在作为ROI的整个图像上,它实现了94.0%的总体F分数,在分割的肺部上,它获得了95.3%的F分数,这与COVID-Net和其他最先进的开源深度学习模型相当或更好。
Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer
Korea Advanced Institute of Science and Technology(韩国科学技术院);Asan Medical Center(峨山医院);University of Ulsan College of Medicine(蔚山大学医学院);College of Medicine, Chungnam National Univerity(忠南国立大学医学院);College of Medicine, Yeungnam University(岭南大学医学院);School of Medicine, Kyungpook National University(庆北国立大学医学院)
Vision Transformer using Low-level Chest X-ray Feature Corpus for COVID-19 Diagnosis and Severity Quantification
Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院);Asan Medical Center, University of Ulsan College of Medicine(蔚山大学医学院峨山医学中心);College of Medicine, Yeungnam University(岭南大学医学院);School of Medicine, Kyungpook National University(庆北国立大学医学院)
COVID-Net S: Towards computer-aided severity assessment via training and validation of deep neural networks for geographic extent and opacity extent scoring of chest X-rays for SARS-CoV-2 lung disease severity
University of Waterloo(滑铁卢大学);DarwinAI Corp.(DarwinAI公司);Stony Brook School of Medicine(石溪大学医学院);Montefiore Medical Center(蒙蒂菲奥里医疗中心);Albert Einstein College of Medicine(阿尔伯特·爱因斯坦医学院)
Vision Transformer-based Model for Severity Quantification of Lung Pneumonia Using Chest X-ray Images
University of the Basque Country(巴斯克大学);IKERBASQUE;Ho Chi Minh City Open University(胡志明市开放大学);University of Strasbourg(斯特拉斯堡大学);INSERM(法国国家健康与医学研究院);Université de Haute-Alsace(上阿尔萨斯大学)
本文提出 ViTReg-IP,一种由 ViT 与回归头构成的轻量模型,用于根据胸部 X 光量化 COVID-19 等肺病严重程度,并在多来源数据集上验证其低成本、高性能与泛化性。