SAVGAN: Self-Attention Based Generation of Tumour on Chip Videos

Sandeep Manandhar, I. Veith, M. Parrini, Auguste Genovesio
{"title":"SAVGAN: Self-Attention Based Generation of Tumour on Chip Videos","authors":"Sandeep Manandhar, I. Veith, M. Parrini, Auguste Genovesio","doi":"10.1109/ISBI52829.2022.9761518","DOIUrl":null,"url":null,"abstract":"Generation of videomicroscopy sequences will become increasingly important in order to train and evaluate dynamic image analysis methods. The latter are crucial to the study of biological dynamic processes such as tumour-immune cell interactions. However, current generative models developed in the context of natural image sequences employ either a single 3D (2D+time) convolutional neural network (CNN) based generator, which fails to capture long range interactions, or two separate (spatial and temporal) generators, which are unable to faithfully reproduce the morphology of moving objects. Here, we propose a self-attention based generative model for videomicroscopy sequences that aims to take into account for the full range of interactions within a spatio-temporal volume of 32 frames. To reduce the computational burden of such a strategy, we consider the Nyström approximation of the attention matrix. This approach leads to significant improvements in reproducing the structures and the proper motion of videomicroscopy sequences as assessed by a range of existing and proposed quantitative metrics.","PeriodicalId":6827,"journal":{"name":"2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","volume":"30 1","pages":"1-5"},"PeriodicalIF":0.0000,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISBI52829.2022.9761518","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Generation of videomicroscopy sequences will become increasingly important in order to train and evaluate dynamic image analysis methods. The latter are crucial to the study of biological dynamic processes such as tumour-immune cell interactions. However, current generative models developed in the context of natural image sequences employ either a single 3D (2D+time) convolutional neural network (CNN) based generator, which fails to capture long range interactions, or two separate (spatial and temporal) generators, which are unable to faithfully reproduce the morphology of moving objects. Here, we propose a self-attention based generative model for videomicroscopy sequences that aims to take into account for the full range of interactions within a spatio-temporal volume of 32 frames. To reduce the computational burden of such a strategy, we consider the Nyström approximation of the attention matrix. This approach leads to significant improvements in reproducing the structures and the proper motion of videomicroscopy sequences as assessed by a range of existing and proposed quantitative metrics.
SAVGAN:基于自我关注的肿瘤芯片视频生成
为了训练和评估动态图像分析方法,生成视频显微序列将变得越来越重要。后者对于诸如肿瘤免疫细胞相互作用等生物动力学过程的研究至关重要。然而,目前在自然图像序列背景下开发的生成模型要么使用单个基于3D (2D+时间)卷积神经网络(CNN)的生成器,无法捕获远程相互作用,要么使用两个独立的(空间和时间)生成器,无法忠实地再现运动物体的形态。在这里,我们提出了一个基于自注意的视频显微序列生成模型,旨在考虑32帧时空体积内的全部相互作用。为了减少这种策略的计算负担,我们考虑Nyström对注意力矩阵的近似。通过一系列现有的和拟议的定量指标评估,这种方法在再现视频显微镜序列的结构和适当运动方面取得了显著的改进。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信