基于单数据集子卷训练的U-Nets分割含甲烷砂变对比度XCT图像方法比较

Methane Pub Date : 2022-12-20 DOI:10.3390/methane2010001
F. Alvarez-Borges, O. N. King, B. N. Madhusudhan, T. Connolley, M. Basham, Sharif I. Ahmed
{"title":"基于单数据集子卷训练的U-Nets分割含甲烷砂变对比度XCT图像方法比较","authors":"F. Alvarez-Borges, O. N. King, B. N. Madhusudhan, T. Connolley, M. Basham, Sharif I. Ahmed","doi":"10.3390/methane2010001","DOIUrl":null,"url":null,"abstract":"Methane (CH4) hydrate dissociation and CH4 release are potential geohazards currently investigated using X-ray computed tomography (XCT). Image segmentation is an important data processing step for this type of research. However, it is often time consuming, computing resource-intensive, operator-dependent, and tailored for each XCT dataset due to differences in greyscale contrast. In this paper, an investigation is carried out using U-Nets, a class of Convolutional Neural Network, to segment synchrotron XCT images of CH4-bearing sand during hydrate formation, and extract porosity and CH4 gas saturation. Three U-Net deployments previously untried for this task are assessed: (1) a bespoke 3D hierarchical method, (2) a 2D multi-label, multi-axis method and (3) RootPainter, a 2D U-Net application with interactive corrections. U-Nets are trained using small, targeted hand-annotated datasets to reduce operator time. It was found that the segmentation accuracy of all three methods surpass mainstream watershed and thresholding techniques. Accuracy slightly reduces in low-contrast data, which affects volume fraction measurements, but errors are small compared with gravimetric methods. Moreover, U-Net models trained on low-contrast images can be used to segment higher-contrast datasets, without further training. This demonstrates model portability, which can expedite the segmentation of large datasets over short timespans.","PeriodicalId":74177,"journal":{"name":"Methane","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2022-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Comparison of Methods to Segment Variable-Contrast XCT Images of Methane-Bearing Sand Using U-Nets Trained on Single Dataset Sub-Volumes\",\"authors\":\"F. Alvarez-Borges, O. N. King, B. N. Madhusudhan, T. Connolley, M. Basham, Sharif I. Ahmed\",\"doi\":\"10.3390/methane2010001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Methane (CH4) hydrate dissociation and CH4 release are potential geohazards currently investigated using X-ray computed tomography (XCT). Image segmentation is an important data processing step for this type of research. However, it is often time consuming, computing resource-intensive, operator-dependent, and tailored for each XCT dataset due to differences in greyscale contrast. In this paper, an investigation is carried out using U-Nets, a class of Convolutional Neural Network, to segment synchrotron XCT images of CH4-bearing sand during hydrate formation, and extract porosity and CH4 gas saturation. Three U-Net deployments previously untried for this task are assessed: (1) a bespoke 3D hierarchical method, (2) a 2D multi-label, multi-axis method and (3) RootPainter, a 2D U-Net application with interactive corrections. U-Nets are trained using small, targeted hand-annotated datasets to reduce operator time. It was found that the segmentation accuracy of all three methods surpass mainstream watershed and thresholding techniques. Accuracy slightly reduces in low-contrast data, which affects volume fraction measurements, but errors are small compared with gravimetric methods. Moreover, U-Net models trained on low-contrast images can be used to segment higher-contrast datasets, without further training. This demonstrates model portability, which can expedite the segmentation of large datasets over short timespans.\",\"PeriodicalId\":74177,\"journal\":{\"name\":\"Methane\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-12-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Methane\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/methane2010001\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Methane","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/methane2010001","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

甲烷(CH4)水合物解离和CH4释放是目前使用X射线计算机断层扫描(XCT)研究的潜在地质灾害。图像分割是这类研究中一个重要的数据处理步骤。然而,由于灰度对比度的差异,它通常是耗时的、计算资源密集型的、依赖于操作员的,并且是为每个XCT数据集量身定制的。本文利用一类卷积神经网络U-Nets对水合物形成过程中含CH4砂的同步辐射XCT图像进行了分割,并提取了孔隙率和CH4气体饱和度。评估了之前未尝试用于该任务的三种U-Net部署:(1)定制的3D分层方法,(2)2D多标签、多轴方法,以及(3)RootPainter,一种具有交互式校正的2D U-Net应用程序。U-Nets使用小型、有针对性的手工注释数据集进行训练,以减少操作员时间。研究发现,这三种方法的分割精度都超过了主流的分水岭和阈值技术。低对比度数据的准确性略有下降,这会影响体积分数的测量,但与重量分析方法相比,误差较小。此外,在低对比度图像上训练的U-Net模型可以用于分割对比度较高的数据集,而无需进一步训练。这证明了模型的可移植性,可以在短时间内加快大型数据集的分割。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Comparison of Methods to Segment Variable-Contrast XCT Images of Methane-Bearing Sand Using U-Nets Trained on Single Dataset Sub-Volumes
Methane (CH4) hydrate dissociation and CH4 release are potential geohazards currently investigated using X-ray computed tomography (XCT). Image segmentation is an important data processing step for this type of research. However, it is often time consuming, computing resource-intensive, operator-dependent, and tailored for each XCT dataset due to differences in greyscale contrast. In this paper, an investigation is carried out using U-Nets, a class of Convolutional Neural Network, to segment synchrotron XCT images of CH4-bearing sand during hydrate formation, and extract porosity and CH4 gas saturation. Three U-Net deployments previously untried for this task are assessed: (1) a bespoke 3D hierarchical method, (2) a 2D multi-label, multi-axis method and (3) RootPainter, a 2D U-Net application with interactive corrections. U-Nets are trained using small, targeted hand-annotated datasets to reduce operator time. It was found that the segmentation accuracy of all three methods surpass mainstream watershed and thresholding techniques. Accuracy slightly reduces in low-contrast data, which affects volume fraction measurements, but errors are small compared with gravimetric methods. Moreover, U-Net models trained on low-contrast images can be used to segment higher-contrast datasets, without further training. This demonstrates model portability, which can expedite the segmentation of large datasets over short timespans.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Application of Digestate from a Methane Fermentation Process for Supplying Water and Nutrients in Sweet Potato Cultivation in Sandy Soil Pathways toward Climate-Neutral Red Meat Production Recent Advances in the Use of Controlled Nanocatalysts in Methane Conversion Reactions Dry Reforming of CH4 Using a Microreactor A Study on the Heterogeneity and Anisotropy of the Porous Grout Body Created in the Stabilization of a Methane Hydrate Reservoir through Grouting
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1