• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

从历史飞机的大规模 CT 数据集选择注释实例分割子体积。

Selected annotated instance segmentation sub-volumes from a large scale CT data-set of a historic aircraft.

机构信息

Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Division Development Center X-Ray Technology, Fürth, Germany.

Friedrich-Alexander-Universität Erlangen-Nürnberg, Chair for Visual Computing, Erlangen, Germany.

出版信息

Sci Data. 2024 Jun 24;11(1):680. doi: 10.1038/s41597-024-03347-4.

DOI:10.1038/s41597-024-03347-4
PMID:38914545
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11196272/
Abstract

The Me 163 was a Second World War fighter airplane and is currently displayed in the Deutsches Museum in Munich, Germany. A complete computed tomography (CT) scan was obtained using a large scale industrial CT scanner to gain insights into its history, design, and state of preservation. The CT data enables visual examination of the airplane's structural details across multiple scales, from the entire fuselage to individual sprockets and rivets. However, further processing requires instance segmentation of the CT data-set. Currently, there are no adequate computer-assisted tools for automated or semi-automated segmentation of such large scale CT airplane data. As a first step, an interactive data annotation process has been established. So far, seven 512 × 512 × 512 voxel sub-volumes of the Me 163 airplane have been annotated, which can potentially be used for various applications in digital heritage, non-destructive testing, or machine learning. This work describes the data acquisition process, outlines the interactive segmentation and post-processing, and discusses the challenges associated with interpreting and handling the annotated data.

摘要

梅 163 战斗机是二战时期的一种战斗机，现陈列于德国慕尼黑的德意志博物馆。我们使用大型工业 CT 扫描仪对其进行了全面的计算机断层扫描（CT），以深入了解其历史、设计和保存状况。CT 数据使我们能够在多个尺度上对飞机的结构细节进行直观检查，从整个机身到单个链轮和铆钉。然而，进一步的处理需要对 CT 数据集进行实例分割。目前，还没有足够的计算机辅助工具来对如此大规模的 CT 飞机数据进行自动或半自动分割。作为第一步，我们建立了一个交互式数据注释过程。到目前为止，已经对梅 163 飞机的七个 512×512×512 体素子体积进行了注释，这些数据可能可用于数字遗产、无损检测或机器学习等各个领域的应用。本文描述了数据采集过程，概述了交互式分割和后处理，并讨论了与解释和处理注释数据相关的挑战。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/2aad509e99a9/41597_2024_3347_Fig19_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/f5568fc20d8a/41597_2024_3347_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/078953663452/41597_2024_3347_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/fd5834196485/41597_2024_3347_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/ef9c9b5107e1/41597_2024_3347_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/9d20b7e64cf7/41597_2024_3347_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/2472f13671ab/41597_2024_3347_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/0da524bf61b1/41597_2024_3347_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/faa918d8884a/41597_2024_3347_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/9759d41fd8dc/41597_2024_3347_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/0163b5011871/41597_2024_3347_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/b5d5ba67cddd/41597_2024_3347_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/7ba6c2368ee8/41597_2024_3347_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/74f236f5732c/41597_2024_3347_Fig13_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/73bdcf419811/41597_2024_3347_Fig14_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/3087f7bc503f/41597_2024_3347_Fig15_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/f10ec2fb40f8/41597_2024_3347_Fig16_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/33ced025d927/41597_2024_3347_Fig17_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/3de7ad909a2e/41597_2024_3347_Fig18_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/2aad509e99a9/41597_2024_3347_Fig19_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/f5568fc20d8a/41597_2024_3347_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/078953663452/41597_2024_3347_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/fd5834196485/41597_2024_3347_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/ef9c9b5107e1/41597_2024_3347_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/9d20b7e64cf7/41597_2024_3347_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/2472f13671ab/41597_2024_3347_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/0da524bf61b1/41597_2024_3347_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/faa918d8884a/41597_2024_3347_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/9759d41fd8dc/41597_2024_3347_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/0163b5011871/41597_2024_3347_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/b5d5ba67cddd/41597_2024_3347_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/7ba6c2368ee8/41597_2024_3347_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/74f236f5732c/41597_2024_3347_Fig13_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/73bdcf419811/41597_2024_3347_Fig14_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/3087f7bc503f/41597_2024_3347_Fig15_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/f10ec2fb40f8/41597_2024_3347_Fig16_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/33ced025d927/41597_2024_3347_Fig17_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/3de7ad909a2e/41597_2024_3347_Fig18_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb30/11196272/2aad509e99a9/41597_2024_3347_Fig19_HTML.jpg

相似文献

1
Selected annotated instance segmentation sub-volumes from a large scale CT data-set of a historic aircraft.从历史飞机的大规模 CT 数据集选择注释实例分割子体积。
Sci Data. 2024 Jun 24;11(1):680. doi: 10.1038/s41597-024-03347-4.
2
Interactive 3D U-net for the segmentation of the pancreas in computed tomography scans.交互式 3D U-net 用于 CT 扫描中胰腺的分割。
Phys Med Biol. 2020 Mar 11;65(6):065002. doi: 10.1088/1361-6560/ab6f99.
3
PWD-3DNet: A Deep Learning-Based Fully-Automated Segmentation of Multiple Structures on Temporal Bone CT Scans.PWD-3DNet：基于深度学习的颞骨 CT 扫描多结构全自动分割。
IEEE Trans Image Process. 2021;30:739-753. doi: 10.1109/TIP.2020.3038363. Epub 2020 Dec 4.
4
Automatic image annotation for fluorescent cell nuclei segmentation.用于荧光细胞核分割的自动图像标注
PLoS One. 2021 Apr 16;16(4):e0250093. doi: 10.1371/journal.pone.0250093. eCollection 2021.
5
Two-stage deep learning model for fully automated pancreas segmentation on computed tomography: Comparison with intra-reader and inter-reader reliability at full and reduced radiation dose on an external dataset.基于 CT 的全自动胰腺分割的两阶段深度学习模型：在外部数据集上比较全剂量和低剂量下的同读者和异读者可靠性。
Med Phys. 2021 May;48(5):2468-2481. doi: 10.1002/mp.14782. Epub 2021 Mar 16.
6
Automated segmentation of lesions and organs at risk on [Ga]Ga-PSMA-11 PET/CT images using self-supervised learning with Swin UNETR.使用基于 Swin UNETR 的自监督学习对 [Ga]Ga-PSMA-11 PET/CT 图像上的病变和危险器官进行自动分割。
Cancer Imaging. 2024 Feb 29;24(1):30. doi: 10.1186/s40644-024-00675-x.
7
Learning fuzzy clustering for SPECT/CT segmentation via convolutional neural networks.通过卷积神经网络学习用于SPECT/CT分割的模糊聚类
Med Phys. 2021 Jul;48(7):3860-3877. doi: 10.1002/mp.14903. Epub 2021 May 28.
8
CT Male Pelvic Organ Segmentation via Hybrid Loss Network With Incomplete Annotation.基于混合损失网络的不完全标注 CT 男性盆腔器官分割。
IEEE Trans Med Imaging. 2020 Jun;39(6):2151-2162. doi: 10.1109/TMI.2020.2966389. Epub 2020 Jan 13.
9
A computed tomography vertebral segmentation dataset with anatomical variations and multi-vendor scanner data.具有解剖变异和多供应商扫描仪数据的计算机断层扫描椎体分割数据集。
Sci Data. 2021 Oct 28;8(1):284. doi: 10.1038/s41597-021-01060-0.
10
Semi-supervised semantic segmentation of prostate and organs-at-risk on 3D pelvic CT images.基于3D盆腔CT图像的前列腺及危及器官的半监督语义分割
Biomed Phys Eng Express. 2021 Oct 5;7(6). doi: 10.1088/2057-1976/ac26e8.

本文引用的文献

1
Reducing manual operation time to obtain a segmentation learning model for volume electron microscopy using stepwise deep learning with manual correction.使用分步深度学习并结合手动校正来减少手动操作时间，从而获得用于体式电子显微镜的分割学习模型。
Microscopy (Oxf). 2021 Nov 24;70(6):526-535. doi: 10.1093/jmicro/dfab025.
2
X-ray Imaging Analysis of Silo Flow Parameters Based on Trace Particles Using Targeted Crowdsourcing.基于目标众包的使用示踪粒子的筒仓流动参数的X射线成像分析
Sensors (Basel). 2019 Jul 28;19(15):3317. doi: 10.3390/s19153317.
3
3D Slicer as an image computing platform for the Quantitative Imaging Network.
3D Slicer 作为定量成像网络的图像计算平台。
Magn Reson Imaging. 2012 Nov;30(9):1323-41. doi: 10.1016/j.mri.2012.05.001. Epub 2012 Jul 6.
4
Interactive volume exploration for feature detection and quantification in industrial CT data.工业CT数据中用于特征检测和量化的交互式体数据探索
IEEE Trans Vis Comput Graph. 2008 Nov-Dec;14(6):1507-14. doi: 10.1109/TVCG.2008.147.