arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.05907eess.IVcs.LG
收藏

2DeteCT——用于机器学习的大型二维可扩展、可训练实验性计算机断层扫描数据集

2DeteCT -- A large 2D expandable, trainable, experimental Computed Tomography dataset for machine learning

Centrum Wiskunde & Informatica(荷兰国家数学与计算机科学研究所);University of Manchester(曼彻斯特大学);Leiden University(莱顿大学);Utrecht University(乌得勒支大学)

Maximilian B. Kiss, Sophia B. Coban, K. Joost Batenburg, Tristan van Leeuwen, Felix Lucka

AI总结:

针对X射线CT缺乏大规模实验ML数据集的问题,本文构建开放的二维扇形束2DeteCT数据集,包含5000层多射束模式扫描及750个分布外层,并提供原始投影、重建与分割数据。

摘要:

计算成像领域的最新研究主要集中于开发用于图像重建的机器学习(ML)技术,这需要由测量数据和真值图像组成的大规模训练数据集。然而,适用于X射线计算机断层扫描(CT)的实验数据集十分稀缺,相关方法往往仅在模拟数据上开发和评估。我们通过向社区提供一个多功能、开放的二维扇形束CT数据集来填补这一空白,该数据集适用于为一系列图像重建任务开发ML技术。为采集该数据集,我们设计了一套精密的半自动扫描流程,采用高度灵活的实验室X射线CT装置。研究人员对形状和密度具有高度自然变异性的多样化样本组合进行逐层扫描(共5000层),具备高角度分辨率和空间分辨率,并使用三种不同射束特征:高保真模式、低剂量模式和射束硬化影响模式。此外,还通过样本和射束变化扫描了750个分布外层,以支持鲁棒性和分割任务。我们提供基于开源数据处理流程的原始投影数据、参考重建结果和分割结果。

英文摘要:

Recent research in computational imaging largely focuses on developing machine learning (ML) techniques for image reconstruction, which requires large-scale training datasets consisting of measurement data and ground-truth images. However, suitable experimental datasets for X-ray Computed Tomography (CT) are scarce, and methods are often developed and evaluated only on simulated data. We fill this gap by providing the community with a versatile, open 2D fan-beam CT dataset suitable for developing ML techniques for a range of image reconstruction tasks. To acquire it, we designed a sophisticated, semi-automatic scan procedure that utilizes a highly-flexible laboratory X-ray CT setup. A diverse mix of samples with high natural variability in shape and density was scanned slice-by-slice (5000 slices in total) with high angular and spatial resolution and three different beam characteristics: A high-fidelity, a low-dose and a beam-hardening-inflicted mode. In addition, 750 out-of-distribution slices were scanned with sample and beam variations to accommodate robustness and segmentation tasks. We provide raw projection data, reference reconstructions and segmentations based on an open-source data processing pipeline.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑