Suppr超能文献

对大型扩散加权和结构磁共振成像数据集处理的可扩展质量控制

Scalable quality control on processing of large diffusion-weighted and structural magnetic resonance imaging datasets.

作者信息

Kim Michael E, Gao Chenyu, Newlin Nancy R, Rudravaram Gaurav, Krishnan Aravind R, Ramadass Karthik, Kanakaraj Praitayini, Schilling Kurt G, Dewey Blake E, Bennett David A, O'Bryant Sid, Barber Robert C, Archer Derek, Hohman Timothy J, Bao Shunxing, Li Zhiyuan, Landman Bennett A, Mohd Khairi Nazirah

机构信息

Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States of America.

Vanderbilt University, Department of Electrical and Computer Engineering, Nashville, Tennessee, United States of America.

出版信息

PLoS One. 2025 Aug 1;20(8):e0327388. doi: 10.1371/journal.pone.0327388. eCollection 2025.

Abstract

Thorough quality control (QC) can be time consuming when working with large-scale medical imaging datasets, yet necessary, as poor-quality data can lead to erroneous conclusions or poorly trained machine learning models. Most efforts to reduce data QC time rely on quantitative outlier detection, which cannot capture every instance of algorithm failure. Thus, there is a need to visually inspect every output of data processing pipelines in a scalable manner. We design a QC pipeline that allows for low time cost and effort across a team setting for a large database of diffusion-weighted and structural magnetic resonance images. Our proposed method satisfies the following design criteria: 1.) a consistent way to perform and manage quality control across a team of researchers, 2.) quick visualization of preprocessed data that minimizes the effort and time spent on the QC process without compromising the condition/caliber of the QC, and 3.) a way to aggregate QC results across pipelines and datasets that can be easily shared. In addition to meeting these design criteria, we also provide a comparison experiment of our method to an automated QC method for a T1-weighted dataset of [Formula: see text] images and an inter-rater variability experiment for several processing pipelines. The experiments show mostly high agreement among raters and slight differences with the automated QC method. While researchers must spend time on robust visual QC of data, there are mechanisms by which the process can be streamlined and efficient.

摘要

在处理大规模医学成像数据集时,全面的质量控制(QC)可能会很耗时,但却是必要的,因为低质量的数据可能会导致错误的结论或训练不佳的机器学习模型。大多数减少数据质量控制时间的努力都依赖于定量离群值检测,而这种方法无法捕捉算法失败的每一个实例。因此,需要以可扩展的方式对数据处理管道的每个输出进行可视化检查。我们设计了一种质量控制管道,对于一个包含扩散加权和结构磁共振图像的大型数据库,在团队环境中可以实现较低的时间成本和工作量。我们提出的方法满足以下设计标准:1)一种在一组研究人员中执行和管理质量控制的一致方法;2)对预处理数据进行快速可视化,在不影响质量控制的条件/水准的情况下,将质量控制过程中花费的精力和时间降至最低;3)一种汇总跨管道和数据集的质量控制结果并易于共享的方法。除了满足这些设计标准外,我们还针对一个包含[公式:见正文]图像的T1加权数据集,将我们的方法与一种自动质量控制方法进行了比较实验,并针对几个处理管道进行了评分者间变异性实验。实验表明,评分者之间大多具有高度一致性,与自动质量控制方法存在细微差异。虽然研究人员必须花时间对数据进行可靠的可视化质量控制,但有一些机制可以简化这个过程并提高效率。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/682a/12316263/13aa6d87668f/pone.0327388.g001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验