DATASET for: "Carotid Ultrasound Boundary Study (CUBS): Technical considerations on an open multi-center analysis of computerized measurement systems for intima-media thickness measurement on common carotid artery longitudinal B-mode ultrasound scans"

Here we provide the entire dataset (500 images, conversion factors for images, 3 manual segmentations, 7 computerized segmentations) for the article "Carotid Ultrasound Boundary Study (CUBS): Technical considerations on an open multi-center analysis of computerized measurement systems for intima-media thickness measurement on common carotid artery longitudinal B-mode ultrasound scans" published in Computers in Biology and Medicine, 2022 (DOI: https://doi.org/10.1016/j.compbiomed.2022.105333).

Any results obtained using the published dataset MUST cite the original research article (Meiburger K.M. et al, Carotid Ultrasound Boundary Study (CUBS): Technical considerations on an open multi-center analysis of computerized measurement systems for intima-media thickness measurement on common carotid artery longitudinal B-mode ultrasound scans", Computers in Biology and Medicine, 2022, DOI: https://doi.org/10.1016/j.compbiomed.2022.105333. See the ReadMe file "readme.txt" for all details.

Abstract:
"After publishing an in-depth study that analyzed the ability of computerized methods to assist or replace human experts in obtaining carotid intima-media thickness (CIMT) measurements leading to correct therapeutic decisions, here the same consortium joined to present technical outlooks on computerized CIMT measurement systems and provide considerations for the community regarding the development and comparison of these methods, including considerations to encourage the standardization of computerized CIMT measurements and results presentation. A multi-center database of 500 images was collected, upon which three manual segmentations and seven computerized methods were employed to measure the CIMT, including traditional methods based on dynamic programming, deformable models, the first order absolute moment, anisotropic Gaussian derivative filters and deep learning-based image processing approaches based on Unet convolutional neural networks. An inter- and intra-analyst variability analysis was conducted and segmentation results were analyzed by dividing the database based on carotid morphology, image signal-to-noise ratio, and research center. The computerized methods’ obtained CIMT absolute bias results that were comparable with studies in literature and they generally were similar and often better than the observed inter- and intra-analyst variability. Several computerized methods showed promising segmentation results, including one deep learning method (CIMT absolute bias = 106 ± 89 μm vs. 160 ± 140 μm intra-analyst variability) and three other traditional image processing methods (CIMT absolute bias = 139 ± 119 μm, 143 ± 118 μm and 139 ± 136 μm). The entire database used has been made publicly available for the community to facilitate future studies and to encourage an open comparison and technical analysis."

本次研究公开了发表于《计算机生物学与医学》（Computers in Biology and Medicine）2022年期刊的论文《颈动脉超声边界研究（Carotid Ultrasound Boundary Study, CUBS）：颈总动脉纵向B型超声扫描内膜中层厚度（intima-media thickness, IMT）计算机测量系统开放多中心分析的技术考量》（DOI: https://doi.org/10.1016/j.compbiomed.2022.105333）所配套的完整数据集，包含500幅超声图像、图像转换系数、3组手动分割结果与7组计算机辅助分割结果。
使用本公开数据集开展研究得到的所有结果，均须引用上述原创研究论文（Meiburger K.M. 等，《颈动脉超声边界研究（CUBS）：颈总动脉纵向B型超声扫描内膜中层厚度计算机测量系统开放多中心分析的技术考量》，《计算机生物学与医学》，2022年，DOI: https://doi.org/10.1016/j.compbiomed.2022.105333）。详细信息请参阅自述文件readme.txt。
摘要：
此前本研究团队已发表一项深度研究，分析了计算机辅助方法辅助或替代人类专家获取颈动脉内膜中层厚度（carotid intima-media thickness, CIMT）测量值以辅助制定正确治疗决策的能力。本次本团队联合推出该研究的技术展望，阐述计算机辅助CIMT测量系统的相关技术要点，并为学界提供此类方法的开发与对比参考标准，其中包括推动计算机辅助CIMT测量及结果呈现标准化的相关考量。
本研究收集了包含500幅图像的多中心数据库，采用3组手动分割方案与7种计算机辅助方法开展CIMT测量，其中既包含基于动态编程、可变形模型、一阶绝对矩、各向异性高斯导数滤波器的传统图像处理方法，也涵盖基于Unet卷积神经网络的深度学习图像处理方案。
研究开展了分析师间与分析师内变异性分析，并根据颈动脉形态、图像信噪比（signal-to-noise ratio, SNR）以及所属研究中心对数据库进行分组，以此分析分割结果。
计算机辅助方法得到的CIMT绝对偏差结果与现有文献中的研究水平相当，整体表现与人工测量结果相近，且多数情况下优于人工测量的分析师间与分析师内变异性水平。多款计算机辅助方法展现出优异的分割性能，其中1款深度学习方法（CIMT绝对偏差为106±89μm，对应分析师内变异性为160±140μm）以及3款传统图像处理方法（CIMT绝对偏差分别为139±119μm、143±118μm与139±136μm）表现尤为突出。
本研究所用的完整数据库已向学界公开，以助力后续相关研究，并推动开放化对比与技术分析工作的开展。

搜集汇总

背景与挑战

背景概述

该数据集是一个用于颈动脉内膜中层厚度（CIMT）测量的多中心超声图像数据库，包含500张图像、3个手动分割和7个计算机化分割结果，旨在评估计算机化测量系统的性能并与人工分析变异性进行比较。数据集支持技术标准化和开放比较，适用于医学图像处理研究，特别是CIMT测量方法的开发和验证。