Newlin Nancy R, Schilling Kurt, Koudoro Serge, Chandio Bramsh Qamar, Kanakaraj Praitayini, Moyer Daniel, Kelly Claire E, Genc Sila, Chen Jian, Yang Joseph Yuan-Mou, Wu Ye, He Yifei, Zhang Jiawei, Zeng Qingrun, Zhang Fan, Adluru Nagesh, Nath Vishwesh, Pathak Sudhir, Schneider Walter, Gade Anurag, Rathi Yogesh, Hendriks Tom, Vilanova Anna, Chamberland Maxime, Pieciak Tomasz, Ciupek Dominika, Vega Antonio Tristán, Aja-Fernández Santiago, Malawski Maciej, Ouedraogo Gani, Machnio Julia, Ewert Christian, Thompson Paul M, Jahanshad Neda, Garyfallidis Eleftherios, Landman Bennett A
Department of Computer Science, Vanderbilt University, Nashville, TN.
Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center.
ArXiv. 2024 Nov 14:arXiv:2411.09618v1.
White matter alterations are increasingly implicated in neurological diseases and their progression. International-scale studies use diffusion-weighted magnetic resonance imaging (DW-MRI) to qualitatively identify changes in white matter microstructure and connectivity. Yet, quantitative analysis of DW-MRI data is hindered by inconsistencies stemming from varying acquisition protocols. Specifically, there is a pressing need to harmonize the preprocessing of DW-MRI datasets to ensure the derivation of robust quantitative diffusion metrics across acquisitions. In the MICCAI-CDMRI 2023 QuantConn challenge, participants were provided raw data from the same individuals collected on the same scanner but with two different acquisitions and tasked with preprocessing the DW-MRI to minimize acquisition differences while retaining biological variation. Harmonized submissions are evaluated on the reproducibility and comparability of cross-acquisition bundle-wise microstructure measures, bundle shape features, and connectomics. The key innovations of the QuantConn challenge are that (1) we assess bundles and tractography in the context of harmonization for the first time, (2) we assess connectomics in the context of harmonization for the first time, and (3) we have 10x additional subjects over prior harmonization challenge, MUSHAC and 100x over SuperMUDI. We find that bundle surface area, fractional anisotropy, connectome assortativity, betweenness centrality, edge count, modularity, nodal strength, and participation coefficient measures are most biased by acquisition and that machine learning voxel-wise correction, RISH mapping, and NeSH methods effectively reduce these biases. In addition, microstructure measures AD, MD, RD, bundle length, connectome density, efficiency, and path length are least biased by these acquisition differences. A machine learning approach that learned voxel-wise cross-acquisition relationships was the most effective at harmonizing connectomic, microstructure, and macrostructure features, but requires the same subject be scanned at each site co-registered. NeSH, a spatial and angular resampling method, was also effective and has generalizable framework not reliant co-registration. Our code is available at https://github.com/nancynewlin-masi/QuantConn/.
白质改变与神经疾病及其进展的关联日益密切。国际规模的研究使用扩散加权磁共振成像（DW-MRI）来定性识别白质微观结构和连通性的变化。然而，由于不同采集协议导致的不一致性，DW-MRI数据的定量分析受到阻碍。具体而言，迫切需要统一DW-MRI数据集的预处理，以确保在不同采集之间得出可靠的定量扩散指标。在2023年MICCAI-CDMRI定量连接挑战赛中，参与者获得了来自同一台扫描仪上对同一批个体采集的原始数据，但采用了两种不同的采集方式，并负责对DW-MRI进行预处理，以尽量减少采集差异，同时保留生物学变异。对统一提交的结果根据跨采集束状微观结构测量、束状形状特征和连接组学的可重复性和可比性进行评估。定量连接挑战赛的关键创新之处在于：（1）我们首次在统一的背景下评估束和纤维束成像；（2）我们首次在统一的背景下评估连接组学；（3）与之前的统一挑战赛MUSHAC相比，我们的受试者数量增加了10倍，与SuperMUDI相比增加了100倍。我们发现，束表面积、分数各向异性、连接组配适度、介数中心性、边数、模块化、节点强度和参与系数测量受采集影响最大，而机器学习体素级校正方法——RISH映射和NeSH方法能有效减少这些偏差。此外，微观结构测量指标——表观扩散系数（AD）、平均扩散系数（MD）、径向扩散系数（RD）、束长度、连接组密度、效率和路径长度受这些采集差异的影响最小。一种学习体素级跨采集关系的机器学习方法在统一连接组学特征、微观结构特征和宏观结构特征方面最为有效，但要求在每个共配准的扫描部位对同一受试者进行扫描。NeSH是一种空间和角度重采样方法，也很有效，并且具有不依赖共配准的通用框架。我们的代码可在https://github.com/nancynewlin-masi/QuantConn/获取。
