Uncovering and mitigating bias in large, automated MRI analyses of brain development.
Uncovering and mitigating bias in large, automated MRI analyses of brain development.
复制标题
发现并减轻大脑发育的大型自动化 MRI 分析中的偏差。
DOI：
10.1101/2023.02.28.530498
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Barch,
中科院分区：
文献类型：
--
作者：
Elyounssi,Safia;Kunitoki,Keiko;Clauss,JacquelineA;Laurent,Eline;Kane,Kristina;Hughes,DylanE;Hopkinson,CaseyE;Bazer,Oren;Sussman,RachelFreed;Doyle,AlysaE;Lee,Hang;Tervo-Clemmens,Brenden;Eryilmaz,Hamdi;Gollub,RandyL;Barch,
以人群为基础的大型青少年MRI研究有望对神经发育和精神疾病风险提供变革性的见解1,2。然而，年轻人的MRI研究特别容易受到运动和其他人为因素的影响。这些伪影可能无法被高通量成像研究中首选的自动化质量控制（QC）方法检测到5，并且可能在临床关联分析中引入非随机噪声。通过青少年大脑认知发展（ABCD）研究，我们通过严格的视觉质量控制，对9-10岁儿童11,263张T1 MRI扫描图进行了严格的视觉质量控制，从而证明了儿童结构MRI分析中的偏差，因为包含了较低质量的图像。与评分最高的图像（44.9%的样本）相比，较低质量的图像通常与皮质厚度减少和皮质表面积增加有关（科恩d 0.14-2.84）。不同的图像质量导致与结构MRI和临床测量相关联的分析中出现违反直觉的模式，因为包含低质量扫描以增加假阳性和阴性风险的方式改变了明显的效应大小。通过控制表面孔数，可以部分减轻质量相关的偏差。表面孔数是一种拓扑复杂性的自动指数，可以区分基线（0.81-0.93）和1000次Year 2扫描（0.88-1.00）的低质量扫描，具有良好的特异性。然而，即使在评分最高的图像中，在图像预处理过程中也会出现细微的拓扑错误，通过手工编辑对其进行校正，显著地、可重复地改变了大部分皮层的厚度测量值（d 0.15-0.92）。这些发现表明，青少年结构MRI扫描的质量控制不足会破坏大样本量检测有意义关联的优势。
Large, population-based MRI studies of adolescents promise transformational insights into neurodevelopment and mental illness risk 1,2. However, MRI studies of youth are especially susceptible to motion and other artifacts 3,4. These artifacts may go undetected by automated quality control (QC) methods that are preferred in high-throughput imaging studies, 5 and can potentially introduce non-random noise into clinical association analyses. Here we demonstrate bias in structural MRI analyses of children due to inclusion of lower quality images, as identified through rigorous visual quality control of 11,263 T1 MRI scans obtained at age 9–10 through the Adolescent Brain Cognitive Development (ABCD) Study6. Compared to the best-rated images (44.9% of the sample), lower-quality images generally associated with decreased cortical thickness and increased cortical surface area measures (Cohen’s d 0.14–2.84). Variable image quality led to counterintuitive patterns in analyses that associated structural MRI and clinical measures, as inclusion of lower-quality scans altered apparent effect sizes in ways that increased risk for both false positives and negatives. Quality-related biases were partially mitigated by controlling for surface hole number, an automated index of topological complexity that differentiated lower-quality scans with good specificity at Baseline (0.81–0.93) and in 1,000 Year 2 scans (0.88–1.00). However, even among the highest-rated images, subtle topological errors occurred during image preprocessing, and their correction through manual edits significantly and reproducibly changed thickness measurements across much of the cortex (d 0.15–0.92). These findings demonstrate that inadequate QC of youth structural MRI scans can undermine advantages of large sample size to detect meaningful associations.