当前位置: X-MOL 学术Neuroinformatics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Generating Longitudinal Atrophy Evaluation Datasets on Brain Magnetic Resonance Images Using Convolutional Neural Networks and Segmentation Priors
Neuroinformatics ( IF 3 ) Pub Date : 2021-01-02 , DOI: 10.1007/s12021-020-09499-z
Jose Bernal 1 , Sergi Valverde 1 , Kaisar Kushibar 1 , Mariano Cabezas 1 , Arnau Oliver 1 , Xavier Lladó 1 ,
Affiliation  

Brain atrophy quantification plays a fundamental role in neuroinformatics since it permits studying brain development and neurological disorders. However, the lack of a ground truth prevents testing the accuracy of longitudinal atrophy quantification methods. We propose a deep learning framework to generate longitudinal datasets by deforming T1-w brain magnetic resonance imaging scans as requested through segmentation maps. Our proposal incorporates a cascaded multi-path U-Net optimised with a multi-objective loss which allows its paths to generate different brain regions accurately. We provided our model with baseline scans and real follow-up segmentation maps from two longitudinal datasets, ADNI and OASIS, and observed that our framework could produce synthetic follow-up scans that matched the real ones (Total scans= 584; Median absolute error: 0.03 ± 0.02; Structural similarity index: 0.98 ± 0.02; Dice similarity coefficient: 0.95 ± 0.02; Percentage of brain volume change: 0.24 ± 0.16; Jacobian integration: 1.13 ± 0.05). Compared to two relevant works generating brain lesions using U-Nets and conditional generative adversarial networks (CGAN), our proposal outperformed them significantly in most cases (p < 0.01), except in the delineation of brain edges where the CGAN took the lead (Jacobian integration: Ours - 1.13 ± 0.05 vs CGAN - 1.00 ± 0.02; p < 0.01). We examined whether changes induced with our framework were detected by FAST, SPM, SIENA, SIENAX, and the Jacobian integration method. We observed that induced and detected changes were highly correlated (Adj. R2 > 0.86). Our preliminary results on harmonised datasets showed the potential of our framework to be applied to various data collections without further adjustment.



中文翻译:

使用卷积神经网络和分割先验在脑磁共振图像上生成纵向萎缩评估数据集

脑萎缩量化在神经信息学中起着重要作用,因为它允许研究大脑发育和神经系统疾病。然而,缺乏基本事实会妨碍测试纵向萎缩量化方法的准确性。我们提出了一个深度学习框架,通过根据分割图的要求对 T1-w 脑磁共振成像扫描进行变形来生成纵向数据集。我们的提议结合了一个级联的多路径 U-Net,优化了多目标损失,使其路径能够准确地生成不同的大脑区域。我们为我们的模型提供了来自两个纵向数据集 ADNI 和 OASIS 的基线扫描和真实后续分割图,并观察到我们的框架可以生成与真实数据相匹配的合成后续扫描(总扫描 = 584;中值绝对误差:0.03±0.02;结构相似性指数:0.98±0.02;骰子相似系数:0.95±0.02;脑容量变化百分比:0.24±0.16;雅可比积分:1.13 ± 0.05)。与使用 U-Net 和条件生成对抗网络 (CGAN) 产生脑损伤的两项相关工作相比,我们的提议在大多数情况下明显优于它们(p < 0.01),除了 CGAN 领先的大脑边缘描绘(雅可比积分:我们的 - 1.13 ± 0.05 vs CGAN - 1.00 ± 0.02;p < 0.01)。我们检查了我们的框架引起的变化是否被 FAST、SPM、SIENA、SIENAX 和雅可比积分方法检测到。我们观察到诱导和检测到的变化高度相关 (Adj. R 2 > 0.86)。我们对协调数据集的初步结果表明,我们的框架有可能无需进一步调整即可应用于各种数据收集。

更新日期:2021-01-03
down
wechat
bug