Multi‐channel IIT and Rush University Aging (MIITRA) Atlas: Development and evaluation of multimodal templates of the older adult brain

• Published in: Alzheimer's & dementia Vol. 16
• Main Authors: Wu, Yingjuan, Ridwan, Abdur Raquib, Qi, Xiaoxiao, Zhang, Shengwei, Bennett, David A, Arfanakis, Konstantinos
• Format: Journal Article
• Language: English
• Published: 01.12.2020
• ISSN: 1552-5260; 1552-5279
• DOI: 10.1002/alz.041276

Background Recent years have seen an increasing demand for multimodal MRI templates of the older adult brain. As part of the Multi‐channel IIT and Rush university Aging (MIITRA) atlas, this work aimed to develop high quality multi‐modal T1‐weighted (T1w) and diffusion tensor imaging (DTI) templates of the older adult brain. This was accomplished through a proposed iterative multimodal template construction strategy. Method Template construction: T1w and DTI data on 202 non‐demented older adults (50% male,65.2‐94.9 yrs) from Rush MAP were used. DTI data were aligned to the raw T1w images. In the proposed approach, each iteration includes two steps(Fig.1). In step1, a temporary T1w template is generated and the resulting transformations are also applied to the DTI data. In step2, a temporary DTI template is generated and the resulting transformations are also applied to the T1w data. The template quality at each iteration was assessed through the spatial matching of deformed data. The T1w and DTI template spatial matching was assessed by the overlap between the white matter tissue probability map and the FA map. Comparison to other templates: For the evaluation, T1w and DTI data on 202 non‐demented older adults from ADNI3 were used. The new MIITRA templates generated through the proposed approach were compared with study‐specific template(constructed using evaluation data) and other standardized templates including older adults in terms of inter‐subject spatial normalization accuracy and inter‐modality spatial matching when used as reference for normalization of evaluation data. Results Figure 2 demonstrates that the spatial normalization of the T1w and DTI data used to construct the templates improves(p<10‐10) and the spatial matching between the T1w and DTI templates also improves(p<10‐10), suggesting better quality of the templates with more iterations. Figure 4 to 6 show that the new MIITRA templates allow higher spatial normalization accuracy of data from older adults compared to other available templates(p<10‐10). Conclusion This work proposed a new multimodal templates construction approach and generated new MIITRA T1w and DTI templates of the older adult brain in the same space, which allow better spatial normalization of T1w and DTI data from older adults compared to other available templates.