Each week, we publish layman’s abstracts of new articles from our prestigious portfolio of journals in statistics. The aim is to highlight the latest research to a broader audience in an accessible format.The article featured today is from The Canadian Journal of Statistics special issue on Neuroimaging Data Analysis, with the full article now available to read here.
Liu, R., Zhu, H. and (2021), Statistical disease mapping for heterogeneous neuroimaging studies. Can J Statistics, 49: 10-34. https://doi.org/10.1002/cjs.11595
With the rapid growth of modern technology, many large-scale biomedical studies, including the Alzheimer’s disease neuroimaging initiative (ADNI) study, have been conducted to collect massive datasets with large volumes of complex information from increasingly large cohorts. Despite the numerous successes of biomedical studies, it has been difficult to unravel the etiology of cancers and neuro-related disorders largely due to large disease heterogeneity at the genomic, imaging, and clinical scales. Specifically, imaging heterogeneity often represents at both global and local scales. At the global scale, diseased regions can significantly vary across subjects and/or time in terms of their number, size, and location. At the local scale, various local imaging features can have large intra- and inter- spatial heterogeneity. Understanding such imaging heterogeneity is critical for the development of urgently needed approaches to the prevention, diagnosis, treatment, and prognosis of those diseases, and precision medicine broadly. The aim of this paper is to propose a novel statistical disease mapping (SDM) framework with several formal functional data analysis tools to address the above technical challenges in delineating disease heterogeneity at both group and individual scales. SDM consists of two components: (i) diseased regions detection at the individual level and (ii) disease map construction at the group level. Furthermore, both simulation studies and real data analysis reveal that SDM can efficiently delineate imaging heterogeneity at both global and local scales.