Abstract #2352

Use of population-specific atlases for brain morphometry: benefits in Alzheimer’s Disease diagnosis decision support for Chinese patients

Bénédicte Maréchal^1,2,3, Peipeng Liang^4,5,6, Lin Shi⁷, Tianyi Qian⁸, Defeng Wang^5,6, Tobias Kober^1,2,3, Alexis Roche^1,2,3, and Kuncheng Li⁴

¹Advanced Clinical Imaging Technology, Siemens Healthcare HC CEMEA SUI DI PI, Lausanne, Switzerland, ²Department of Radiology, CHUV, Lausanne, Switzerland, ³LTS5, EPFL, Lausanne, Switzerland, ⁴Department of Radiology, Xuanwu Hospital, Capital Medical University, Beijing, China, ⁵Research Center for Medical Image Computing, Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, China, ⁶Shenzhen Research Institute, The Chinese University of Hong Kong, Shenzhen, China, ⁷Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Shatin, NT, Hong Kong, ⁸MR Collaboration Northeast Asia, Siemens Healthcare, Beijing, China

We investigate the potential of a Chinese-specific brain atlas derived from a large MR database of healthy Chinese subjects to accurately support Alzheimer’s Disease diagnosis using automated brain volumetry in the Chinese population. Our experiments show that disease detection sensitivity is higher than when using either a Westerner-specific atlas and normative ranges or combining a Westerner atlas with Chinese-specific normative ranges. These findings suggest that population-specific models improve the reliability of medical decision support systems based on automated brain volumetry.

This abstract and the presentation materials are available to members only; a login is required.

Join Here