Abstract #3519

Machine Learning-based Features of DKI to Evaluate and Automate Alzheimer’s Disease and amnestic mild cognitive impairment Diagnoses

Yu Zhang¹, Tongtong Li¹, Xiuwei Fu², Xianchang Zhang³, Yuan Luo⁴, and Hongyan Ni⁵

¹First Central Clinical College, Tianjin Medical University, Tianjin, China, ²Tianjin Medical University General Hospital, Tianjin, China, ³MR Collaboration, Siemens Healthcare Ltd., Beijing, China, ⁴Department of Radiology, China-Japan Friendship Hospital, Beijing, China, ⁵Department of Radiology, Tianjin First Central Hospital, Tianjin, China

The early diagnoses of Alzheimer’s disease (AD) and amnestic mild cognitive impairment (aMCI) are crucial. This study aimed to acquire new imaging markers to assess the severity of AD and provide early diagnoses using machine learning algorithm. Diffusion kurtosis imaging (DKI) parameters were acquired on 58 AD patients, 64 aMCI patients, and 60 healthy volunteers. It’s found that radial diffusivity value of right uncinate fasciculus was the most important feature for assessing severity. The random forest classifier showed the highest diagnostic efficacy for AD. The RF classifier can provide an early diagnosis of disease based on the quantitative DKI features.

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

Join Here