Multiscale deep neural network based analysis of FDG-PET images for the early diagnosis of Alzheimer's disease.
Medical Image Analysis(2018)
摘要
•Proposed a novel multiscale deep neural network to learn the patterns of metabolism changes due to AD pathology as discriminative from the patterns of metabolism in normal controls (NC).•Showed that by transferring samples from NC and AD individuals, the deep architecture can obtain better discriminative ability in the early diagnosis task.•Demonstrated that ensemble multiple classifiers with different validation settings can make the proposed method more stable and robust, and improve its classification performance.•We present a comprehensive validation of our method analyzing metabolism measures taken from 1051 subjects that were processed with stringent quality control requirements including expert manual editing of all segmentations for ensuring accuracy. To-date, our study is perhaps the first study to utilize such a large number of FDG-PET images, and hence, these results indicate good potential for generalizability.
更多查看译文
关键词
Alzheimer’s disease,Multiscale deep neural network learning,Metabolism FDG-PET,Early diagnosis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络