AGE ESTIMATION FROM BRAIN MRI IMAGES USING DEEP LEARNING

被引：0

作者：

Huang, Tzu-Wei ^{[1
]}

Chen, Hwann-Tzong ^{[1
]}

Fujimoto, Ryuichi ^{[2
]}

Ito, Koichi ^{[2
]}

Wu, Kai ^{[3
]}

Sato, Kazunori ^{[4
]}

Taki, Yasuyuki ^{[4
]}

Fukuda, Hiroshi ^{[5
]}

Aoki, Takafumi ^{[2
]}

机构：

[1] Natl Tsing Hua Univ, Dept Comp Sci, Hsinchu, Taiwan

[2] Tohoku Univ, Grad Sch Informat Sci, Sendai, Miyagi, Japan

[3] South China Univ Technol, Guangzhou, Guangdong, Peoples R China

[4] Tohoku Univ, Inst Dev Aging & Canc, Sendai, Miyagi, Japan

[5] Tohoku Med & Pharmaceut Univ, Sendai, Miyagi, Japan

来源：

2017 IEEE 14TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2017) | 2017年

关键词：

MRI; T1-weighted image; deep learning; age estimation; brain-aging;

D O I：

暂无

中图分类号：

Q5 [生物化学];

学科分类号：

071010 ; 081704 ;

摘要：

Estimating human age from brain MR images is useful for early detection of Alzheimer's disease. In this paper we propose a fast and accurate method based on deep learning to predict subject's age. Compared with previous methods, our algorithm achieves comparable accuracy using fewer input images. With our GPU version program, the time needed to make a prediction is 20 ms. We evaluate our methods using mean absolute error (MAE) and our method is able to predict subject's age with MAE of 4.0 years.

引用

页码：849 / 852

页数：4

共 6 条

[1]

[Anonymous], BIGLEARN NIPS WORKSH

[2] Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: Exploring the influence of various parameters [J].