TY - CHAP
T1 - Anatomical-Landmark-Based Deep Learning for Alzheimer’s Disease Diagnosis with Structural Magnetic Resonance Imaging
AU - Liu, Mingxia
AU - Lian, Chunfeng
AU - Shen, Dinggang
N1 - Funding Information:
This study was partly supported by NIH grants (EB006733, EB008374, EB009634, MH100217, AG041721, AG042599, AG010129, and AG030514). Data used in preparation of this article were obtained from the Alzheimer?s Disease Neuroimaging Initiative (ADNI) database. The investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report, with details shown online.
Publisher Copyright:
© 2020, Springer Nature Switzerland AG.
PY - 2020
Y1 - 2020
N2 - Structural magnetic resonance imaging (sMRI) has been widely used in computer-aided diagnosis of brain diseases, such as Alzheimer’s disease (AD) and its prodromal stage, i.e., mild cognitive impairment (MCI). Based on sMRI data, anatomical-landmark-based deep learning has been recently proposed for AD and MCI diagnosis. These methods usually first locate informative anatomical landmarks in brain sMR images, and then integrate both feature learning and classification training into a unified framework. This chapter presents the latest anatomical-landmark-based deep learning approaches for automatic diagnosis of AD and MCI. Specifically, an automatic landmark discovery method is first introduced to identify discriminative regions in brain sMR images. Then, a landmark-based deep learning framework is presented for AD/MCI classification, by jointly performing feature extraction and classifier training. Experimental results on three public databases demonstrate that the proposed framework boosts the disease diagnosis performance, compared with several state-of-the-art sMRI-based methods.
AB - Structural magnetic resonance imaging (sMRI) has been widely used in computer-aided diagnosis of brain diseases, such as Alzheimer’s disease (AD) and its prodromal stage, i.e., mild cognitive impairment (MCI). Based on sMRI data, anatomical-landmark-based deep learning has been recently proposed for AD and MCI diagnosis. These methods usually first locate informative anatomical landmarks in brain sMR images, and then integrate both feature learning and classification training into a unified framework. This chapter presents the latest anatomical-landmark-based deep learning approaches for automatic diagnosis of AD and MCI. Specifically, an automatic landmark discovery method is first introduced to identify discriminative regions in brain sMR images. Then, a landmark-based deep learning framework is presented for AD/MCI classification, by jointly performing feature extraction and classifier training. Experimental results on three public databases demonstrate that the proposed framework boosts the disease diagnosis performance, compared with several state-of-the-art sMRI-based methods.
UR - http://www.scopus.com/inward/record.url?scp=85075530250&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-32606-7_8
DO - 10.1007/978-3-030-32606-7_8
M3 - Chapter
AN - SCOPUS:85075530250
T3 - Intelligent Systems Reference Library
SP - 127
EP - 147
BT - Intelligent Systems Reference Library
PB - Springer
ER -