Journals & Publications

Title: Classification of Brain Disease in Magnetic Resonance Images using Two-Stage Local Feature Fusion

Authors: Li, T; Li, W; Yang, YH; Zhang, WS

Author Full Names: Li, Tao; Li, Wu; Yang, Yehui; Zhang, Wensheng

Source: PLOS ONE, 12 (2):10.1371/journal.pone.0171749 FEB 16 2017

Language: English

Abstract: Background Many classification methods have been proposed based on magnetic resonance images. Most methods rely on measures such as volume, the cerebral cortical thickness and grey matter density. These measures are susceptible to the performance of registration and limited in representation of anatomical structure. This paper proposes a two-stage local feature fusion method, in which deformable registration is not desired and anatomical information is represented from moderate scale. Methods Keypoints are firstly extracted from scale-space to represent anatomical structure. Then, two kinds of local features are calculated around the keypoints, one for correspondence and the other for representation. Scores are assigned for keypoints to quantify their effect in classification. The sum of scores for all effective keypoints is used to determine which group the test subject belongs to. Results We apply this method to magnetic resonance images of Alzheimer's disease and Parkinson's disease. The advantage of local feature in correspondence and representation contributes to the final classification. With the help of local feature (Scale Invariant Feature Transform, SIFT) in correspondence, the performance becomes better. Local feature (Histogram of Oriented Gradient, HOG) extracted from 16x16 cell block obtains better results compared with 4x4 and 8x8 cell block. Discussion This paper presents a method which combines the effect of SIFT descriptor in correspondence and the representation ability of HOG descriptor in anatomical structure. This method has the potential in distinguishing patients with brain disease from controls.

ISSN: 1932-6203

Article Number: e0171749

IDS Number: EL2BG

Unique ID: WOS:000394424500051

PubMed ID: 28207873

*Click Here to View Full Record