Multiscale spatial gradient features for 18F-FDG PET image-guided diagnosis of Alzheimer’s disease

• Published in: Computer methods and programs in biomedicine Vol. 180; p. 105027
• Main Authors: Pan, Xiaoxi, Adel, Mouloud, Fossati, Caroline, Gaidon, Thierry, Wojak, Julien, Guedj, Eric
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2019; Elsevier
• Subjects: 18F-FDG PET; Alzheimer’s disease; Ensemble classification; Human health and pathology; Life Sciences; Multiscale spatial gradients; Multiscale spatial gradients; 18F-FDG PET; Ensemble classification; Alzheimer’s disease
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2019.105027

•The spatial gradient feature is applied to capture discriminative pat- terns of 18F-FDG PET brain images in Alzheimer’s Disease diagnosis.•A region ranking method is proposed based on multiple small scale spatial gradient features, namely Small Scale HOG (SSH), which can guide the region selection.•An ensemble classification framework is designed which takes into ac- count the performance of individual region and concatenated regions.•Results of multiple classification are reported and analyzed, and results show that using the spatial gradient feature to characterize 18F-FDG PET images is effective. Background and Objective:18F-FluoroDeoxyGlucose Positron Emission Tomography (18F-FDG PET) is one of the imaging biomarkers to diagnose Alzheimer’s Disease (AD). In 18F-FDG PET images, the changes of voxels’ intensities reflect the differences of glucose rates, therefore voxel intensity is usually used as a feature to distinguish AD from Normal Control (NC), or at earlier stage to distinguish between progressive and stable Mild Cognitive Impairment (pMCI and sMCI). In this paper, 18F-FDG PET images are characterized in an alternative way—the spatial gradient, which is motivated by the observation that the changes of 18F-FDG rates also cause gradient changes. Methods: We improve Histogram of Oriented Gradient (HOG) descriptor to quantify spatial gradients, thereby achieving the goal of diagnosing AD. First, the spatial gradient of 18F-FDG PET image is computed, and then each subject is segmented into different regions by using an anatomical atlas. Second, two types of improved HOG features are extracted from each region, namely Small Scale HOG and Large Scale HOG, then some relevant regions are selected based on a classifier fed with spatial gradient features. Last, an ensemble classification framework is designed to make a decision, which considers the performance of both individual and concatenated selected regions. Results: the evaluation is done on ADNI dataset. The proposed method outperforms other state-of-the-art 18F-FDG PET-based algorithms for AD vs. NC with an accuracy, a sensitivity and a specificity values of 93.65%, 91.22% and 96.25%, respectively. For the case of pMCI vs. sMCI, the three metrics are 75.38%, 74.84% and 77.11%, which is significantly better than most existing methods. Besides, promising results are also achieved for multiple classifications under 18F-FDG PET modality. Conclusions:18F-FDG PET images can be characterized by spatial gradient features for diagnosing AD and its early stage, and the proposed ensemble framework can enhance the classification performance.