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

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.

[1]  J. O'Brien,et al.  A comparison of FDG‐PET and blood flow SPECT in the diagnosis of neurodegenerative dementias: a systematic review , 2014, International journal of geriatric psychiatry.

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  Daniel Rueckert,et al.  Random forest-based similarity measures for multi-modal classification of Alzheimer's disease , 2013, NeuroImage.

[4]  Danni Cheng,et al.  Classification of Alzheimer’s Disease by Combination of Convolutional and Recurrent Neural Networks Using FDG-PET Images , 2018, Front. Neuroinform..

[5]  Christos Davatzikos,et al.  A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages , 2017, NeuroImage.

[6]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[7]  Sotirios Bisdas,et al.  The diagnostic value of FDG and amyloid PET in Alzheimer's disease-A systematic review. , 2017, European journal of radiology.

[8]  Margarida Silveira,et al.  Predicting conversion from MCI to AD with FDG-PET brain images at different prodromal stages , 2015, Comput. Biol. Medicine.

[9]  J. Weuve,et al.  Alzheimer disease in the United States (2010–2050) estimated using the 2010 census , 2013, Neurology.

[10]  M. Prince,et al.  World Alzheimer report 2016: improving healthcare for people living with dementia: coverage, quality and costs now and in the future , 2016 .

[11]  N. Tzourio-Mazoyer,et al.  Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain , 2002, NeuroImage.

[12]  I. Lombardo,et al.  The efficacy of RVT-101, a 5-ht6 receptor antagonist, as an adjunct to donepezil in adults with mild-to-moderate Alzheimer’s disease: Completer analysis of a phase 2b study , 2015, Alzheimer's & Dementia.

[13]  A. Chincarini,et al.  Volume of interest-based [18F]fluorodeoxyglucose PET discriminates MCI converting to Alzheimer's disease from healthy controls. A European Alzheimer's Disease Consortium (EADC) study , 2014, NeuroImage: Clinical.

[14]  Dinggang Shen,et al.  Subspace Regularized Sparse Multitask Learning for Multiclass Neurodegenerative Disease Identification , 2016, IEEE Transactions on Biomedical Engineering.

[15]  Dinggang Shen,et al.  Effective feature learning and fusion of multimodality data using stage‐wise deep neural network for dementia diagnosis , 2018, Human brain mapping.

[16]  Mirza Faisal Beg,et al.  Multiscale deep neural network based analysis of FDG‐PET images for the early diagnosis of Alzheimer's disease , 2018, Medical Image Anal..

[17]  Moo K. Chung,et al.  Spatially augmented LPboosting for AD classification with evaluations on the ADNI dataset , 2009, NeuroImage.

[18]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[19]  Yiming Ding,et al.  A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain. , 2019, Radiology.

[20]  Daoqiang Zhang,et al.  Domain Transfer Learning for MCI Conversion Prediction , 2015, IEEE Transactions on Biomedical Engineering.

[21]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[22]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[23]  S. de Santi,et al.  Pre-clinical detection of Alzheimer's disease using FDG-PET, with or without amyloid imaging. , 2010, Journal of Alzheimer's disease : JAD.

[24]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Salah Bourennane,et al.  Histogram-Based Features Selection and Volume of Interest Ranking for Brain PET Image Classification , 2018, IEEE Journal of Translational Engineering in Health and Medicine.

[26]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[27]  Karl J. Friston,et al.  Statistical parametric mapping , 2013 .

[28]  Stefan Kramer,et al.  Gaussian Mixture Models and Model Selection for [18F] Fluorodeoxyglucose Positron Emission Tomography Classification in Alzheimer’s Disease , 2015, PloS one.

[29]  Daoqiang Zhang,et al.  Relationship Induced Multi-Template Learning for Diagnosis of Alzheimer’s Disease and Mild Cognitive Impairment , 2016, IEEE Transactions on Medical Imaging.

[30]  Caroline Fossati,et al.  Multilevel Feature Representation of FDG-PET Brain Images for Diagnosing Alzheimer's Disease , 2019, IEEE Journal of Biomedical and Health Informatics.

[31]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[32]  Daniel Rueckert,et al.  Multi-region analysis of longitudinal FDG-PET for the classification of Alzheimer's disease , 2012, NeuroImage.

[33]  Juan Manuel Górriz,et al.  NMF-SVM Based CAD Tool Applied to Functional Brain Images for the Diagnosis of Alzheimer's Disease , 2012, IEEE Transactions on Medical Imaging.