Multi-View Separable Pyramid Network for AD Prediction at MCI Stage by 18F-FDG Brain PET Imaging.

Alzheimer's Disease (AD), one of the main causes of death in elderly people, is characterized by Mild Cognitive Impairment (MCI) at prodromal stage. Nevertheless, only part of MCI subjects could progress to AD. The main objective of this paper is thus to identify those who will develop a dementia of AD type among MCI patients. 18F-FluoroDeoxyGlucose Positron Emission Tomography (18F-FDG PET) serves as a neuroimaging modality for early diagnosis as it can reflect neural activity via measuring glucose uptake at resting-state. In this paper, we design a deep network on 18F-FDG PET modality to address the problem of AD identification at early MCI stage. To this end, a Multi-view Separable Pyramid Network (MiSePyNet) is proposed, in which representations are learned from axial, coronal and sagittal views of PET scans so as to offer complementary information and then combined to make a decision jointly. Different from the widely and naturally used 3D convolution operations for 3D images, the proposed architecture is deployed with separable convolution from slice-wise to spatial-wise successively, which can retain the spatial information and reduce training parameters compared to 2D and 3D networks, respectively. Experiments on ADNI dataset show that the proposed method can yield better performance than both traditional and deep learning-based algorithms for predicting the progression of Mild Cognitive Impairment, with a classification accuracy of 83.05%.

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.

Multilevel Feature Representation of FDG-PET Brain Images for Diagnosing Alzheimer's Disease.

Using a single imaging modality to diagnose Alzheimer's disease (AD) or mild cognitive impairment (MCI) is a challenging task. FluoroDeoxyGlucose Positron Emission Tomography (FDG-PET) is an important and effective modality used for that purpose. In this paper, we develop a novel method by using single modality (FDG-PET) but multilevel feature, which considers both region properties and connectivities between regions to classify AD or MCI from normal control. First, three levels of features are extracted: statistical, connectivity, and graph-based features. Then, the connectivity features are decomposed into three different sets of features according to a proposed similarity-driven ranking method, which can not only reduce the feature dimension but also increase the classifier's diversity. Last, after feeding the three levels of features to different classifiers, a new classifier selection strategy, maximum Mean squared Error (mMsE), is developed to select a pair of classifiers with high diversity. In order to do the majority voting, a decision-making scheme, a nested cross validation technique is applied to choose another classifier according to the accuracy. Experiments on Alzheimer's Disease Neuroimaging Initiative database show that the proposed method outperforms most FDG-PET-based classification algorithms, especially for classifying progressive MCI (pMCI) from stable MCI (sMCI).

Efficient time of arrival estimation in the presence of multipath propagation.

Most of acoustical experiments face multipath propagation issues. The times of arrival of different ray paths on a sensor can be very close. To estimate them, high resolution algorithms have been developed. The main drawback of these methods is their need of a full rank spectral matrix of the signals. The frequential smoothing technique overcomes this issue by dividing the received signal spectrum into several overlapping sub-bands. This division yields a transfer matrix that may suffer rank deficiency. In this paper, a new criterion to optimally choose the sub-band frequencies is proposed. Encouraging results were obtained on real-world data.

Fast approximation of transfer cross coefficient for optical proximity correction.

Model Based Optical Proximity Correction (MBOPC) is since a decade a widely used technique that permits to achieve resolutions on silicon layout smaller than the wavelength used in commercially-available photolithography tools. This is an important point, because patterns dimensions on masks are continuously shrinking. Commonly-used algorithms, involving Transfer Cross Coefficients (TCC) drawn from Hopkins formulation to compute aerial images during MBOPC treatment are based on TCC decomposition into its eigenvectors using matricization and the well known Singular Value Decomposition (SVD) tool. This technique remains highly runtime consuming. We propose in this paper to extend a fast fixed point algorithm to estimate an a priori fixed number of leading eigenvectors required to obtain a good approximation while ensuring a low information loss for computing aerial images.

The finite element method as applied to the diffraction by an anisotropic grating.

The main goal of the method proposed in this paper is the numerical study of various kinds of anisotropic gratings deposited on isotropic substrates, without any constraint upon the diffractive pattern geometry or electromagnetic properties. To that end we propose a new FEM (Finite Element Method) formulation which rigorously deals with each infinite issue inherent to grating problems. As an example, 2D numerical experiments are presented in the cases of the diffraction of a plane wave by an anisotropic aragonite grating on silica substrate (for the two polarization cases and at normal or oblique incidence). We emphasize the interesting property that the diffracted field is non symmetric in a geometrically symmetric configuration.

Integrated photothermal microscope and laser damage test facility for in-situ investigation of nanodefect induced damage.

An integrated setup allowing high resolution photothermal microscopy and laser damage measurements at the same wavelength has been implemented. The microscope is based on photothermal deflection of a transmitted probe beam : the probe beam (633 nm wavelength) and the CW pump beam (1.06 microm wavelength) are collinear and focused through the same objective. In-situ laser irradiation tests are performed thanks to a pulsed beam (1.06 microm wavelength and 6 nanosecond pulse). We describe this new facility and show that it is well adapted to the detection of sub-micronic absorbing defects, that, once located, can be precisely aimed and irradiated. Photothermal mappings are performed before and after shot, on metallic inclusions in dielectric. Results obtained on gold inclusions of about 600 nm in diameter embedded in silica are presented.

Multiwavelength imaging of defects in ultraviolet optical materials.

Laser-induced damage in bare glass substrates and thin films has long been widely acknowledged as a localized phenomenon associated with the presence of micrometer and submicrometer scale defects. The scanning of both optical absorption and scattering allows us to discriminate between absorbing and nonabsorbing defects and can give specific information about the origin of the defects. We investigate the spectral properties of defects in thin films and fused-silica surfaces. Absorbing and scattering defects are studied at different wavelengths in the ultraviolet, visible, and infrared ranges. Absorbing defects are shown to be highly wavelength dependent, whereas we have observed significant correlation between scattering defects.