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 on18F-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%.

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).

FluoroDeoxyGlucose Positron Emission Tomography (FDG- PET) is an important and effective modality used for diagnosing Alzheimer's Disease (AD) or Mild Cognitive Impairment (MCI). In this paper, we develop a novel method by using single modality (FDG- PET) but multi-level features, which considers both region properties and connectivities between regions, to diagnose AD or MCI. First, post-processed FDG-PET images are segmented into 116 Regions of Interest according to Automated Anatomical Labeling atlas. Second, three levels of features are extracted. Then the 2nd-Level feature is decomposed into 3 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 3 levels of features to different classifiers, the majority voting, is applied to make the prediction. Experiments on ADNI database show that the proposed method outperforms other FDG-PET-based classification algorithms.

Linear structures such as blood vessels in medical images are important features for computer-aided diagnosis and follow-up of many diseases. In this letter a new tracking-based segmentation method is proposed to detect blood vessels in retinal angiorams. Bayesian segmentation with the maximum a posteriori (MAP) probability criterion is used for that purpose. First promising results are presented and discussed.

The optimal detection and location of a target in a scene in presence of non-additive noise is studied. The optimal processors in the maximum likelihood sense are determined for different white or correlated noise statistics. It is shown that the required computations are mainly correlations, and that there is no need of iterative methods.

This paper deals with a new method for estimation of motion field in image sequence coding domain. The proposed method is based on a pel-recursive technique and characterised by two fundamental points: the use of a convex function for the regularization and a deterministic relaxation algorithm for edge preserving regularization. These two points are completely new in motion estimation techniques.>

Introduces a new image coding scheme using lattice vector quantization. The proposed method involves two steps: biorthogonal wavelet transform of the image, and lattice vector quantization of wavelet coefficients. In order to obtain a compromise between minimum distortion and bit rate, we must truncate and scale the lattice suitably. To meet this goal, we need to know how many lattice points lie within the truncated area. We investigate the case of Laplacian sources where surfaces of equal probability are spheres for the L(1) metric (pyramids) for arbitrary lattices. We give explicit generating functions for the codebook sizes for the most useful lattices like Z(n), D(n), E(s), wedge(16).

A new method of multiresolution edge detection is described. This method is based on a recursive biorthogonal wavelet transform which relates the digital filter to a continuous analysis function, the so-called wavelet. In biorthogonal wavelet analysis, there is a high-pass filter corresponding to the wavelet and a low-pass filter corresponding to the scaling function. The new idea is to compute optimal edge detection filters which yield multiresolution analysis (continuous wavelet). The high-pass filter (infinite impulse filter) is chosen in order to have first derivative properties. The family of low-pass filters is deduced from the high-pass filter using wavelet transform theory relations. The detection filters are proposed as a trade-off between detection, localization and regularity criteria.>