José V. Manjón

Patch-based Segmentation using Expert Priors: Application to Hippocampus and Ventricle Segmentation

Quantitative magnetic resonance analysis often requires accurate, robust, and reliable automatic extraction of anatomical structures. Recently, template-warping methods incorporating a label fusion strategy have demonstrated high accuracy in segmenting cerebral structures. In this study, we propose a novel patch-based method using expert manual segmentations as priors to achieve this task. Inspired by recent work in image denoising, the proposed nonlocal patch-based label fusion produces accurate and robust segmentation. Validation with two different datasets is presented. In our experiments, the hippocampi of 80 healthy subjects and the lateral ventricles of 80 patients with Alzheimers disease were segmented. The influence on segmentation accuracy of different parameters such as patch size and number of training subjects was also studied. A comparison with an appearance-based method and a template-based method was also carried out. The highest median kappa index values obtained with the proposed method were 0.884 for hippocampus segmentation and 0.959 for lateral ventricle segmentation.

Adaptive Non-Local Means Denoising of MR Images with Spatially Varying Noise Levels

To adapt the so‐called nonlocal means filter to deal with magnetic resonance (MR) images with spatially varying noise levels (for both Gaussian and Rician distributed noise).

MRI denoising using Non-Local Means

Magnetic Resonance (MR) images are affected by random noise which limits the accuracy of any quantitative measurements from the data. In the present work, a recently proposed filter for random noise removal is analyzed and adapted to reduce this noise in MR magnitude images. This parametric filter, named Non-Local Means (NLM), is highly dependent on the setting of its parameters. The aim of this paper is to find the optimal parameter selection for MR magnitude image denoising. For this purpose, experiments have been conducted to find the optimum parameters for different noise levels. Besides, the filter has been adapted to fit with specific characteristics of the noise in MR image magnitude images (i.e. Rician noise). From the results over synthetic and real images we can conclude that this filter can be successfully used for automatic MR denoising.

BEaST: brain extraction based on nonlocal segmentation technique.

Brain extraction is an important step in the analysis of brain images. The variability in brain morphology and the difference in intensity characteristics due to imaging sequences make the development of a general purpose brain extraction algorithm challenging. To address this issue, we propose a new robust method (BEaST) dedicated to produce consistent and accurate brain extraction. This method is based on nonlocal segmentation embedded in a multi-resolution framework. A library of 80 priors is semi-automatically constructed from the NIH-sponsored MRI study of normal brain development, the International Consortium for Brain Mapping, and the Alzheimers Disease Neuroimaging Initiative databases. In testing, a mean Dice similarity coefficient of 0.9834±0.0053 was obtained when performing leave-one-out cross validation selecting only 20 priors from the library. Validation using the online Segmentation Validation Engine resulted in a top ranking position with a mean Dice coefficient of 0.9781±0.0047. Robustness of BEaST is demonstrated on all baseline ADNI data, resulting in a very low failure rate. The segmentation accuracy of the method is better than two widely used publicly available methods and recent state-of-the-art hybrid approaches. BEaST provides results comparable to a recent label fusion approach, while being 40 times faster and requiring a much smaller library of priors.

Robust Rician noise estimation for MR images

In this paper, a new object-based method to estimate noise in magnitude MR images is proposed. The main advantage of this object-based method is its robustness to background artefacts such as ghosting. The proposed method is based on the adaptation of the Median Absolute Deviation (MAD) estimator in the wavelet domain for Rician noise. The MAD is a robust and efficient estimator initially proposed to estimate Gaussian noise. In this work, the adaptation of MAD operator for Rician noise is performed by using only the wavelet coefficients corresponding to the object and by correcting the estimation with an iterative scheme based on the SNR of the image. During the evaluation, a comparison of the proposed method with several state-of-the-art methods is performed. A quantitative validation on synthetic phantom with and without artefacts is presented. A new validation framework is proposed to perform quantitative validation on real data. The impact of the accuracy of noise estimation on the performance of a denoising filter is also studied. The results obtained on synthetic images show the accuracy and the robustness of the proposed method. Within the validation on real data, the proposed method obtained very competitive results compared to the methods under study.

New Methods for MRI Denoising based on Sparseness and Self-Similarity

This paper proposes two new methods for the three-dimensional denoising of magnetic resonance images that exploit the sparseness and self-similarity properties of the images. The proposed methods are based on a three-dimensional moving-window discrete cosine transform hard thresholding and a three-dimensional rotationally invariant version of the well-known nonlocal means filter. The proposed approaches were compared with related state-of-the-art methods and produced very competitive results. Both methods run in less than a minute, making them usable in most clinical and research settings.

Non-Local MRI Upsampling

In Magnetic Resonance Imaging, image resolution is limited by several factors such as hardware or time constraints. In many cases, the acquired images have to be upsampled to match a specific resolution. In such cases, image interpolation techniques have been traditionally applied. However, traditional interpolation techniques are not able to recover high frequency information of the underlying high resolution data. In this paper, a new upsampling method is proposed to recover some of this high frequency information by using a data-adaptive patch-based reconstruction in combination with a subsampling coherence constraint. The proposed method has been evaluated on synthetic and real clinical cases and compared with traditional interpolation methods. The proposed method is shown to outperform classical interpolation methods compared in terms of quantitative measures and visual observation.

Schizophrenia with auditory hallucinations: a voxel-based morphometry study.

Many studies have shown widespread but subtle pathological changes in gray matter in patients with schizophrenia. Some of these studies have related specific alterations to the genesis of auditory hallucinations, particularly in the left superior temporal gyrus, but none has analysed the relationship between morphometric data and a specific scale for auditory hallucinations. The present study aims to define the presence and characteristics of structural abnormalities in relation with the intensity and phenomenology of auditory hallucinations by means of magnetic resonance voxel-based morphometry (MR-VBM) method applied on a highly homogeneous group of 18 persistent hallucinatory patients meeting DSM-IV criteria for schizophrenia compared to 19 healthy matched controls. Patients were evaluated using the PSYRATS scale for auditory hallucinations. Reductions of gray matter concentration in patients to controls were observed in bilateral insula, bilateral superior temporal gyri and left amygdala. In addition, specific relationships between left inferior frontal and right postcentral gyri reductions and the severity of auditory hallucinations were observed. All these areas might be implicated in the genesis and/or persistence of auditory hallucinations through specific mechanisms. Precise morphological abnormalities may help to define reliable MR-VBM biomarkers for the genesis and persistence of auditory hallucinations.

Diffusion Weighted Image Denoising Using Overcomplete Local PCA

Diffusion Weighted Images (DWI) normally shows a low Signal to Noise Ratio (SNR) due to the presence of noise from the measurement process that complicates and biases the estimation of quantitative diffusion parameters. In this paper, a new denoising methodology is proposed that takes into consideration the multicomponent nature of multi-directional DWI datasets such as those employed in diffusion imaging. This new filter reduces random noise in multicomponent DWI by locally shrinking less significant Principal Components using an overcomplete approach. The proposed method is compared with state-of-the-art methods using synthetic and real clinical MR images, showing improved performance in terms of denoising quality and estimation of diffusion parameters.

Simultaneous segmentation and grading of anatomical structures for patient's classification: application to Alzheimer's disease.

In this paper, we propose an innovative approach to robustly and accurately detect Alzheimers disease (AD) based on the distinction of specific atrophic patterns of anatomical structures such as hippocampus (HC) and entorhinal cortex (EC). The proposed method simultaneously performs segmentation and grading of structures to efficiently capture the anatomical alterations caused by AD. Known as SNIPE (Scoring by Non-local Image Patch Estimator), the novel proposed grading measure is based on a nonlocal patch-based frame-work and estimates the similarity of the patch surrounding the voxel under study with all the patches present in different training populations. In this study, the training library was composed of two populations: 50 cognitively normal subjects (CN) and 50 patients with AD, randomly selected from the ADNI database. During our experiments, the classification accuracy of patients (CN vs. AD) using several biomarkers was compared: HC and EC volumes, the grade of these structures and finally the combination of their volume and their grade. Tests were completed in a leave-one-out framework using discriminant analysis. First, we showed that biomarkers based on HC provide better classification accuracy than biomarkers based on EC. Second, we demonstrated that structure grading is a more powerful measure than structure volume to distinguish both populations with a classification accuracy of 90%. Finally, by adding the ages of subjects in order to better separate age-related structural changes from disease-related anatomical alterations, SNIPE obtained a classification accuracy of 93%.