This paper describes a segmentation algorithm designed to separate bone from soft tissue in magnetic resonance (MR) images developed for computer-assisted surgery of the spine. The algorithm was applied to MR images of the spine of healthy volunteers. Registration experiments were carried out on a physical model of a spine generated from computed tomography (CT) data of a surgical patient. Segm...

Mutual information (MI) is a widely used similarity metric for multimodality image registration. However, it involves an extremely high computational time especially when it is applied to volume images. Moreover, its robustness is affected by existence of local maxima. The multi-resolution pyramid approaches have been proposed to speed up the registration process and increase the accuracy of th...

Cochlear nerve (CN) aplasia refers to the absence of a visible CN on oblique sagittal magnetic resonance images of the lateral aspect of the inner auditory canal (IAC). Magnetic resonance (MR) is the preferred technique in patients with sensorineural hearing loss and/or vertigo; however, computed tomography (CT) is used to evaluate the IAC or facial nerve canal. Three types of aplasia or hypopl...

BACKGROUND AND PURPOSE Early assignment of disease progression among patients with X-linked adrenoleukodystrophy (ALD) is critical for the appropriate selection of effective therapy. We evaluated the association between contrast enhancement on T1-weighted spin-echo MR images and disease progression. METHODS Clinical charts of patients with X-linked ALD were reviewed for age, availability of M...

This study compares the visualization of otic capsule anatomy by thin-section three-dimensional Fourier transformation (3DFT) MR imaging with that by high-resolution CT. The osseous margins of the otic capsule are delineated by high-resolution CT, while MR displays the soft-tissue structures. Routine two-dimensional Fourier transformation (2DFT) spin-echo MR techniques have been limited by slic...

In this paper, a method is developed that reconstructs a high resolution image from an arbitrary set of multi-slice 3D MR images with a high in-plane resolution and a low through-plane resolution. Such images are often recorded to increase the efficiency of the acquisition. With a model of the acquisition of MR images, which is improved compared to previous super-resolution methods for MR image...

BACKGROUND AND PURPOSE Proton (hydrogen-1 [(1)H]) MR spectroscopy is a useful diagnostic tool in many metabolic diseases, but only scattered and inconclusive data are available on mitochondrial diseases. We performed MR imaging and (1)H MR spectroscopy of the brain in patients with different types of primary mitochondrial diseases to investigate the role of (1)H MR spectroscopy in the clinical ...

Medical image translation has the potential to reduce imaging workload, by removing need capture some sequences, and annotation burden for developing machine learning methods. GANs have been used successfully translate images from one domain another, such as MR CT. At present, paired data (registered CT images) or extra supervision (e.g. segmentation masks) is needed learn good models. Register...

this paper represents a new region-based active contour model that can be used to segment images with intensity non-uniformity and high level noise. the main idea of our proposed method is to use gaussian distributions with different means and variances with incorporation of intensity non-uniformity model for image segmentation. in order to integrate the spatial information between neighboring ...

Plain and Gd-DTPA-enhanced MR images of the brain were obtained in 18 consecutive patients with meningitis (eight with tuberculous, five with bacterial, three with viral, and two with fungal infections); the MR images were compared with CT scans. MR images were obtained on a 2.0-T superconducting unit with both T1- and T2-weighted pulse sequences before injection and with a T1-weighted sequence...