Brain Tissues In Magnetic Resonance Images Research Articles

A Squeeze U-SegNet Architecture Based on Residual Convolution for Brain MRI Segmentation

This paper proposes an improved brain magnetic resonance imaging (MRI) segmentation model by integrating U-SegNet with fire modules and residual convolutions to segment brain tissues in MRI. In the proposed encoder-decoder method, the residual connections and squeeze-expand convolutional layers from the fire module lead to a lighter and more efficient architecture for brain MRI segmentation. The residual unit helps in the smooth training of the deep architecture, and features obtained from residual convolutions exhibit a superior representation of the features in the segmentation network. In addition, the method provides a design with more efficient architecture, fewer network parameters, and better segmentation accuracy for brain MRI. The proposed architecture was evaluated on publicly available open access series of imaging studies (OASIS) and internet brain segmentation repository (IBSR) datasets for brain tissue segmentation. The experimental results showed superior performance compared to other state-of-the-art methods on brain MRI segmentation with a dice similarity coefficient (DSC) score of 0.96 and Jaccard index (JI) of 0.92.

Maximum Evidence Method for classification of brain tissues in MRI

Within the family of statistical image segmentation methods, those based on Bayesian inference have been commonly applied to classify brain tissues as obtained with Magnetic Resonance Imaging (MRI). In this framework we present an unsupervised algorithm to account for the main tissue classes that constitute MR brain volumes. Two models are examined: the Discrete Model (DM), in which every voxel belongs to a single tissue class, and the Partial Volume Model (PVM), where two classes may be present in a single voxel with a certain probability. We make use of the Maximum Evidence (ME) criterion to estimate the most probable parameters describing each model in a separate fashion. Since an exact image inference would be computationally very expensive, we propose an approximate algorithm for model optimization. Such method was tested on a simulated MRI-T1 brain phantom in 3D, as well as on clinical MR images. As a result, we found that the PVM slightly outperforms the DM, both in terms of Evidence and Mean Absolute Error (MAE). We also show that the Evidence is a very useful figure of merit for error prediction as well as a convenient tool to determine the most probable model from measured data.

Simulation of brain tumors in MR images for evaluation of segmentation efficacy.

Obtaining validation data and comparison metrics for segmentation of magnetic resonance images (MRI) are difficult tasks due to the lack of reliable ground truth. This problem is even more evident for images presenting pathology, which can both alter tissue appearance through infiltration and cause geometric distortions. Systems for generating synthetic images with user-defined degradation by noise and intensity inhomogeneity offer the possibility for testing and comparison of segmentation methods. Such systems do not yet offer simulation of sufficiently realistic looking pathology. This paper presents a system that combines physical and statistical modeling to generate synthetic multi-modal 3D brain MRI with tumor and edema, along with the underlying anatomical ground truth, Main emphasis is placed on simulation of the major effects known for tumor MRI, such as contrast enhancement, local distortion of healthy tissue, infiltrating edema adjacent to tumors, destruction and deformation of fiber tracts, and multi-modal MRI contrast of healthy tissue and pathology. The new method synthesizes pathology in multi-modal MRI and diffusion tensor imaging (DTI) by simulating mass effect, warping and destruction of white matter fibers, and infiltration of brain tissues by tumor cells. We generate synthetic contrast enhanced MR images by simulating the accumulation of contrast agent within the brain. The appearance of the the brain tissue and tumor in MRI is simulated by synthesizing texture images from real MR images. The proposed method is able to generate synthetic ground truth and synthesized MR images with tumor and edema that exhibit comparable segmentation challenges to real tumor MRI. Such image data sets will find use in segmentation reliability studies, comparison and validation of different segmentation methods, training and teaching, or even in evaluating standards for tumor size like the RECIST criteria (response evaluation criteria in solid tumors).