Multi-atlas label fusion by using supervised local weighting for brain image segmentation
Journal Title: TecnoLógicas - Year 2017, Vol 20, Issue 39
Abstract
The automatic segmentation of interest structures is devoted to the morphological analysis of brain magnetic resonance imaging volumes. It demands significant efforts due to its complicated shapes and since it lacks contrast between tissues and inter-subject anatomical variability. One aspect that reduces the accuracy of the multi-atlas-based segmentation is the label fusion assumption of one-to-one correspondences between targets and atlas voxels. To improve the performance of brain image segmentation, label fusion approaches include spatial and intensity information by using voxel-wise weighted voting strategies. Although the weights are assessed for a predefined atlas set, they are not very efficient for labeling intricate structures since most tissue shapes are not uniformly distributed in the images. This paper proposes a methodology of voxel-wise feature extraction based on the linear combination of patch intensities. As far as we are concerned, this is the first attempt to locally learn the features by maximizing the centered kernel alignment function. Our methodology aims to build discriminative representations, deal with complex structures, and reduce the image artifacts. The result is an enhanced patch-based segmentation of brain images. For validation, the proposed brain image segmentation approach is compared against Bayesian-based and patch-wise label fusion on three different brain image datasets. In terms of the determined Dice similarity index, our proposal shows the highest segmentation accuracy (90.3% on average); it presents sufficient artifact robustness, and provides suitable repeatability of the segmentation results
Authors and Affiliations
D. Cárdenas-Peña, E. Fernández, José M. Ferrández-Vicente, G. Castellanos-Domínguez
Keywords
Related Articles
- EP ID EP348409
- DOI 10.22430/22565337.724
- Views 103
- Downloads 0
Prostasomas: search of biomarkers for the early detection of prostate cancer
Prostate cancer is the second most diagnosed disease in men worldwide, with an increasing mortality rate in recent years. Currently, there are two early detection tests, the measurement of blood levels of prostate-specif...
Secondary voltage regulation based on average voltage control
Thispaper compares a conventional Secondary Voltage Regulation (SVR) scheme based on pilot nodes witha proposed SVR thattakes into account average voltages of control zones. Voltage control significance for the...
An adaptive algorithm for overcurrent protections on the case study IEEE9
A proper coordination of electrical protections is fundamental in electric power systems, with the aim of avoiding unexpected disconnections. These disconnections can produce problems in the operation of the power system...
Quasi-switched inverter using space vector pulse width modulation with triangular comparison for photovoltaic applications
This workanalyzes a prototype of a quasi-switched boost inverter (qSBI) feeding an isolated resistive load from a DC source. The use of spatial vector pulse width modulation (SPWM) with triangula...
Influence of the pulse wave in the stratification of high density particles in a JIG device
A study of particle motion subjected to four different pulsation profiles on a pulsated fluidized bed jig concentrator was carried out. The profiles used in the simulation were – sinusoidal, triangle, sawtooth-backward a...