One can find in the literature numerous techniques to reduce noise in Magnetic Resonance Images (MRI). This paper critically reviews modern de-noising algorithms (Gaussian filter, anisotropic diffusion, wavelet, and non-local mean) in terms of their efficiency, statistical assumptions, and their ability to improve brain tumor segmentation results. We will show that although different techniques do reduce the noise, many generate artifacts that are incompatible with precise brain tumor segmentation. We also show that the non-local means algorithm is the best de-noising technique for brain tumor segmentation.
One of the most frequent reasons for instituting mechanical ventilation is to decrease patient's work of breathing. Many attempts have been made to increase the effectiveness of the evaluation of the respiratory pattern with the analysis of the respiratory signals. This work proposes a method for the study of the differences in respiratory pattern variability in patients on weaning trials. The proposed method is based on a support vector machine using 35 features extracted from the respiratory flow signal. In this paper, a group of 146 patients with mechanical ventilation were studied: group S of 79 patients with successful weaning trials and group F of 67 patients that failed to maintain spontaneous breathing and were reconnected. Applying a feature selection procedure based on the use of the support vector machine with a leave-one-out cross-validation, it was obtained 86.67% of well classified patients on group S and 73.34% on group F, using only 8 of the 35 features. Therefore, support vector machine can be a classification method of the respiratory pattern variability useful in the study of patients on weaning trials.
Automated brain tumor segmenters typically run a "skull-stripping" pre-process to extract the brain from the 3D image, before segmenting the area of interest within the extracted volume. We demonstrate that an effective existing segmenter can be improved by replacing its skull-stripper component with one that instead uses a registration-based approach. In particular, we compare our automated brain segmentation system with the original system as well as three other approaches that differ only by using a different skull-stripper-BET, HWA, and ROBEX: (1) Over scans of 120 patients with brain tumors, our system's segmentation accuracy (Dice score with respect to expert segmentation) is 8.6% (resp. 2.7%) better than the original system on gross tumor volumes (resp. edema); (2) Over 103 scans of controls, the new system found 92.9% (resp. 57.8%) fewer false positives on T1C (resp. FLAIR) volumes. (The other three methods were significantly worse on both tasks). Finally, the new registration-based approach is over 15% faster than the original, requiring on average only 178 CPU seconds per volume.
Brain atlas to patient registration in the presence of tumors is a challenging task because its presence cause brain structure deformations and introduce large intensity variation between the affected areas. This large dissimilarity affects the results of traditional registration methods based on intensity or shape similarities. In order to overcome these problems, we propose a novel method that brings closer the atlas and the patient's image by simulating the mechanical behavior of brain deformation under a tumor pressure. The proposed method use a mesh-free total Lagrangian Explicit Dynamic algorithm for the simulation of atlas deformation and a data driven model of the tumor using multi-modal MRI segmentation. Experimental results look structurally very similar to the patient's image and outperform two of the top ranking algorithms.
This paper introduces an automatic brain tumor segmentation method (ABTS) for segmenting multiple components of brain tumor using four magnetic resonance image modalities. ABTS's four stages involve automatic histogram multi-thresholding and morphological operations including geodesic dilation. Our empirical results, on 16 real tumors, show that ABTS works very effectively, achieving a Dice accuracy compared to expert segmentation of 81% in segmenting edema and 85% in segmenting gross tumor volume (GTV).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with đź’™ for researchers
Part of the Research Solutions Family.