Development of image-processing software for automatic segmentation of brain tumors in MR images

Abstract

Most of the commercially available software for brain tumor segmentation have limited functionality and frequently lack the careful validation that is required for clinical studies. We have developed an image-analysis software package called ‘Prometheus,’ which performs neural system–based segmentation operations on MR images using pre-trained information. The software also has the capability to improve its segmentation performance by using the training module of the neural system. The aim of this article is to present the design and modules of this software. The segmentation module of Prometheus can be used primarily for image analysis in MR images. Prometheus was validated against manual segmentation by a radiologist and its mean sensitivity and specificity was found to be 85.71±4.89% and 93.2±2.87%, respectively. Similarly, the mean segmentation accuracy and mean correspondence ratio was found to be 92.35±3.37% and 0.78±0.046, respectively.

MRI Segmentation of the Human Brain: Challenges, Methods, and Applications

“…They combined minimum error global thresholding and a spatial-feature-based FCM clustering to segment 3D MRI in a “slice-by-slice” manner. In the work of Vijayakumar and Gharpure [ 117 ], a hybrid MRI segmentation method, based on artificial neural networks (ANN), is proposed for segmenting tumor lesions, edema, cysts, necrosis, and normal tissue in T2 and FLAIR MRI. More recently, Ortiz et al [ 119 ] suggested an improved brain MRI segmentation method using self-organizing maps (a particular case of ANN) and entropy-gradient clustering.…”

Supervised Brain Tumor Segmentation Based on Gradient and Context-Sensitive Features

“…The threshold-based techniques, region-based techniques, and pixel classification techniques are commonly used for two-dimensional image segmentation (Vijayakumar and Gharpure, 2011 ). Model-based techniques and voxel classification methods are usually used for three-dimensional image segmentation.…”

A comprehensive review: Segmentation of MRI images-brain tumor

“…Some of the hybrid methods are: Combination of multi‐region with multi‐reference framework to obtain lower standard deviations and higher tissue overlapping rates (Phillips et al, ). Combination of EM segmentation and active contours with binary mathematical morphology is used to segment adult brain using 2D MRI for segmenting different brain tissues (Kapur et al, ). Combining thresholding, active contours with T1 and T2 weighted MRI the volume of newborn brain can be segmented (Despotovic et al, ). Support Vector Machines are combined with the conditional random field to achieve low computational times of segmentation with multispectral datasets among different patients (Bauer et al, a, ). Based on ANN hybrid segmentation of T2 and FLAIR MRI is proposed (Vijayakumar and Chandrashekhar Gharpure, ) to segment normal tissues, edema, cysts, and tumor lesions. Combination of kernel feature selection with SVM is used achieve to low computational time and better results in testing T1W and T2W MRI (Zhang et al, ). Combining K‐means with FCM is used to obtain better reproducibility and accurate results (Gupta and Shringirishi, ). Self‐organizing maps are combined with entropy‐gradient clustering method to improve brain segmentation in MRI images (Ortiz et al, ). Integration of modified Particle Swarm Optimization with fuzzy entropy based segmentation provides the maximum entropy while segmenting tumors in brain with less computation time (Remamany et al, ). …”