Conventional and Deep Learning Methods for Skull Stripping in Brain MRI

Rehman, Hafiz Zia Ur; Hwang, Hyunho; Lee, Sungon

doi:10.3390/app10051773

Cited by 41 publications

(34 citation statements)

References 129 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Skull removal has lately acquired popularity as a result of escalated demand for a fast, reliable, and consistent algorithm for different variations of brain datasets. For neuroimaging diagnostic systems, precise skull removal is critical since the results could lead to an unnoticed inaccuracy in the upcoming processing [22]. It refers to a process of eliminating the skull from the image to escalate segmentation accuracy, and lessen the number of distracting pixels that could interfere with tumour segmentation.…”

Section: Skull Removalmentioning

confidence: 99%

Substantial adaptive artificial bee colony algorithm implementation for glioblastoma detection

Ibrahim

Samah²,

Hamzah³

et al. 2023

IJ-AI

View full text Add to dashboard Cite

<p><span lang="EN-US">Glioblastoma multiforme (GBM) is a high-grade brain tumor that is extremely dangerous and aggressive. Due to its rapid development rate, high-grade cancers require early detection and treatment, and early detection may possibly increase the chances of survival. The current practice of GBM detection is performed by a radiologist; due to the enormous number of cases, it is nevertheless tedious, intrusive, and error-prone. Thus, this study attempted a substantial adaptive artificial bee colony (a-ABC) algorithm implementation in providing a non-invasive approach for GBM detection. The basic statistical intensity-based analysis of minimum (minGL), maximum (maxGL), and mean (meanGL) of grey level data was employed to investigate the GBM's feature properties. The a-ABC's performance for adaptive GBM detection identification was evaluated using T1-weighted (T1), T2-weighted (T2), fluid attenuated inversion recovery (FLAIR), and T1-contrast (T1C) which are four different magnetic resonance imaging (MRI) imaging sequences. Hundred and twenty MRI of GBM images were assessed in total, with 30 images per imaging sequence. The overall mean of GBM detection accuracy percentage was 93.67%, implying that the proposed a-ABC algorithm is capable of detecting GBM brain tumors. Other feature extraction strategies, on the other hand, may be added in the future to enhancee the performance of feature extraction. </span></p>

show abstract

Section: Skull Removalmentioning

confidence: 99%

Substantial adaptive artificial bee colony algorithm implementation for glioblastoma detection

Ibrahim

Samah²,

Hamzah³

et al. 2023

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Developing a model with a high accuracy is a challenging task. Recent version of CNN models [8][9][10] have hardly focused on hyper parameters whereas we do so; the collection [2] of features that are locally available to the CNN are also a critical issue; moreover bluntly increasing the dilation rate may add to the failure of feature collections due to the sparseness of the kernel, affecting small object detection [11]. High dilation rates may affect small object detection.…”

Section: Introductionmentioning

confidence: 99%

Incremental Dilations Using CNN for Brain Tumor Classification

2020

View full text Add to dashboard Cite

Brain tumor classification is a challenging task in the field of medical image processing.Technology has now enabled medical doctors to have additional aid for diagnosis. We aim toclassify brain tumors using MRI images, which were collected from anonymous patients andartificial brain simulators . In this article, we carry out a comparative study between SimpleArtificial Neural Networks with dropout, Basic Convolutional Neural Networks (CNN), and DilatedConvolutional Neural Networks. The experimental results shed light on the high classificationperformance (accuracy 97%) of Dilated CNN. On the other hand, Dilated CNN suffers from thegridding phenomenon. An incremental, even number dilation rate takes advantage of the reducedcomputational overhead and also overcomes the adverse effects of gridding. Comparative analysisbetween different combinations of dilation rates for the different convolution layers, help validatethe results. The computational overhead in terms of efficiency for training the model to reach anacceptable threshold accuracy of 90% is another parameter to compare the model performance.

show abstract

“…Most automated methods for brain extraction can be classified in categories, such as mathematical morphology-based, intensity-based, deformable surface-based, atlas-based, and hybrid methods [ 2 , 7 , 8 ]. Machine learning techniques, including neural networks are also widely used for skull stripping [ 9 , 10 ]. We review different skull stripping techniques before describing GUBS.…”

Section: Introductionmentioning

confidence: 99%

GUBS: Graph-Based Unsupervised Brain Segmentation in MRI Images

et al. 2022

View full text Add to dashboard Cite

Brain segmentation in magnetic resonance imaging (MRI) images is the process of isolating the brain from non-brain tissues to simplify the further analysis, such as detecting pathology or calculating volumes. This paper proposes a Graph-based Unsupervised Brain Segmentation (GUBS) that processes 3D MRI images and segments them into brain, non-brain tissues, and backgrounds. GUBS first constructs an adjacency graph from a preprocessed MRI image, weights it by the difference between voxel intensities, and computes its minimum spanning tree (MST). It then uses domain knowledge about the different regions of MRIs to sample representative points from the brain, non-brain, and background regions of the MRI image. The adjacency graph nodes corresponding to sampled points in each region are identified and used as the terminal nodes for paths connecting the regions in the MST. GUBS then computes a subgraph of the MST by first removing the longest edge of the path connecting the terminal nodes in the brain and other regions, followed by removing the longest edge of the path connecting non-brain and background regions. This process results in three labeled, connected components, whose labels are used to segment the brain, non-brain tissues, and the background. GUBS was tested by segmenting 3D T1 weighted MRI images from three publicly available data sets. GUBS shows comparable results to the state-of-the-art methods in terms of performance. However, many competing methods rely on having labeled data available for training. Labeling is a time-intensive and costly process, and a big advantage of GUBS is that it does not require labels.

show abstract

Conventional and Deep Learning Methods for Skull Stripping in Brain MRI

Cited by 41 publications

References 129 publications

Substantial adaptive artificial bee colony algorithm implementation for glioblastoma detection

Substantial adaptive artificial bee colony algorithm implementation for glioblastoma detection

Incremental Dilations Using CNN for Brain Tumor Classification

GUBS: Graph-Based Unsupervised Brain Segmentation in MRI Images

Contact Info

Product

Resources

About