ArticlePublisher preview available

Deep learning neural networks for medical image segmentation of brain tumours for diagnosis: a recent review and taxonomy

Authors:
Sindhu Devunooru
Sindhu Devunooru
Sindhu Devunooru
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Abeer Alsadoon
Abeer Alsadoon
Abeer Alsadoon
  • This person is not on ResearchGate, or hasn't claimed this research yet.
P. W. C. Chandana
P. W. C. Chandana
P. W. C. Chandana
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Azam Beg at United Arab Emirates University
Azam Beg
Read publisher preview
Download citation
To read the full-text of this research, you can request a copy directly from the authors.

Abstract and Figures

Brain tumour identification with traditional magnetic resonance imaging (MRI) tends to be time-consuming and in most cases, reading of the resulting images by human agents is prone to error, making it desirable to use automated image segmentation. This is a multi-step process involving: (a) collecting data in the form of raw processed or raw images, (b) removing bias by using pre-processing, (c) processing the image and locating the brain tumour, and (d) showing the tumour affected areas on a computer screen or projector. Several systems have been proposed for medical image segmentation but have not been evaluated in the field. This may be due to ongoing issues of image clarity, grey and white matter present in a scan image, lack of knowledge of the end user and constraints arising from MRI imaging systems. This makes it imperative to develop a comprehensive technique for the accurate diagnosis of brain tumors in MRI images. In this paper, we introduce a taxonomy consisting of ‘Data, Image segmentation processing, and View’ (DIV) which are the major components required to develop a high-end system for brain tumour diagnosis based on deep learning neural networks. The DIV taxonomy is evaluated based on system completeness and acceptance. The utility of the DIV taxonomy is demonstrated by classifying 30 state-of-the-art publications in the domain of medFical image segmentation systems based on deep neural networks. The results demonstrate that few components of medical image segmentation systems have been validated although several have been evaluated by identifying role and efficiency of the components in this domain.
Diagram depicted the process flow of VoxResNet
Diagram depicted the process flow of VoxResNet
… 
The above figure shows the three factors of our Image Segmentation taxonomy (i.e., data, image segmentation processing and view), as well as the classes and subclasses (solid-line arrows) that represent them. The relationships between them (dashed-line arrows) are also shown. Numbers in the figure specify the cardinality of the relationships. The image segmentation processing is associated with both visually processed data and view classes. The view is the component that is interacted with by the user and therefore, the component which is most limited by constraints
The above figure shows the three factors of our Image Segmentation taxonomy (i.e., data, image segmentation processing and view), as well as the classes and subclasses (solid-line arrows) that represent them. The relationships between them (dashed-line arrows) are also shown. Numbers in the figure specify the cardinality of the relationships. The image segmentation processing is associated with both visually processed data and view classes. The view is the component that is interacted with by the user and therefore, the component which is most limited by constraints
… 
The diagnostic scenario describes the type of diagnosis and the number of diagnostic steps that are executed to provide the diagnosis, whereby each step describes the action, its associated precision, and completion time. Each diagnosis step is associated with visually processed data and, therefore, indirectly with the view
The diagnostic scenario describes the type of diagnosis and the number of diagnostic steps that are executed to provide the diagnosis, whereby each step describes the action, its associated precision, and completion time. Each diagnosis step is associated with visually processed data and, therefore, indirectly with the view
… 
Data classes, their most relevant attributes and an instances are presented here. The different types of data are patient-specific and visually processed. The solid arrow represents inheritance, and the rounded squares represent examples of how the image segmentation processing is associated with both visually processed data and view classes
Data classes, their most relevant attributes and an instances are presented here. The different types of data are patient-specific and visually processed. The solid arrow represents inheritance, and the rounded squares represent examples of how the image segmentation processing is associated with both visually processed data and view classes
… 
The main classes of the image segmentation processing, their subclasses, their most relevant attributes, and instances are depicted.The arrow heads represent inheritance, and dotted lines represent aggregation (i.e., “has a” relationships)
+4
The main classes of the image segmentation processing, their subclasses, their most relevant attributes, and instances are depicted.The arrow heads represent inheritance, and dotted lines represent aggregation (i.e., “has a” relationships)
… 
Figures - available from: Journal of Ambient Intelligence and Humanized Computing
This content is subject to copyright. Terms and conditions apply.
A preview of this full-text is provided by Springer Nature.
Learn more
Content available from Journal of Ambient Intelligence and Humanized Computing
This content is subject to copyright. Terms and conditions apply.
Vol.:(0123456789)
1 3
Journal of Ambient Intelligence and Humanized Computing (2021) 12:455–483
https://doi.org/10.1007/s12652-020-01998-w
ORIGINAL RESEARCH
Deep learning neural networks formedical image segmentation
ofbrain tumours fordiagnosis: arecent review andtaxonomy
SindhuDevunooru1· AbeerAlsadoon1· P.W.C.Chandana1· AzamBeg2
Received: 28 April 2019 / Accepted: 17 April 2020 / Published online: 6 May 2020
© Springer-Verlag GmbH Germany, par t of Springer Nature 2020
Abstract
Brain tumour identification with traditional magnetic resonance imaging (MRI) tends to be time-consuming and in most cases,
reading of the resulting images by human agents is prone to error, making it desirable to use automated image segmentation.
This is a multi-step process involving: (a) collecting data in the form of raw processed or raw images, (b) removing bias by
using pre-processing, (c) processing the image and locating the brain tumour, and (d) showing the tumour affected areas
on a computer screen or projector. Several systems have been proposed for medical image segmentation but have not been
evaluated in the field. This may be due to ongoing issues of image clarity, grey and white matter present in a scan image,
lack of knowledge of the end user and constraints arising from MRI imaging systems. This makes it imperative to develop a
comprehensive technique for the accurate diagnosis of brain tumors in MRI images. In this paper, we introduce a taxonomy
consisting of ‘Data, Image segmentation processing, and View’ (DIV) which are the major components required to develop
a high-end system for brain tumour diagnosis based on deep learning neural networks. The DIV taxonomy is evaluated based
on system completeness and acceptance. The utility of the DIV taxonomy is demonstrated by classifying 30 state-of-the-art
publications in the domain of medFical image segmentation systems based on deep neural networks. The results demonstrate
that few components of medical image segmentation systems have been validated although several have been evaluated by
identifying role and efficiency of the components in this domain.
Keywords Taxonomy· Medical image segmentation· Magnetic resonance imaging (MRI)· Brain tumour· Deep neural
networks (DNN)· Diagnosis· Image contrast· Image clustering· Re-clustering· Image pixels· Tumour boundaries
Abbreviations
MRI Magnetic resonance imaging
MCFM Modified fuzzy C-means
CLE Confocal laser endomicroscopy
CNN Convolutional neural networks
DCNN Deep conventional neural network
ACM Active contour models
CRFs Conditional random fields
FCNN Fully convolutional neural network
LHNPSO Low-discrepancy sequence initialized par-
ticle swarm optimization algorithm with
high-order nonlinear time-varying inertia
weight
KFECSB Kernelized fuzzy entropy clustering with
spatial information and bias correction
RF Classifier Random forests classifier
1 Introduction
Brain image segmentation processing is the subject of a sig-
nificant body of research that aims to develop systems for
accurate cancer diagnosis, capable of differentiating tumour
affected from healthy tissue. This is achieved by image pre-
processing, clustering, and post-segmentation processes to
enhance contrast in the raw or processed Magnetic Reso-
nance Imaging MRI data, using clustering algorithms for
automatic segmentation of images into different parts and
fine-tuning the output data to eliminate bias. This process
enhances accuracy of MRI images making tumour-affected
regions easily identifiable (Chen etal. 2017a, b) through
greater clarity of images, thus eliminating the issues faced
in manual segmentation processes.
* Abeer Alsadoon
aalsadoon@studygroup.com
1 School ofComputing andMathematics, Charles Sturt
University, Sydney Campus, Sydney, Australia
2 College ofInformation Technology, United Arab Emirates
University, AlAin, UAE
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
... These models consist of multiple hidden layers and perform automated learning on the dataset. 24 Amin et al. 25 proposed long short-term memory for automated brain tumor categorization, utilizing N4ITK and Gaussian filters for quality enhancement. CNN has been widely used for brain tumor categorization, outperforming other methods like SVM, Fuzzy C-Mean, and Random Forest. ...
... [26][27][28][29] Sajid et al. 30 presented a model for segmentation by combining dropout regularization, batch normalization, and a two-phase training approach to address overfitting and data imbalance. Devunooru et al. 24 used CNN for brain malignancy detection, achieving high accuracy on a tumor dataset without region-based segmentation. Özyurt et al. 4 proposed NS-CNN, a hybrid technique combining neutrosophy and CNNs for distinguishing benign and malignant tumor regions, achieving an average success rate of 95.62% with SVM classification. ...
Systematic study and design of multimodal MRI image augmentation for brain tumor detection with loss aware exchange and residual networks
Article
Full-text available
  • Nov 2023
  • INT J IMAG SYST TECH
One of the most difficult problems that develop when brain cells start to grow out of control is a brain tumor, which is regarded as the most lethal disease of the century. Finding and identifying malignant brain magnetic resonance imaging (MRI) images is the major challenge before therapy. Researchers have been putting a lot of effort into creating the best method for more accurate real‐world medical image recognition. For manual categorization, it is quite time‐consuming to segment large quantities of MRI data. To mitigate these issues, this paper suggests the information exchange gateway‐based residual UNet (IEGResUNet) model, which uses the ResUNet model as a base model. Additionally, including principal component analysis (PCA) data augmentation will increase the model's efficiency while also enhancing its speed. The IEGResUNet model shows an ablation investigation on three Brats datasets, with and without PCA augmentation. The results demonstrate that IEGResUNet will improve segmentation effectiveness and can also manage the imbalance in input data when PCA data augmentation models are included. The dice score on BraTS 2019 for whole tumor, region of core tumor, and region of enhancing tumor were 0.9083, 0.883, and 0.8106 respectively. Also, on BraTS 2020, the dice score for WT, CT, and ET 0.9083, 0.883, and 0.8106 was respectively. Similarly, on BraTS 2021, the dice score for WT, CT, and ET was 0.8737, 0.8866, and 0.7963 respectively. Comparing against baseline models, the IEGResUNet scored well in terms of dice score and intersection over union.
View
... Brain image segmentation is a subject addressed by a vast number of researchers who seek to develop systems for accurate cancer diagnosis able to differentiate cancer cells from healthy ones [105][106][107][108][109][110][111]. A problem that such approaches can mitigate is that human verification of magnetic resonance imaging to locate tumors can be prone to errors. ...
... A problem that such approaches can mitigate is that human verification of magnetic resonance imaging to locate tumors can be prone to errors. In a recent study, Devunooru et al. [105] provided a taxonomy system for the key components needed to develop an innovative brain tumor diagnosis system based on DL models. The taxonomy system, named data image segmentation processing and viewing (DIV), comprised research that had been developed since 2016. ...
Developments in Image Processing Using Deep Learning and Reinforcement Learning
Article
Full-text available
  • Sep 2023
The growth in the volume of data generated, consumed, and stored, which is estimated to exceed 180 zettabytes in 2025, represents a major challenge both for organizations and for society in general. In addition to being larger, datasets are increasingly complex, bringing new theoretical and computational challenges. Alongside this evolution, data science tools have exploded in popularity over the past two decades due to their myriad of applications when dealing with complex data, their high accuracy, flexible customization, and excellent adaptability. When it comes to images, data analysis presents additional challenges because as the quality of an image increases, which is desirable, so does the volume of data to be processed. Although classic machine learning (ML) techniques are still widely used in different research fields and industries, there has been great interest from the scientific community in the development of new artificial intelligence (AI) techniques. The resurgence of neural networks has boosted remarkable advances in areas such as the understanding and processing of images. In this study, we conducted a comprehensive survey regarding advances in AI design and the optimization solutions proposed to deal with image processing challenges. Despite the good results that have been achieved, there are still many challenges to face in this field of study. In this work, we discuss the main and more recent improvements, applications, and developments when targeting image processing applications, and we propose future research directions in this field of constant and fast evolution.
View
... The task of segmenting the affected tumor region is critical for cancer diagnosis. For tumor segmentation and classification, a variety of semi-automatic and automatic methods and methodologies, and approaches are used [2]. Image textures, local histograms, etc are all aspects of MRIsthat have been used in brain tumor segmentation analysis and classification. ...
Brain Tumor Classification using Conventional Machine Learning Algorithms
Article
Full-text available
  • Mar 2021
Brain tumors and associated nervous system cancers are one of the largest reasons behind the death of human beings. Timely identification of a tumor can help save a person's life. The detection of brain tumors is time-consuming and also needs a specialized radiologist for lesion detection. Machine Learning techniques can assist in the detection of brain tumors. These algorithms are critical in correctly predicting the presence of tumors in human beings. In this context, this paper uses the K-means algorithm to segment the brain MRI and then extracts features from these segmented MRIs for the purpose of detecting the brain tumor. The features are extracted by using the Gray Level Co-occurrence Matrix (GLCM). The features extracted are fed into the classifiers Support Vector Machine (SVM) and Decision Tree (DT) to segregate the tumorous and non-tumorous MRIs. Our proposed approach performs better than state-of-the-art methods in terms of classification accuracy.
View
... Medical image segmentation is an active research area that plays a vital role in diagnosis [7], treatment planning [38], and disease monitoring [31]. U-net [35] has been widely used for various medical image segmentation tasks. ...
AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder
Article
Full-text available
  • Nov 2023
The recently introduced Segment Anything Model (SAM) combines a clever architecture and large quantities of training data to obtain remarkable image segmentation capabilities. However, it fails to reproduce such results for Out-Of-Distribution (OOD) domains such as medical images. Moreover, while SAM is conditioned on either a mask or a set of points, it may be desirable to have a fully automatic solution. In this work, we replace SAM's conditioning with an encoder that operates on the same input image. By adding this encoder and without further fine-tuning SAM, we obtain state-of-the-art results on multiple medical images and video benchmarks. This new encoder is trained via gradients provided by a frozen SAM. For inspecting the knowledge within it, and providing a lightweight segmentation solution, we also learn to decode it into a mask by a shallow deconvolution network.
View
... Recently, a new deep learning model based on the cascade regression method was also used for brain tumor segmentation [36]. The methods reported in [33] and [11] provided a comprehensive review of existing machine learning based approaches used to segment brain images for detecting brain tumors. Haque et al [12] expanded on the deep learning methods for automatic segmentation of images in this field. ...
Segmentation of brain MRI using moth-flame optimization with modified cross entropy based fitness function
Article
Full-text available
  • Feb 2024
  • MULTIMED TOOLS APPL
The work presents a newly designed penalty function to be added with an existing Cross Entropy based fitness function [3] for optimal selection of multi-level thresholds for image segmentation. The extended fitness function so designed is tested here for Brain magnetic resonance (MR) image segmentation using nature-inspired meta-heuristics such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA) and Moth-flame Optimization (MFO), and MFO is finally selected. The proposed method excels in Brain MR image segmentation when tested on WBA database and BrainWeb MR image database with other nature-inspired meta-heuritic based methods. It outperformed the other methods in terms of the three performance metrics Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM) and Feature Similarity Index (FSIM). The best results shown by the proposed method on WBA database in terms of these metrics - PSNR, SSIM and FSIM - are 29.77, 0.927 and 0.899 respectively. On BrainWeb database, the proposed method yields 26.91, 0.864 and 0.892 for the three respective metrics.
View
... Xie et al. [39] surveyed DL models that improved their segmentation performance by utilizing domain knowledge of a medical image modality provided by medical experts and Zhou et al. [40] studied methods that used multi-modality fusion techniques. Some other studies focused on models performing segmentation on particular organ(s) or for the detection of a particular disease; for example, Devunooru et al. [41] and Wadhwa et al. [42] reviewed works on brain tumor segmentation, Fu et al. [43] studied models focusing on multi-organ segmentation, and Shi et al. [44] included works on the task of segmentation of lung infection for Covid-19 detection. ...
Advances in Deep Learning Models for Resolving Medical Image Segmentation Data Scarcity Problem: A Topical Review
Article
  • Dec 2023
Deep learning (DL) methods have recently become state-of-the-art in most automated medical image segmentation tasks. Some of the biggest challenges in this field are related to datasets. This paper aims to review the recent developments in deep learning architectures and approaches that aim to resolve dataset-related challenges faced in DL-based medical image segmentation. We have studied architectural developments in deep learning models and their recent applications in medical image segmentation tasks. Popular U-Net-based models are tested for segmentation performance comparison on a Coronavirus disease 2019 (Covid-19) lung infection Computed Tomography segmentation dataset. The comparison results prove the effectiveness of the original U-Net architecture, even in present-day medical image segmentation tasks. To overcome major dataset-related challenges such as labeled data scarcity, high annotation time and cost, distribution shifts, low-quality of images, and generalizability issues; we have studied recent developments in deep learning approaches like active learning, data augmentation, domain adaptation, and self- and semi-supervised learning, that aim to provide innovative solutions for those challenges. With rapid developments in the field, approaches like data augmentation, domain adaptation, and semi-supervised learning have become some of the hot areas of research, aiming for more efficient use of datasets, better segmentation prediction, and model generalizability.
View
... In a human biological system, the brain tumor is considered a harmful disease category [1]. Hence, the early tumor diagnosis framework is a major concern in recovering human lives with proper treatment procedures [2]. ...
The Effective Quantitative Analysis for Brain Tumor Diagnosis Using an Efficient Deep Learning Algorithm
Article
Full-text available
  • Aug 2023
In the medical field, imaging analysis is the hottest topic. It has attracted many researchers to accurately analyses the disease severity and predict the outcome. However, if the trained images are more complex, the noise pruning results have decreased, which has tended to gain less prediction exactness score. So, a novel Chimp-based Boosting Multilayer Perceptron (CbBMP) prediction framework has been built in this present study. Moreover, the objective of this study is brain tumor prediction and severity analysis from the MRI brain images. The boosting function is employed to earn the most acceptable error pruning outcome. Henceforth, the feature analysis and the tumor prediction process were executed accurately with the help chimp solution function. The planned framework is tested in the MATLAB environment, and the prediction improvement score is analyzed by performing a comparative analysis. A novel CbBMP model has recorded the finest tumor forecasting rate.
View
... The non-automatic analysis of the many sampled slides of the tissue by the doctors is an intensive and expensive process. Thus, the computerized diagnosis systems that are being converted into influential tools are used by doctors to discover and diagnose tumors [6,7]. The most common method for brain tumor medication is surgery. ...
View
Brain tumor image segmentation using model average ensembling of deep networks
Article
  • Jun 2024
In the biomedical field, identification of brain tumors along with their location, regions of spreading, and speed of extension are of utmost importance to decide the treatment for Brain Tumors. Automated segmentation plays a major role in detection because manual extraction of the brain tumor sub-regions from MRI volume is monotonous, error-prone, and intricate. Deep learning significantly contributed to outperforming these issues since it is aware of their complexity. Therefore, a technique for the automated segmentation of MRI brain pictures has been developed using model average ensembling of deep networks such 3D CNN and U-Net architectures. 3D CNN and U-Net architecture have made remarkable progress on the task of segmentation of brain tumors. Due to their reliability, ensembling of these models have been opted to have a model with greater reliability. The novelty of this paper is to build a robust segmentation technique by model average ensembling of 3D CNN and U-Net models for abnormality identification by improving the image quality using preprocessing methods. The model includes the testing set BraTS-19 as its input dataset. After performing a lot of experiments, it has been observed that the obtained dice scores by the proposed model for TC (Tumor Core), WT (Whole Tumor), and ET (Enhancing Tumor) are 0.9603, 0.9201, and 0.9237 respectively. The obtained dice scores from the ensembling technique are better than existing techniques. The demonstrated results show the supremacy of the proposed method with an overall accuracy greater than 96%.
View
Beyond Accuracy: An Empirical Study on Unit Testing in Open-source Deep Learning Projects
Article
  • Dec 2023
Deep Learning (DL) models have rapidly advanced, focusing on achieving high performance through testing model accuracy and robustness. However, it is unclear whether DL projects, as software systems, are tested thoroughly or functionally correct when there is a need to treat and test them like other software systems. Therefore, we empirically study the unit tests in open-source DL projects, analyzing 9,129 projects from GitHub. We find that: 1) unit tested DL projects have positive correlation with the open-source project metrics and have a higher acceptance rate of pull requests, 2) 68% of the sampled DL projects are not unit tested at all, 3) the layer and utilities (utils) of DL models have the most unit tests. Based on these findings and previous research outcomes, we built a mapping taxonomy between unit tests and faults in DL projects. We discuss the implications of our findings for developers and researchers and highlight the need for unit testing in open-source DL projects to ensure their reliability and stability. The study contributes to this community by raising awareness of the importance of unit testing in DL projects and encouraging further research in this area.
View
White matter network topology relates to cognitive flexibility and cumulative neurological risk in adult survivors of pediatric brain tumors
Article
Full-text available
  • Aug 2018
Adult survivors of pediatric brain tumors exhibit deficits in executive functioning. Given that brain tumors and medical treatments for brain tumors result in disruptions to white matter, a network analysis was used to explore the topological properties of white matter networks. This study used diffusion tensor imaging and deterministic tractography in 38 adult survivors of pediatric brain tumors (mean age in years = 23.11 (SD = 4.96), 54% female, mean years post diagnosis = 14.09 (SD = 6.19)) and 38 healthy peers matched by age, gender, handedness, and socioeconomic status. Nodes were defined using the Automated Anatomical Labeling (AAL) parcellation scheme, and edges were defined as the mean fractional anisotropy of streamlines that connected each node pair. Global efficiency and average clustering coefficient were reduced in survivors compared to healthy peers with preferential impact to hub regions. Global efficiency mediated differences in cognitive flexibility between survivors and healthy peers, as well as the relationship between cumulative neurological risk and cognitive flexibility. These results suggest that adult survivors of pediatric brain tumors, on average one and a half decades post brain tumor diagnosis and treatment, exhibit altered white matter topology in the form of suboptimal integration and segregation of large scale networks, and that disrupted topology may underlie executive functioning impairments. Network based studies provided important topographic insights on network organization in long-term survivors of pediatric brain tumor.
View
A New Deformable Model Based on Fractional Wright Energy Function for Tumor Segmentation of Volumetric Brain MRI Scans
Article
Full-text available
  • May 2018
  • COMPUT METH PROG BIO
Background and objectives: The MRI brain tumors segmentation is challenging due to variations in terms of size, shape, location and features' intensity of the tumor. Active contour has been applied in MRI scan image segmentation due to its ability to produce regions with boundaries. The main difficulty that encounters the active contour segmentation is the boundary tracking which is controlled by minimization of energy function for segmentation. Hence, this study proposes a novel fractional Wright function (FWF) as a minimization of energy technique to improve the performance of active contour without edge method. Method: In this study, we implement FWF as an energy minimization function to replace the standard gradient-descent method as minimization function in Chan-Vese segmentation technique. The proposed FWF is used to find the boundaries of an object by controlling the inside and outside values of the contour. In this study, the objective evaluation is used to distinguish the differences between the processed segmented images and ground truth using a set of statistical parameters; true positive, true negative, false positive, and false negative. Results: The FWF as a minimization of energy was successfully implemented on BRATS 2013 image dataset. The achieved overall average sensitivity score of the brain tumors segmentation was 94.8 ± 4.7%. Conclusions: The results demonstrate that the proposed FWF method minimized the energy function more than the gradient-decent method that was used in the original three-dimensional active contour without edge (3DACWE) method.
View
View
Implementing cooperative bacterial foraging optimisation algorithm based resources and VM management in IaaS cloud
Article
  • Jan 2019
In cloud computing, Infrastructure as a Service (IaaS) placed a crucial role for providing the enormous services to the user based on the demands. The infrastructure provides the components such as server, networking hardware, storage, visualisation for making the system power effective. Even though the IaaS provides various resources, it has still issues such as cost expensive, responsible for backup, VM management is fully depends on the customer, makespan for resource provisioning in scientific workflow and no control of VM location. Among the various issues, cost and makespan is one of the major issues which lead to reduce the entire resource allocation process. So, in this paper introduces the cooperative bacterial foraging optimisation algorithm (CBFOA) for optimising the resource allocation activities while user requesting various scientific application in the infrastructure resources in cloud. Initially, the BFO method allocates the resources according to the bacterial function such as chemotaxis, swarming, reproduction, elimination and dispersal process which examines the user request according to the animal food searching process. During the resource searching process, the search space has been determined with the help of hybrid search space optimisation algorithm which handle the decision depending on the search space. This scientific workflow application process is worked continuously for allocating the resources and manages the virtual resources in IaaS in cloud environment successfully. In addition to this, user requested workload has been traced by using cybershake workload trace, which is used to examine the resource provisioning activities and trace the status of the particular task with effective manner. Then the excellence of the system has been implemented with the help of cloudsim tool and the efficiency is examined in terms of experimental results and discussions.
View
A Multi-phase Semi-automatic Approach for Multisequence Brain Tumor Image Segmentation
Article
  • Jun 2018
  • EXPERT SYST APPL
Accurate Magnetic Resonance Imaging (MRI) image segmentation is a clinically challenging task. More often than not, one type of MRI image is insufficient to provide the complete information about a pathological tissue or a visual object from the image. As a result, radiology experts often combine multisequence images of a patient to verify the location, extension, prognosis and diagnosis of an object. There are mainly two challenges in medical image segmentation. One is ambiguous boundary that appears between an object and its neighboring region, and the other is intensity inhomogeneity that appears within a region. Thus, this paper focuses on how to effectively segment multisequence medical images despite these two main challenges. This paper proposes a multi-phase approach that integrates both data and domain knowledge into multisequence MR image segmentation. This study divides the segmentation approach into three phases, which are (i) information modeling, (ii), information fusion, and (iii) visual object extraction. In the first phase, random walks algorithm is modified and used to model the information of an image. Because of the ambiguous boundary and intensity inhomogeneity that appear within an image, extra terms related to homogeneity- and object feature-based components are added into the weighting function of random walks algorithm. In the second phase, weighted averaging method is used to fuse information from the image sequences. Both data information of an image as well as user knowledge are integrated to determine the weights of each sequence for fusion. In the final phase, the concept of information theoretic rough sets (ITRS) is utilized to address the issue of ambiguous boundary that may appear between the visual object and its background for object extraction. The proposed approach is tested on MICCAI brain tumor dataset to extract brain tumor and its performance is compared with other established methods. The experiments show promising results, with an average DICE accuracy of 0.7 and 0.63 for high- and low-grade tumor, respectively. As compared to the other fully- and semi-automatic methods that require training and careful initialization processes, the proposed approach is able to extract the brain tumor with prior knowledge about the image.
View
Bayesian HCS-based multi-SVNN: A classification approach for brain tumor segmentation and classification using Bayesian fuzzy clustering
Article
  • Jun 2018
Brain tumor segmentation and classification is the interesting area for differentiating the tumerous and the non-tumerous cells in the brain and to classify the tumerous cells for identifying its level. The conventional methods lack the automatic classification and they consumed huge time and are ineffective in decision-making. To overcome the challenges faced by the conventional methods, this paper proposes the automatic method of classification using the Harmony-Crow Search (HCS) Optimization algorithm to train the multi-SVNN classifier. The brain tumor segmentation is performed using the Bayesian fuzzy clustering approach, whereas the tumor classification is done using the proposed HCS Optimization algorithm-based multi-SVNN classifier. The proposed method of classification determines the level of the brain tumor using the features of the segments generated based on Bayesian fuzzy clustering. The robust features are obtained using the information theoretic measures, scattering transform, and wavelet transform. The experimentation performed using the BRATS database conveys proves the effectiveness of the proposed method and the proposed HCS-based tumor segmentation and classification achieves the classification accuracy of 0.93 and outperforms the existing segmentation methods. © 2018 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences
View
Machine learning based brain tumour segmentation on limited data using local texture and abnormality
Article
  • May 2018
  • COMPUT BIOL MED
Brain tumour segmentation in medical images is a very challenging task due to the large variety in tumour shape, position, appearance, scanning modalities and scanning parameters. Most existing segmentation algorithms use information from four different MRI-sequences, but since this is often not available, there is need for a method able to delineate the different tumour tissues based on a minimal amount of data. We present a novel approach using a Random Forests model combining voxelwise texture and abnormality features on a contrast-enhanced T1 and FLAIR MRI. We transform the two scans into 275 feature maps. A random forest model next calculates the probability to belong to 4 tumour classes or 5 normal classes. Afterwards, a dedicated voxel clustering algorithm provides the final tumour segmentation. We trained our method on the BraTS 2013 database and validated it on the larger BraTS 2017 dataset. We achieve median Dice scores of 40.9% (low-grade glioma) and 75.0% (high-grade glioma) to delineate the active tumour, and 68.4%/80.1% for the total abnormal region including edema. Our fully automated brain tumour segmentation algorithm is able to delineate contrast enhancing tissue and oedema with high accuracy based only on post-contrast T1-weighted and FLAIR MRI, whereas for non-enhancing tumour tissue and necrosis only moderate results are obtained. This makes the method especially suitable for high-grade glioma.
View
Hierarchical Brain Tumour Segmentation using Extremely Randomized Trees
Article
  • May 2018
  • PATTERN RECOGN
Gliomas are the most common and aggressive primary brain tumours, with a short-life expectancy in their highest grade. Magnetic Resonance Imaging is the most common imaging technique to assess brain tumours. However, performing manual segmentation is a difficult and tedious task, mainly due to the large amount of information to be analysed. Therefore, there is a need for automatic and robust segmentation methods. We propose an automatic hierarchical brain tumour segmentation pipeline using Extremely Randomized Trees with appearance- and context-based features. Some of these features are computed over non-linear transformations of the Magnetic Resonance Imaging images. Our proposal was evaluated using the publicly available 2013 Brain Tumour Segmentation Challenge database, BRATS 2013. In the Challenge dataset, the proposed approach obtained a Dice Similarity Coefficient of 0.85, 0.79, and 0.75 for the complete, core, and enhancing regions, respectively.
View
Big data analysis for brain tumor detection: Deep convolutional neural networks
Article
  • May 2018
  • FUTURE GENER COMP SY
Brain tumor detection is an active area of research in brain image processing. In this work, a methodology is proposed to segment and classify the brain tumor using magnetic resonance images (MRI). Deep Neural Networks (DNN) based architecture is employed for tumor segmentation. In the proposed model, 07 layers are used for classification that consist of 03 convolutional, 03 ReLU and a softmax layer. First the input MR image is divided into multiple patches and then the center pixel value of each patch is supplied to the DNN. DNN assign labels according to center pixels and perform segmentation. Extensive experiments are performed using eight large scale benchmark datasets including BRATS 2012 (image dataset and synthetic dataset), 2013 (image dataset and synthetic dataset), 2014, 2015 and ISLES (Ischemic stroke lesion segmentation) 2015 and 2017. The results are validated on accuracy (ACC), sensitivity (SE), specificity (SP), Dice Similarity Coefficient (DSC), precision, false positive rate (FPR), true positive rate (TPR) and Jaccard similarity index (JSI) respectively.
View
A DCT-based local and non-local fuzzy C-means algorithm for segmentation of brain magnetic resonance images
Article
  • Apr 2018
  • APPL SOFT COMPUT
Accurate segmentation of brain tissues from magnetic resonance images (MRI) is a crucial requirement for the quantitative analysis of brain images. Due to the presence of noise in brain MRI, many segmentation methods suffer from low segmentation accuracy. The existing methods deal the noise sensitivity of the MRI segmentation in the spatial domain by combining the local and nonlocal information in the fuzzy C-means (FCM) method. These methods are prone to loosing image details while reducing the effect of noise. In this paper, we propose a transform domain approach using the discrete cosine transform (DCT). Working in the transform domain has an advantage over the spatial domain in which the intensity of the image is decorrelated and the image information is represented by the independent frequency bands. The low and middle level frequency bands represent the holistic and fine structures of the image and the high frequency band mostly carries the noise information. In the proposed method, called the DCT-based local and nonlocal FCM (DCT-LNLFCM), the distance function of the FCM is represented as the sum of the local and nonlocal distances which themselves are the weighted values of the Euclidean distance used in the FCM. Since the weights are computed in the transform domain, a good tradeoff is achieved between noise insensitivity and preservation of the image details. This results in the high accuracy of the MRI segmentation. Detailed experimental results are presented and comparison with the state-of-the-art techniques is performed to demonstrate the high performance of the proposed approach. The proposed method provides an improvement in the average segmentation accuracy from 1.10% to 2.03% on simulated images and 1.52% to 1.91% on real images.
View