Brain Tumor Segmentation Using Support Vector Machines

Ayachi, Raouia; Amor, Nahla Ben

doi:10.1007/978-3-642-02906-6_63

Cited by 59 publications

(38 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The majority of these methods can be broadly categorized into discriminative [12]–[15], and generative approaches such as [16]–[24]. Generative approaches explicitly define a model for the joint probability distribution of voxel labels (target variables) and intensities (observed variables).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GLISTR: Glioma Image Segmentation and Registration

Gooya¹,

Pohl

Bilello

et al. 2012

IEEE Trans. Med. Imaging

199

181

View full text Add to dashboard Cite

We present a generative approach for simultaneously registering a probabilistic atlas of a healthy population to brain magnetic resonance (MR) scans showing glioma and segmenting the scans into tumor as well as healthy tissue labels. The proposed method is based on the expectation maximization (EM) algorithm that incorporates a glioma growth model for atlas seeding, a process which modifies the original atlas into one with tumor and edema adapted to best match a given set of patient’s images. The modified atlas is registered into the patient space and utilized for estimating the posterior probabilities of various tissue labels. EM iteratively refines the estimates of the posterior probabilities of tissue labels, the deformation field and the tumor growth model parameters. Hence, in addition to segmentation, the proposed method results in atlas registration and a low-dimensional description of the patient scans through estimation of tumor model parameters. We validate the method by automatically segmenting 10 MR scans and comparing the results to those produced by clinical experts and two state-of-the-art methods. The resulting segmentations of tumor and edema outperform the results of the reference methods, and achieve a similar accuracy from a second human rater. We additionally apply the method to 122 patients scans and report the estimated tumor model parameters and their relations with segmentation and registration results. Based on the results from this patient population, we construct a statistical atlas of the glioma by inverting the estimated deformation fields to warp the tumor segmentations of patients scans into a common space.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Support vector machine (SVM) classifiers [13]–[15] comprise a subgroup of discriminative methods which their label inferring models are SVM scoring functions. These functions are trained by maximizing the margin in the training and minimizing expected error in the testing data.…”

Section: Introductionmentioning

confidence: 99%

GLISTR: Glioma Image Segmentation and Registration

Gooya¹,

Pohl

Bilello

et al. 2012

IEEE Trans. Med. Imaging

199

181

View full text Add to dashboard Cite

show abstract

“…Image processing chain consists of preprocessing, segmentation, feature extraction and classification [9]. First the dental x-ray images are preprocessed based on image enhancement technique namely contrast stretching.…”

Section: Image Processing Chainmentioning

confidence: 99%

Computer Aided Classification using Support Vector Machines in Detecting Cysts of Jaws

K¹,

Jatti²,

P³

et al. 2017

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…In a discriminative scenario, a decision function is directly learned from manually annotated training images to characterize the difference between cancerous and normal tissues. A broad spectrum of algorithms have been used for learning the decision function (see for example [1,3,18,27,34,39]). In recent years, convolutional neural networks [1,18,20,21,34] have become an extremely popular choice as the base learner, achieving high rankings in BRATS competitions.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of Gliomas in Pre-operative and Post-operative Multimodal Magnetic Resonance Imaging Volumes Based on a Hybrid Generative-Discriminative Framework

Zeng

Bakas

Sotiras

et al. 2016

Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries

View full text Add to dashboard Cite

We present an approach for segmenting both low- and high-grade gliomas in multimodal magnetic resonance imaging volumes. The proposed framework is an extension of our previous work [6,7], with an additional component for segmenting post-operative scans. The proposed approach is based on a hybrid generative-discriminative model. Firstly, a generative model based on a joint segmentation-registration framework is used to segment the brain scans into cancerous and healthy tissues. Secondly, a gradient boosting classification scheme is used to refine tumor segmentation based on information from multiple patients. We evaluated our approach in 218 cases during the training phase of the BRAin Tumor Segmentation (BRATS) 2016 challenge and report promising results. During the testing phase, the proposed approach was ranked among the top performing methods, after being additionally evaluated in 191 unseen cases.

show abstract

Brain Tumor Segmentation Using Support Vector Machines

Cited by 59 publications

References 13 publications

GLISTR: Glioma Image Segmentation and Registration

GLISTR: Glioma Image Segmentation and Registration

Computer Aided Classification using Support Vector Machines in Detecting Cysts of Jaws

Segmentation of Gliomas in Pre-operative and Post-operative Multimodal Magnetic Resonance Imaging Volumes Based on a Hybrid Generative-Discriminative Framework

Contact Info

Product

Resources

About