Automatic Detection and Segmentation of Brain Tumor Using Random Forest Approach

Kapás, Zoltán; Lefkovits, László; Szilágyi, László

doi:10.1007/978-3-319-45656-0_25

Cited by 20 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Segmentations are shown in Figure 10. Classification results can be further improved by using preprocessed data instead of raw data, and by means of postprocessing to remove the outlying voxels and inlying holes as demonstrated in Reference [16]. Lastly, the performance of the RF classifier trained on all tumor cores of the 20 real high-grade glioma volumes using the 3D Slicer extension were compared to similar studies performed on the BraTS dataset.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Tool for Supervised Segmentation Using 3D Slicer

Chalupa

Mikulka

2018

Symmetry

View full text Add to dashboard Cite

The rather impressive extension library of medical image-processing platform 3D Slicer lacks a wide range of machine-learning toolboxes. The authors have developed such a toolbox that incorporates commonly used machine-learning libraries. The extension uses a simple graphical user interface that allows the user to preprocess data, train a classifier, and use that classifier in common medical image-classification tasks, such as tumor staging or various anatomical segmentations without a deeper knowledge of the inner workings of the classifiers. A series of experiments were carried out to showcase the capabilities of the extension and quantify the symmetry between the physical characteristics of pathological tissues and the parameters of a classifying model. These experiments also include an analysis of the impact of training vector size and feature selection on the sensitivity and specificity of all included classifiers. The results indicate that training vector size can be minimized for all classifiers. Using the data from the Brain Tumor Segmentation Challenge, Random Forest appears to have the widest range of parameters that produce sufficiently accurate segmentations, while optimal Support Vector Machines' training parameters are concentrated in a narrow feature space.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Approach DICE This paper RF 0.43 Geremia [21] Spatial decision forests with intrinsic hierarchy 0.32 Kapás [16] RF 0.58 Bauer [22] Integrated hierarchical RF 0.48 Zikic [23] Context-sensitive features with a decision tree ensemble 0.47 Festa [24] RF using neighborhood and local context features 0.50…”

Section: Papermentioning

confidence: 99%

A Novel Tool for Supervised Segmentation Using 3D Slicer

Chalupa

Mikulka

2018

Symmetry

View full text Add to dashboard Cite

show abstract

“…This technique classifies the brain MRI as normal (no tumor or benign) or abnormal (malign) in an efficient way. Zolt´an Kap´as et al [11] presents preliminary results (detection and localization of tumors in MRI volumes) obtained using the random forest technique. Keeping three goals in mind, that is, Histogram normalization, feature computation and missing data, pre-processing has been carried out.…”

Section: Decision Treementioning

confidence: 99%

Survey on Brain Tumor Identification

Malathy¹,

Kundu²,

Sadhukhan³

2018

IJET

View full text Add to dashboard Cite

Brain tumors are caused by the growth of abnormal cells inside the Brain. Brain tumor can be classified as Benign (non cancerous) and malignant(cancerous). Malignant brain tumors usually grow rapidly when compared to benign tumors, and aggressively spread and affect the surrounding tissues. Detection of tumor in brain can turn out to be cumbersome, owing to the complex organization of the Brain. The cost of making an error in Identifying a Malignant Tumor from a Benign Tumor is too high. At a time, when cases of Brain Tumors are growing, mostly among people of age between 65 and 79, but not just confined to that age bracket, we can take advantage of the advancement in the field of technology and accurately identify tumors and help save lives.

show abstract

“…The unsupervised model, such as fuzzy c-means [ 19 ], k-means [ 20 ], and principal component analysis (PCA) [ 21 , 22 ], do not need a training procedure. The supervised model, such as random forest (RF) [ 23 ], markov random field [ 24 ], support vector machine (SVM) [ 25 ], extreme learning machine [ 26 ] and deep learning [ 7 ], need to first train a classification or segmentation model, then feed a new acquired MRI into the trained network to obtain a segmented contour of the brain image. A late example is by Yang et al where PCA feature extraction is conducted, they are able to diagnose breast tumors by using SVM with differential evolution-based parameter tuning [ 22 ].…”

Section: Introductionmentioning

confidence: 99%

Brain tumor segmentation based on region of interest-aided localization and segmentation U-Net

Liu

Song

2022

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Since magnetic resonance imaging (MRI) has superior soft tissue contrast, contouring (brain) tumor accurately by MRI images is essential in medical image processing. Segmenting tumor accurately is immensely challenging, since tumor and normal tissues are often inextricably intertwined in the brain. It is also extremely time consuming manually. Late deep learning techniques start to show reasonable success in brain tumor segmentation automatically. The purpose of this study is to develop a new region-of-interest-aided (ROI-aided) deep learning technique for automatic brain tumor MRI segmentation. The method consists of two major steps. Step one is to use a 2D network with U-Net architecture to localize the tumor ROI, which is to reduce the impact of normal tissue’s disturbance. Then a 3D U-Net is performed in step 2 for tumor segmentation within identified ROI. The proposed method is validated on MICCAI BraTS 2015 Challenge with 220 high Gliomas grade (HGG) and 54 low Gliomas grade (LGG) patients’ data. The Dice similarity coefficient and the Hausdorff distance between the manual tumor contour and that segmented by the proposed method are 0.876 ±0.068 and 3.594±1.347 mm, respectively. These numbers are indications that our proposed method is an effective ROI-aided deep learning strategy for brain MRI tumor segmentation, and a valid and useful tool in medical image processing.

show abstract

Automatic Detection and Segmentation of Brain Tumor Using Random Forest Approach

Cited by 20 publications

References 15 publications

A Novel Tool for Supervised Segmentation Using 3D Slicer

A Novel Tool for Supervised Segmentation Using 3D Slicer

Survey on Brain Tumor Identification

Brain tumor segmentation based on region of interest-aided localization and segmentation U-Net

Contact Info

Product

Resources

About