Edge detection in MRI brain tumor images based on fuzzy C-means clustering

Зотин, А. Г.; Simonov, Konstantin; Kurako, Mikhail; Hamad, Yousif; Кириллова, С. В.

doi:10.1016/j.procs.2018.08.069

Cited by 53 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on this typical type of brain tumor, we observe that the false negative and false positive regions for the best testing case that are incorrectly distinguished almost always occur at the junction boundaries of different levels of tumors and nontumors. This deficiency can hopefully be reinforced by boundary image processing 46 , boundary segmentation 47 , and edge detection 48 , 49 methods. On the other hand, for the worst testing case (no.…”

Section: Resultsmentioning

confidence: 99%

3D brain tumor segmentation using a two-stage optimal mass transport algorithm

Lin

Juang

Yueh

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Optimal mass transport (OMT) theory, the goal of which is to move any irregular 3D object (i.e., the brain) without causing significant distortion, is used to preprocess brain tumor datasets for the first time in this paper. The first stage of a two-stage OMT (TSOMT) procedure transforms the brain into a unit solid ball. The second stage transforms the unit ball into a cube, as it is easier to apply a 3D convolutional neural network to rectangular coordinates. Small variations in the local mass-measure stretch ratio among all the brain tumor datasets confirm the robustness of the transform. Additionally, the distortion is kept at a minimum with a reasonable transport cost. The original $$240 \times 240 \times 155 \times 4$$ 240 × 240 × 155 × 4 dataset is thus reduced to a cube of $$128 \times 128 \times 128 \times 4$$ 128 × 128 × 128 × 4 , which is a 76.6% reduction in the total number of voxels, without losing much detail. Three typical U-Nets are trained separately to predict the whole tumor (WT), tumor core (TC), and enhanced tumor (ET) from the cube. An impressive training accuracy of 0.9822 in the WT cube is achieved at 400 epochs. An inverse TSOMT method is applied to the predicted cube to obtain the brain results. The conversion loss from the TSOMT method to the inverse TSOMT method is found to be less than one percent. For training, good Dice scores (0.9781 for the WT, 0.9637 for the TC, and 0.9305 for the ET) can be obtained. Significant improvements in brain tumor detection and the segmentation accuracy are achieved. For testing, postprocessing (rotation) is added to the TSOMT, U-Net prediction, and inverse TSOMT methods for an accuracy improvement of one to two percent. It takes 200 seconds to complete the whole segmentation process on each new brain tumor dataset.

show abstract

Section: Resultsmentioning

confidence: 99%

3D brain tumor segmentation using a two-stage optimal mass transport algorithm

Lin

Juang

Yueh

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…P.Shanthakumar et al2015 [18] -propose a method that transparently compare brain abnormalities from normal brain tissue. tumor de-segmentation results are calculated based on similarity indexed, the overlap fraction and positive predicted value whose obtained values are 0.817%, 0.817%,0.812%.. Munmun Saha et al,2018 [20] This paper reviewed and summarised some existing method of segmentation for tumor detection in brain using MRI images Alexander Zotin et al, 2018 [21] The paper present brain tumor edge detection using MRI images which are based on FCM clustering. in biomedical image.…”

Section: Nilesh Bhaskarraomentioning

confidence: 99%

Detection of Brain Tumor using Image Processing Techniques

Kaur¹,

Singh²

2019

IJEAT

View full text Add to dashboard Cite

Image processing in biomedical field is being increasingly used for the detection and diagnosis of various abnormalities in the body parts. The detection of brain tumours using image processing on MRI images is one such field where better results are obtained as comparative to CT-scan and x-ray. Prior detection of the brain tumour is desirable and possible with the help of machine learning and image processing techniques. These techniques detect even a small abnormality in the human brain following a four-stage process which includes pre-processing, segmentation, feature extraction and optimization. Different parameters such as accuracy, PSNR, MSE are calculated to find out the efficiency of process and to compare it with other methods. This paper reviews about various different approaches which are used to detect the brain tumor using image processing techniques.

show abstract

“…The authors have used morphological operation along with thresholding, for segmentation [6].Different edge detection operators like Sobel, Canny and Prewitts have been along with clustering algorithms for segmentation. Sobel method along close contour algorithm has been proposed and the authors claim superior results over conventional methods [7].Canny edge detectors along with fuzzy c-means clustering has been used in [8] and achieved around 10 to 15% more accurate results for some images. An adaptive region growing method based on gradients and variances with anisotropic filter for pre-processing has been proposed and obtained good results [9] Hybrid techniques has been proposed by many researchers for better segmentation results [10] , [11].…”

Section: Related Workmentioning

confidence: 99%

Brain Tumor Segmentation in MRI Images using Convolution Neural Networks

Rani P*,

Harsha,

Singh

et al. 2019

IJRTE

View full text Add to dashboard Cite

Medical image processing is an important task in current scenario as more and more humans are diagnosed with various medical issues. Brain tumor (BT) is one of the problems that is increasing at a rapid rate and its early detection is important in increasing the survival rate of humans. Detection of tumor from Magnetic Resonance Image (MRI) of brain is very difficult when done manually and also time consuming. Further the tumors assume different shapes and may be present in any portion of the brain. Hence identification of the tumor poses an important task in the lives of human and it is necessary to identify its exact position in the brain and the affected regions. The proposed algorithm makes use of deep learning concepts for automatic segmentation of the tumor from the MRI brain images. The algorithm is implemented using MATLAB and an accuracy of 99.1% is achieved.

show abstract

Edge detection in MRI brain tumor images based on fuzzy C-means clustering

Cited by 53 publications

References 7 publications

3D brain tumor segmentation using a two-stage optimal mass transport algorithm

3D brain tumor segmentation using a two-stage optimal mass transport algorithm

Detection of Brain Tumor using Image Processing Techniques

Brain Tumor Segmentation in MRI Images using Convolution Neural Networks

Contact Info

Product

Resources

About