Validation Techniques for Quantitative Brain Tumors Measurements

Salman, Yasser M.; Assal, M.A.; Badawi, Ahmed M.; Alian, S.M.; El-Bayome, M.El.

doi:10.1109/iembs.2005.1616129

Cited by 19 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers have shown the RG based area remains fulfilled method than NR based approaches with regard to segmentation of the MR images, especially in similar tissues and regions [36].…”

Section: Region-based (Rb) Methodsmentioning

confidence: 99%

A Review of Image Denoising and Segmentation Methods Based on Medical Images

Kollem¹,

Reddy²,

Rao³

2019

IJMLC

View full text Add to dashboard Cite

Image denoising and segmentation are required to use in digital image processing. For researchers' point of view, still, these two methods are challenging task in medical images. At present, image denoising and segmentation take part in real-world applications such as computer graphic, computer vision, satellite, and medical fields. These two methods are analyzed by using different images but mainly concentration on medical images such as computed tomography, single photon emission computed tomography, magnetic resonance imaging, positron emission tomography. Medical images can break into noise, major research has created solutions to this complication, various techniques are being proposed. Image segmentation is a widespread and active area not only for medical imaging but also for computer vision and satellite imaging. The foremost plan of image segmentation remains to segment images into different components, which are used to give more information about the medical image. Here is an overview of the different methods after a brief introduction. These methods are classified as the basis for the techniques used. Index Terms-Image denoising, Image segmentation, performance parameters, derivative based image denoising, clustering methods. I. INTRODUCTION Digital image processing requires a computer to work with images, so it is fit aimed at image investigation, pattern recognition, together with human reflection. By means of computer knowledge, digital image processing has several applications over different industries such as face recognition, medical imaging, computer vision, remote sensing, and medical sciences. Medical images such as computed tomography, single photon emission computed tomography, magnetic resonance imaging, positron emission tomography contains rich information, both anatomy, and functionality that can be used to diagnose, plan, and investigate operations. These images can be either a two-dimensional image or a three-dimensional image, which is solved in terms of both time and non-time. A large amount of information on these pictures can be evaluated with simple visualization, but for quantitative measurements, the object must be divided into segments. Possible quantitative measurements such as organs size, heart infarct size, muscle weakness, tumor size, as well as tumor Manuscript

show abstract

Section: Region-based (Rb) Methodsmentioning

confidence: 99%

A Review of Image Denoising and Segmentation Methods Based on Medical Images

Kollem¹,

Reddy²,

Rao³

2019

IJMLC

View full text Add to dashboard Cite

show abstract

“…Ho et al proposed a region competition method which modulates the propagation term with a signed local statistical force to reach a stable state (Ho et al, 2002 ). Salman et al examined the seeded region growing and active contour to be compared against experts' manual segmentations (Salman et al, 2012 ). Sato et al proposed a Sobel gradient magnitude-based region growing algorithm which solves the partial volume effect problem (Sato et al, 2000 ).…”

Section: Related Workmentioning

confidence: 99%

Supervised Brain Tumor Segmentation Based on Gradient and Context-Sensitive Features

et al. 2019

View full text Add to dashboard Cite

Gliomas have the highest mortality rate and prevalence among the primary brain tumors. In this study, we proposed a supervised brain tumor segmentation method which detects diverse tumoral structures of both high grade gliomas and low grade gliomas in magnetic resonance imaging (MRI) images based on two types of features, the gradient features and the context-sensitive features. Two-dimensional gradient and three-dimensional gradient information was fully utilized to capture the gradient change. Furthermore, we proposed a circular context-sensitive feature which captures context information effectively. These features, totally 62, were compressed and optimized based on an mRMR algorithm, and random forest was used to classify voxels based on the compact feature set. To overcome the class-imbalanced problem of MRI data, our model was trained on a class-balanced region of interest dataset. We evaluated the proposed method based on the 2015 Brain Tumor Segmentation Challenge database, and the experimental results show a competitive performance.

show abstract

“…We improve our previous work [10] PC based software package implemented using three programming development environment, as VTK [18], ITK [20] and Visual C++, to segment, visualize and calculate the tumor volume at different instants of tumor growing or shrinking. Figure 2 shows the result of tumor segmentation using T-RG and MRGM.…”

Section: Pc Based Packagementioning

confidence: 99%

“…Segmentation of ROI in volumetric medical images is still a challenging problem, and solutions usually have been based on either model-based deformation of templates or intensity thresholding such as region growing method [6,7]. Recent studies prove that the region growing is an effective approach and less computation intensive for image segmentation especially for the homogenous regions [8,9,10,7,11]. The primary disadvantage of region growing method is the partial volume effect [12,13].…”

Section: Introductionmentioning

confidence: 99%

Modified technique for volumetric brain tumor measurements

Salman¹

2009

JBiSE

View full text Add to dashboard Cite

Quantitative measurements of tumor response rate in three dimensions (3D) become more re-alistic with the use of advanced technology im-aging during therapy, especially when the tumor morphological changes remain subtle, irregular and difficult to assess by clinical examination. These quantitative measurements depend strongly on the accuracy of the segmentations methods used. Improvements on such methods yield to increase the accuracy of the segmentation process. Recently, the essential modification in the Traditional Region Growing (T-RG) method has been developed and a “Modified Region Growing Method” (MRGM) has been presented and gives more accurate boundary detection and holes filling after segmentation. In this pa-per, the new automatic calculation of the volu-metric size of brain tumor has been imple-mented based on Modified Region Growing Method. A comparative study and statistical analysis performed in this work show that the modified method gives more accurate and better performance for 3D volume measurements. The method was tested by 7 fully investigated pa-tients of different tumor type and shape, and better accurate results were reported using MRGM

show abstract

Validation Techniques for Quantitative Brain Tumors Measurements

Cited by 19 publications

References 13 publications

A Review of Image Denoising and Segmentation Methods Based on Medical Images

A Review of Image Denoising and Segmentation Methods Based on Medical Images

Supervised Brain Tumor Segmentation Based on Gradient and Context-Sensitive Features

Modified technique for volumetric brain tumor measurements

Contact Info

Product

Resources

About