Level-set segmentation of brain tumors using a threshold-based speed function

Taheri, Sima; Ong, Sim‐Heng; Chong, Vincent

doi:10.1016/j.imavis.2009.04.005

Cited by 103 publications

(35 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Threshold Level Set, Taheri applied a threshold level set method for brain tumour segmentation in 3D which does not depend on density function estimation by using a global threshold for the speed function [29]. This semi-automatic model requires a user's input to initialize the threshold value for the level set based on information from a region inside a tumour.…”

Section: Snake-based Level Set Methodsmentioning

confidence: 99%

Comparison of level set models in image segmentation

Rahmat¹,

Harris-Birtill

2018

IET Image Processing

View full text Add to dashboard Cite

Image segmentation is one of the most important tasks in modern imaging applications, which leads to shape reconstruction, volume estimation, object detection and classification. One of the most popular active segmentation models are level set models which are used extensively as an important category of modern image segmentation technique with many different available models to tackle different image applications. Level sets are designed to overcome the topology problems during the evolution of curves in their process of segmentation while the previous algorithms cannot deal with this problem effectively. As a result there is often considerable investigation into the performance of several level set models for a given segmentation problem. It would therefore be helpful to know the characteristics of a range of level set models before applying to a given segmentation problem. In this paper we review a range of level set models and their application to image segmentation work and explain in detail their properties for practical use. IntroductionImage segmentation is the process of partitioning the image into meaningful regions. It is one of the most important tasks in modern imaging for shape reconstruction, volume estimation, object detection and classification. Many different algorithms have been proposed to solve image segmentation problems. In some applications such as medical image segmentation, highly precise models are needed where strong assumptions and anatomical prior are often imposed on the expected segmentation results. The methods based on statistical theory methods can fail in the presence of noise as the artificial parameters should be considered as well, while a lot of physical phenomenon can be described by partial differential equations (PDEs). Those based on PDE, began with the Snake technique introduced by Kass in 1987 [1]. The snake model is based on minimization of an energy term to halt the growth of evolving contours at edges or boundaries. It locks into edges and lines by taking advantage of image forces. Another popular image segmentation method is the level set, introduced in 1988 by Osher-Sethian [2] to overcome the shortcomings of the Snake method such as its topological problem as well as accurate prior knowledge for their initialization.Since level set models are independent of prior knowledge, they are very robust segmentation models when there is no ground truth available. Level set methods are used extensively and have many different applications. As a result there is often considerable investigation into the performance of several level set methods for a given problem. It would therefore be helpful to know the characteristics of a range of level set methods before applying any to a given segmentation problem. Several review papers on level set segmentation are available but each is focused on one area or specific aspect of imaging applications. Some of these topics are: Region-based algorithms As image segmentation is a growing area of research many different robust s...

show abstract

Section: Snake-based Level Set Methodsmentioning

confidence: 99%

Comparison of level set models in image segmentation

Rahmat¹,

Harris-Birtill

2018

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…10) by an adaptive scheme which is better than the static one. This idea was already proposed by Taheri et al Taheri et al (2010).…”

Section: Threshold Updating Parametermentioning

confidence: 95%

“…However, this method only segments the enhanced section of tumors in contrast enhanced T1-weighted image. A more recent approach was presented in Taheri et al (2010), combining the threshold-based method and level sets. This method is similar to the method of Chen & Metaxas (2003) but it works in 3D and uses a threshold method to construct the speed function in level sets.…”

mentioning

confidence: 99%

Deformable Model-Based Segmentation of Brain Tumor from MR Images

Bourouis¹,

Hamrouni²

2011

Diagnostic Techniques and Surgical Management of Brain Tumors

View full text Add to dashboard Cite

We are IntechOpen, the first native scientific publisher of Open Access books 12.2%108,000 1.7 M TOP 1% 151 3,350Segmentation of brain tumors is an important task for treatment planning and therapy evaluation. This task could also lead to new applications, including data compression, robust registration, and effective content based image retrieval in large medical databases. Accurate delineation of tumor can also be helpful for general modeling of pathological brains and the construction of pathological brain atlases Toga et al. (2001). Nevertheless, precise delineation of brain Tumor in MRI is a challenging problem that depends on many factors. Indeed, there is a large class of tumor types which vary greatly in size and position, have a variety of shape and appearance properties, have intensities overlapping with normal brain tissue, may deform and defect the surrounding structures giving an abnormal geometry also for healthy tissue. Moreover, MR images segmentation widely depends on the specific application and image modality. These images contain sometimes various amounts of noise and/or artifacts due to patient's motion and soft tissue boundaries are sometimes not well defined. Traditionally manual brain tumors segmentation -usually performed by marking the tumor regions slice-by-slice by human expert -is time-consuming (hence impractical for processing large amounts of data), non-reproducible, difficult, and highly subjective. On the other hand, fully automatic and robust segmentation is highly required for clinical settings because it reduces significantly the computing time and generates satisfactory segmentation results. The existence of several MR acquisition protocols provides different information on the brain. Each image usually highlights a particular region of the tumor. In visualizing brain tumors, a second T1-weighted image is often acquired after the injection of a 'contrast agent'. These 'contrast agent' usually contain an element whose composition causes a decrease in the T1 time of nearby tissue (gadolinium is one example) Brown & Semeka (2003). The presence of this type of 'enhancing' area can indicate the presence of a tumor. Figure 1 illustrates an example of T1-weighted image before and after the injection of a contrast agent. Conventionally, it is difficult to segment a tumor by a simple technique like thresholding or classic edge-detection. These methods may not allow differentiation between non-enhancing tumor and normal tissue due to overlapping intensity distributions of healthy tissue with tumor and surrounding edema. Also, they are unable to exploit all information provided by MRI. Therefore, advanced image analysis techniques are needed to solve the problem. Various promising works have studied the tumor segmentation, offering a diversity of methods and evaluation criteria. In particular, pattern classification techniques refer to a

show abstract

“…It is an effective strategy as long as image indicates very much dense zones and the dark levels are bunched around far off qualities with least cover. It likewise has been utilized to give an underlying estimation or a preceding more perplexing division strategies (procedures in view of snakes, level-sets or dynamic shapes require an underlying division, that can be physically done or acquired by means of thresholding [5,6]), to give veils of regions of interest [7], or, then again even as a method to distinguish movement in reconnaissance situations [8,9]. Thresholding is additionally broadly utilized as a part of the medical imaging field where images are created by a few tissues, represented by the gray levels [10].…”

Section: Introductionmentioning

confidence: 99%

Implementation of Fuzzy Thresholding for Segmentation of Images

Kumari¹,

Enireddy²

2017

IJCA

View full text Add to dashboard Cite

Segmentation is a process of dividing an image into multiple regions making it easier for the analysis. It is also an important step in Image processing. It also has number of applications which includes Medical field to analyze a disease, scientific fields including, engineering and technology, face recognition and object. Many algorithms and techniques have been developed for the image segmentation. To remove distinctive areas from a picture an immediate and straight forward method is using thresholding. It looks for a worldwide esteem that boosts the partition between yield classes. Noisy or uneven illuminated images pose a challenge for segmentation. The utilization of solitary hard limit esteem is absolutely the wellspring of imperative division mistakes in numerous situations like boisterous images or uneven illumination. In this paper a multiregion thresholding technique is displayed to overcome the normal downsides of thresholding strategies when images are debased with artifacts and commotion. Pixels from the images are related to various yield centroids by means of fuzzy membership function, evading any underlying hard choice. To make this strategy robust to noise and artifacts it utilizes spatial data through a local aggregation step where the participation level of every pixel is adjusted by neighborhood data that considers the enrollments of the encompassing pixels. The results are then compared with the existing techniques and results obtained are satisfactory.

show abstract

Level-set segmentation of brain tumors using a threshold-based speed function

Cited by 103 publications

References 22 publications

Comparison of level set models in image segmentation

Comparison of level set models in image segmentation

Deformable Model-Based Segmentation of Brain Tumor from MR Images

Implementation of Fuzzy Thresholding for Segmentation of Images

Contact Info

Product

Resources

About