.png){kind=icon}
.png){kind=icon}
Return
Brain tumour segmentation using memory based learning method
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-019-7673-6.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A brain tumour is a mass of tissue formed by abnormal growth of cells within the brain. Automated detection of brain tumour becomes essential for introduction of robotics based treatment process. The proposed method focuses on enhancing the speed of brain tumour segmentation in 2D sliced images without compromising the detection accuracy. The method uses memory based learning of a particular database along with two fold of histogram stretching for faster and accurate identification of tumour portion in a 2D sliced image.The second histogram stretching is used when the segmentation criterion gets failed after the first histogram stretching. It is necessary to reduce the computational time of accurate tumour segmentation in 2D sliced images obtained from a 3D Magnetic Resonance (MR) image so that faster detection of 3D tumour portion becomes possible without deteriorating the accuracy of detection. 2D tumour segmentation accuracy and computational time of the system is found to be 100% and 0.179 s respectively in the performance analysis. The proposed method reduces the computational time to a large extend by eliminating the conventional iterative process of computation.
Keywords:
Brain tumour
Segmentation
Magnetic Resonance image
Histogram stretching
Iterative process
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W