Vertebrae segmentation techniques for spinal medical images using matlab


ABSTRACT:   

The bone structures in medical images have high contrast but the vertebrae identification is considered a challenging task due to many difficulties like the unclear boundaries of the vertebrae, the abnormal spine curves and complex structure of the vertebra. In order to achieve an accurate, efficient and automated spine segmentation and detection from medical images, there are several techniques. This paper analyzes and review the different vertebrae segmentation techniques. The spine segmentation task divides into three main stages: initial spine skeleton detection, vertebrae segmentation of the spine while the third stage is designed to enhance the results of the vertebrae segmentation. 

EXISTING METHOD:

The previous section which produce in accurate estimation about the vertebrae. So, refinement step is needed to remove the false positive results, eliminate the incorrect output and produce accurate vertebrae localization.

DISADVANTAGES:

Detection is not accurate.
Less efficiency.
Less accuracy.
PROPOSED METHOD:

Our proposed method is efficient and widely used techniques that used to localize and identify the individual vertebrae from the spine. These techniques are grouped in three different segmentation sets: conventional-based segmentation techniques, anatomical model-based segmentation techniques and random forest-based segmentation techniques. The first step in this technique was calculating the gradient image of the initial vertebral skeleton image to detect set of points on the Hough lines of the lumbar vertebrae at each disc level using Hough transform function. Finally, each vertebra was segmented and represented by four points for the four vertebra comers and four mid-way points for each vertebra edge. The researchers obtained an accuracy of 97.3 % and sensitivity of 91.67 %.

ADVANTAGES:

High accuracy is obtained and time consumption for detecting the vertebrae.
More accuracy.
High efficiency.

ALGORITHM:

1. GLCM
2. SVM
3. Image scaling
BLOCK DIAGRAM:

SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:

Processor Type : Pentium -IV
Speed : 2.4 GHZ
Ram : 128 MB RAM
Hard disk                                : 20 GB HD

SOFTWARE REQUIREMENTS

Operating System             : Windows 7 
Software Programming Package : Matlab R2014a

REFERENCES:

H.zhu, "Medical Image Processing Overview," University of Calgary, Summer School Program-Introduction to Mathematical Medicine, held at the University of Waterloo. MIDDLE EAST JOURNAL OF INTERNAL MEDICINE 2.3 (2003) 20