Threshold-Based New Segmentation Model to Separate the Liver from CT Scan Images

Abstract

The liver is considered as one of the complicated organs in human body. It has close proximity to the neighboring organs in abdomen with numerous anatomical variations. It is difficult to find out the severity of disease connected to the liver unless the scanned image is subjected to segmentation process. The difficulty level also varies with the diseases that affect the liver. Any of the disease alters its density, homogeneity, color and texture. Liver image segmentation is necessary to identify the complexity and severity of the disease and it remains as an open challenge to researchers. Among all liver segmentation algorithms, threshold segmentation is fastest, simplest and numerically less complex. The accuracy of threshold-based segmentation lies in the selection of threshold values which separates foreground and background. This paper proposes a novel multi-threshold liver segmentation model based on “Slope Difference Distribution” (SDD) of image histogram. It consists of three stages. In the first stage, the noise in Computed Tomography (CT) scan image is reduced using a median filter. In the second stage, automatic threshold values are obtained from SDD of image histogram. These threshold values separate the liver image accurately from abdominal CT scan image. In the third stage, seed points are selected automatically which grow outwardly using the Fast Marching Method (FMM) discovering liver border in CT scan image. The proposed model is tested on 55 CT scan images and it is providing satisfactory results.

KEYWORDS:

• CT scan image
• Fast marching method
• Liver segmentation
• Slope difference distribution
• Threshold-based segmentation

Acknowledgement

The authors would like to express their heartfelt thanks to the Management of Global Academy of Technology, Bangalore, JSS Academy of Technical Education, Bangalore and JNN College of Engineering, Shivamogga, for their support and encouragement in carrying out this research work.

Additional information

Notes on contributors

Sangeeta K. Siri

Sangeeta K Siri has completed Bachelor of Engineering in 1998 in SDMCET, Dharwad, Karnataka, India. She completed her Master's degree in electronics from BMSCE, Bangalore, Karnataka, India, and PhD has been awarded from VTU, Belagavi, Karnataka, India. She is working as an associate professor in Department of Electronics and Communication at Global Academy of Technology (GAT). Her area of interest is image processing and pattern recognition. She won the “Best Paper” award in National Conference on Networking, Embedded and Wireless System NEWS2010 held at BMS College of Engineering on 6 Aug 2010.

S. Pramod Kumar

Pramod Kumar S received his BE Degree in electronics and communication engineering from VEC Bellay and MTech, in VLSI design and embedded systems from UTL Technologies Limited, Bangalore, PhD from VTU-RRC Belgaum and is working as a faculty in Department of Electronics and Communication, Jawaharlal Nehru National College of Engineering, Shivamogga, India. Email: [email protected]

Mrityunjaya V. Latte

Mrityunjaya V Latte received his BE in electrical engineering and ME in digital electronics from SDM College of Engineering & Technology, Dharwad, Karnataka, India. Dr Latte was awarded the PhD degree in 2004 for his work in the area of digital signal processing. Presently, he is working as the principal, JSS Academy of Technical Education, Bangalore, Karnataka, India. His research interests include coding, image processing and multi-resolution transforms. He received the “Best paper” award for his paper in a National Conference NCSSS 2002 held at Coimbatore, India. Email: [email protected]