Texture Analysis and Modified Level Set Method for Automatic Detection of Bone Boundaries in Hand Radiographs

Abstract

Rheumatoid Arthritis (RA) is a chronic inflammatory joint disease characterized by a distinctive pattern of bone and joint destruction. To give an RA diagnosis, hand bone radiographs are taken and analyzed. A hand bone radiograph analysis starts with the bone boundary detection. It is however an extremely exhausting and time consuming task for radiologists. An automatic bone boundary detection in hand radiographs is thus strongly required. Garcia et al. have proposed a method for automatic bone boundary detection in hand radiographs by using an adaptive snake method, but it doesn’t work for those affected by RA. The level set method has advantages over the snake method. It however often leads to either a complete breakdown or a premature termination of the curve evolution process, resulting in unsatisfactory results. For those reasons, we propose a modified level set method for detecting bone boundaries in hand radiographs affected by RA. Texture analysis is also applied for distinguishing the hand bones and other areas. Evaluating the experiments using a particular set of hand bone radiographs, the effectiveness of the proposed method has been proved.

Authors and Affiliations

Syaiful Anam, Eiji Uchino, Hideaki Misawa, Noriaki Suetake

Keywords

Related Articles

Dynamic Data Aggregation Approach for Sensor-Based Big Data

Sensors are being used in thousands of applications such as agriculture, health monitoring, air and water pollution monitoring, traffic monitoring and control. As these applications collect zettabytes of data everyday se...

QRishing: A User Perspective

QR Code offers more benefits and features than its predecessor, Barcode, which make it more popular. However, there is no doubt that behind the features and conveniences offered by QR Code, it turns that the QR Code can...

Predictive Method for Service Composition in Heterogeneous Environments within Client Requirements

Cloud computing is a new delivery model for Information Technology services. Many actors and parameters play an important role in provisioning of dynamically elastic and virtualized resources at the levels of infrastruct...

Increase Efficiency of SURF using RGB Color Space

SURF is one of the most robust local invariant feature descriptors. SURF is implemented mainly for gray images. However, color presents important information in the object description and matching tasks as it clearly in...

An Efficient Application Specific Memory Storage and ASIP Behavior Optimization in Embedded System

Low power embedded system requires effective memory design system which improves the system performance with the help of memory implementation techniques. Application specific data allocation design pattern implements th...

Download PDF file
  • EP ID EP126907
  • DOI 10.14569/IJACSA.2014.051017#sthash.CAk3HR3T.dpuf
  • Views 91
  • Downloads 0

How To Cite

Syaiful Anam, Eiji Uchino, Hideaki Misawa, Noriaki Suetake (2014). Texture Analysis and Modified Level Set Method for Automatic Detection of Bone Boundaries in Hand Radiographs. International Journal of Advanced Computer Science & Applications, 5(10), 117-126. https://europub.co.uk/articles/-A-126907