A study about evolutionary and non-evolutionary segmentation techniques on hand radiographs for bone age assessment. (March 2017)

• Record Type: Journal Article
• Authors: Simu, Shreyas; Lal, Shyam
• Is Part Of: Biomedical signal processing and control. Volume 33(2017)
• Page Start: 220
• Page End: 235
• Publication Date: 2017-03
• Subjects: Hand bone segmentation -- Bone age assessment -- Evolutionary algorithms -- Non-evolutionary algorithms; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2016.11.016
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract : Highlights: We study evolutionary and non-evolutionary segmentation techniques on hand radiographs. Performance of evolutionary segmentation techniques is better than non-evolutionary segmentation techniques. MICO evolutionary algorithm is very accurate method for segmentation of hand radiographs. Abstract: In this paper, a study and performance comparison of various evolutionary and non-evolutionary segmentation techniques on digital hand radiographs for bone age assessment is presented. The segmented hand bones are of vital importance in process of automated bone age assessment (ABAA). Bone age assessment is a technique of checking the skeletal development and detecting growth disorder in a person. However, it is very difficult to segment out the bone from the soft tissue. The problem arises from overlapping pixel intensities between bone region and soft tissue region and also between soft tissue region and background. Thus there is a requirement for a robust segmentation technique for hand bone segmentation. Taking this into consideration we make a comparison between non-evolutionary and evolutionary segmentation algorithms implemented on hand radiographs to recognize bone borders and shapes. The simulation and experimental results demonstrate that multiplicative intrinsic component optimization (MICO) algorithm provides better results as compared to other existing evolutionary and non-evolutionary algorithms.