Holistic contrast enhancement of carpals ossification sites for skeletal age assessment system

• Published in: Journal of engineering (Stevenage, England) Vol. 2017; no. 8; pp. 479 - 494
• Main Authors: Kim Meng, Liang, Yan Chai, Hum, Pingguan‐Murphy, Belinda, Mohamad Salim, Maheza Irna, Lai, Khin Wee
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.08.2017
• Subjects: bone; bone age assessment; carpal bones; carpals ossification sites; children; classifier accuracy; diagnostic radiography; holistic contrast enhancement; image enhancement; left hand skeletal; medical disorders; optimised bi‐histogram equalisation; paediatrician visibility; paediatricians; paediatrics; Pareto optimisation; Pareto optimised images; pertinent radiographic manifestations; skeletal age assessment system; skeletal maturity
• ISSN: 2051-3305; 2051-3305
• DOI: 10.1049/joe.2017.0216

Paediatricians often apply bone age assessment to measure the skeletal maturity of children and to predict the future height. These discrepancies are good indicators for diagnosing growth disorders. Normally, left hand skeletal is employed in this assessment. The low quality of ossification sites of carpals deteriorates the paediatrician's visibility in inspecting the pertinent radiographic manifestations. This in turn affects the bone age assessment. Therefore, the quality has to be enhanced before assessing them. Histogram equalisation is one of the contrast enhancement techniques that suit this enhancement. Existing histogram equalisations, however, are confronting with problems in preserving the brightness and details as well as preventing the contrast from being over‐enhanced or under‐enhanced simultaneously. The authors propose the comprehensive histogram equalisation considering all criteria of desired histogram‐equalised image to produce moderately contrast enhanced carpals’ ossification sites. Qualitative results show that the determining features of maturity stages have been emphasised in some of the Pareto optimised image. The improvement for Pareto optimised bi‐histogram equalisation is significant for all stages: 7.16, 12.4, 16.03, 21.21 and 18.51%. The authors conclude that the Pareto optimised images are able to improve the classifier accuracy that estimate the maturity stage of the carpal bones.