Automatic bone age estimation based on carpal-bone image--a preliminary report.

B C Fan; C W Hsieh; T L Jong; C M Tiu

Home/Archive/PubMed

PubMed · 11458757

Automatic bone age estimation based on carpal-bone image--a preliminary report.

B C Fan·C W Hsieh·T L Jong·C M Tiu

View original source ↗Export metadata ↓

Abstract

BACKGROUND: Bone age (BA) estimation is one of the important applications of hand radiography in the area of pediatrics, especially for the diagnosis of endocrinological problems and growth disorders. BA estimation (BAE) is tedious, time-consuming and highly dependent upon the expert experience. Nowadays, most BAE standards are based on American standards, but there is no BAE standard for Taiwanese people. We attempt to construct a computerized BAE system to automate BAE and in the long run to build a BAE standard for Taiwanese. METHODS: Our BAE system is based on the carpal bone information. We propose a new 2-stage edge detection method for carpal bone feature extraction and a new method for locating the carpal bone region of interest. RESULTS: After the image is manually equalized, our BAE system can estimate the bone age automatically. The extracted carpal bone features were applied to three classifiers for age estimation: the weighted minimum distance, Bayes, and neural network classifiers. The Bayes and neural network classifiers had better results. In the 0.5-year tolerance case, they both had over 90% correct rate for both male and female training data. In the 1-year tolerance case, they could classify correctly for the male and female testing data. CONCLUSIONS: A computerized BAE system has been developed and some experiments have been conducted. It is found that the classifying results for 0.5-year tolerance are good and satisfactory.

Explore related subjects

Age Determination by Skeleton Carpal Bones Female Humans Male Journal Article Research Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

B C Fan, C W Hsieh, T L Jong, C M Tiu. 2001. Automatic bone age estimation based on carpal-bone image--a preliminary report.. https://pubmed.ncbi.nlm.nih.gov/11458757/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2003

Osseous fragility in Marshall-Smith syndrome.

Marshall-Smith syndrome is characterized by accelerated osseous maturation, craniofacial anomalies, failure to thrive, psychomotor delay, hypotonia, pulmonary dysfunction, and limited life expectancy. We describe a 7-year-old girl who, in addition to meeting these criteria for Marshall-Smith syndrome, had multiple fractures and skeletal anomalies. The purpose of this report is to draw attention to Marshall-Smith syndrome as one of the skeletal dysplasias characterized by osseous fragility.

Age Determination by Skeleton↗

PubMed2003

Body proportions before and during growth hormone therapy in children with chronic renal failure.

Growth retardation is a common problem in children with chronic renal failure (CRF). Few published data are available on whether the normalization of height in these children during growth hormone (GH) treatment is accompanied by proportional growth of the other parts of the body. In this study, body proportions before and during GH therapy were assessed in children with severe growth retardation due to CRF. Various body segments, such as sitting height, arm span, tibia, hand and foot length, biacromial and biiliacal diameter were measured in 15 children participating in a double-blind placebo-controlled cross-over trial and in 22 children participating in a double-blind dose-response trial. Twelve children continued GH therapy after having participated in one of the two former trials and received GH therapy for 4 years. All results were adjusted for age and sex, and expressed as SD scores using reference values for healthy Dutch children. To assess body proportions, the various body segments were related to height and expressed as shape values (SV). At baseline all body segments SD scores were significantly lower than zero, indicating that the stunted growth of children with CRF included all body segments. Since height was not significantly more or less affected than the other body segments, all children had normal SV, indicating normal body proportions. The placebo-controlled study showed a significant increase of the SD scores of height and several body segments during 6 months of GH [28 IU/m(2) per week (or 1.3 mg/m(2) per day)] versus placebo. The dose-response study demonstrated that height SDS as well as all other body segments SD scores increased significantly during 2 years of GH therapy with 28 IU/m(2) per week, compared with treatment with 14 IU/m(2) per week. Also during 4 years of GH therapy with 28 IU/m(2) per week, body segment SD scores increased to the same extent as height SDS, showing that GH did not significantly change SV i.e., body proportions. Both before and during GH therapy, children on dialysis had normal body proportions, comparable with children on conservative renal treatment. In conclusion, children with severe growth retardation due to CRF maintain normal body proportions in spite of their chronic disease. GH therapy with 28 IU/m(2) per week induces and maintains catch-up growth of height and all body segments without signs of disproportionate growth. Thus GH therapy does not negatively influence body proportions in children with severe growth retardation secondary to CRF.

Age Determination by Skeleton↗

PubMed2003

A longitudinal study on hand and wrist skeletal maturation in chimpanzees ( Pan troglodytes), with emphasis on growth in linear dimensions.

Skeletal maturation in the chimpanzee hand and wrist (the RUS system; radius, ulna, and short bones) was studied both longitudinally and cross-sectionally. Maturity states were evaluated in each of the 13 bones of the RUS system based on the TW2 method (Tanner and Whitehouse method), and the RUS score was calculated by the summation of scores for these bones. Individual variation was examined by means of residual curves and pseudo-velocity curves of RUS score and anterior trunk length (ATL). Norms of the age change pattern in RUS skeletal maturation and the growth of ATL were determined for each sex, and the relationships among ATL growth and skeletal and reproductive maturation were examined. We found a fairly good relationship between ATL growth and RUS skeletal maturation. Comparison of growth and development between humans and chimpanzees showed that growth characteristics are coupled with each other at puberty in male chimpanzees and in both sexes of humans. Although nutritional condition influenced ATL growth in infancy, it had no effect on the RUS maturational process. Social relationships appeared to influence both ATL growth and RUS maturation. Analyses on relationships between RUS skeletal maturation, ATL growth, and reproductive maturation, showed that RUS skeletal maturation is a good indicator of "physiological age".

Age Determination by Skeleton↗