• Journal of Korea Multimedia Society
• /
• v.12 no.3
• /
• pp.383-396
• /
• 2009

Bone age assessment has been widely used in pediatrics to identify endocrine problems of children. Since the number of trained doctors is far less than the demands, there has been numerous requests for automatic estimation of bone age. Therefore, in this paper, we propose an automatic bone age assessment method that utilizes pattern classification techniques. The proposed method consists of three modules; a finger segmentation module, a normalized shape model generation module and a bone age estimation module. The finger segmentation module segments fingers and epiphyseal regions by means of various image processing algorithms. The shape model abstraction module employ ASM to improves the accuracy of feature extraction for bone age estimation. In addition, SVM is used for estimation of bone age. Features for the estimation include the length of bone and the ratios of bone length. We evaluated the performance of the proposed method through statistical analysis by comparing the bone age assessment results by clinical experts and the proposed automatic method. Through the experimental results, the mean error of the assessment was 0.679 year, which was better than the average error acceptable in clinical practice.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.22-29
• /
• 2021

In the past decade, deep learning has been applied to various medical image analysis tasks. Skeletal bone age estimation is clinically important as it can help prevent age-related illness and pave the way for new anti-aging therapies. Recent research has applied deep learning techniques to the task of bone age assessment and achieved positive results. In this paper, we propose a bone age prediction method using a deep convolutional neural network. Specifically, we first train a classification model that automatically localizes the most discriminative region of an image and crops it from the original image. The regions of interest are then used as input for a regression model to estimate the age of the patient. The experiments are conducted on a whole-body scintigraphy dataset that was collected by Chonnam National University Hwasun Hospital. The experimental results illustrate the potential of our proposed method, which has a mean absolute error of 3.35 years. Our proposed framework can be used as a robust supporting tool for clinicians to prevent age-related diseases.

• Advances in nano research
• /
• v.12 no.2
• /
• pp.197-212
• /
• 2022

The purpose of this study is to develop an automatic software system for bone age evaluation and to evaluate its accuracy in testing and feasibility in clinical practice. 20394 left-hand radiographs of healthy children (2-18 years old) were collected from China Skeletal Development Survey data of 1998 and China Skeletal Development Survey data of 2005. Three experienced radiologists and China-05 standard maker jointly evaluate the stages of bone development and the reference bone age was determined by consensus. 1020 from 20394 radiographs were picked randomly as test set and the remaining 19374 radiographs as training set and validation set. Accuracy of the automatic software system for bone age assessment is evaluated in test set and two clinical test sets. Compared with the reference standard, the automatic software system based on RUS-CHN for bone age assessment has a 0.04 years old mean difference, ±0.40 years old in 95% confidence interval by single reading, a 85.6% percentage agreement of ratings, a 93.7% bone age accuracy rate, 0.17 years old of MAD, 0.29 years old of RMS; Compared with the reference standard, the automatic software system based on TW3-C RUS has a 0.04 years old mean difference, a ±0.38 years old in 95% confidence interval by single reading, a 90.9% percentage agreement of ratings, a 93.2% bone age accuracy rate, a 0.16 years of MAD, and a 0.28 years of RMS. Automatic software system, AI-China-05 showed reliably accuracy in bone age estimation and steady determination in different clinical test sets.

• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1376-1384
• /
• 2019

The cosmetic and behavioral aspects of aging have become increasingly evident over the years. Physical aging in people can easily be observed on their face, posture, voice, and gait. In contrast, bone aging only becomes apparent once significant bone degeneration manifests through degenerative bone diseases. Therefore, a more accurate and timely assessment of bone aging is needed so that the determinants and its mechanisms can be more effectively identified and ultimately optimized. This study proposed a deep learning approach to assess the bone age of an adult using whole-body bone scintigraphy. The proposed approach uses multiple inputs deep neural network architectures using a loss function, called mean-variance loss. The data set was collected from Chonnam National University Hwasun Hospital. The experiment results show the effectiveness of the proposed method with a mean absolute error of 3.40 years.

• The Journal of Pediatrics of Korean Medicine
• /
• v.37 no.2
• /
• pp.1-11
• /
• 2023

Objectives We aimed to compare the bone age (BA) estimation by a deep learning-based program and by a specialist in pediatrics of Korean medicine using the Tanner-Whitehouse 3 (TW3) technique for the cases of children who visited a Korean medicine hospital for growth, and to report the effect of Korean medicine treatment. Methods For three children who visited the Korean medicine hospital for growth, BA estimation by the deep learning program and by the specialist in pediatrics of Korean medicine using the TW3 technique was compared, and the time required for estimation was investigated. The change of height, BA, and predicted adult height (PAH) using deep learning program after Korean medicine treatment was observed. Results BA estimation of the left hand bone X-ray by the specialist using the TW3 technique showed a difference of -0.03 to +0.15 years from the estimation by the deep learning program. The mean estimation time was 5 minutes and 49 seconds per one for the specialist and 48 seconds for the deep learning program. During the treatment period, the height percentile and PAH estimated by deep learning program were increased after Korean medicine treatment compared to baseline while acceleration of BA was suppressed compared to chronological age. Conclusions BA estimation using the deep learning program and the TW3 technique showed a difference of less than 0.15 years, and in three cases of patients with growth as the chief complaint, Korean medicine treatment increased height percentile and PAH without accelerating BA maturation.

• Journal of Oral Medicine and Pain
• /
• v.13 no.1
• /
• pp.13-21
• /
• 1988

The author studied the vertical height of tooth crown and the amounts of alveolar bone resorption with age. All 84 subjects(44 male, 40female) who visited Dental hospital of Wonkwang University with no history of sever periodontal disease and no experience of periodontal surgery. 84 subject were divided into 3 groups by age, that is, group I(28-32yrs), group II(38-42yrs), and group III(48-52yrs). Informal radiogram with bite wing film(horizontal angulation : $0^{\circ}$, vertical angulation : $+5^{\circ}~+10^{\circ}$) were taken on premolar and molar area. The distances from cusp tip to cementoenamel junction (vertical height of tooth crown) and from cementoenamel junction alveolar crest(amount of alveolar bone resorption) were measured, and then recorded data from 946 teeth were statistically analysed. This study was undertaken to obtain the data for age estimation by the changes of tooth crown height and alveolar bone resorption in the point of forensic odontology. The obtained results were as follows : 1. The average crown height of mandibular right 1st. molar was 7.1mm in group I, 6.7mm in group II, and 6.6mm group III, and the average amount of alveolar bone resorption on mandibular right 1st. molar were 1.8mm in group I, 2.5mm in group II, and 3.0mm in group III. Ratio of tooth crown height to amount of alveolar bone resorption was 4.0:1 in groupI, 2.7:1 in group II, and 2.2:1 in group III, the ratio was decreased with age. 2. In comparison with upper teeth and lower teeth in ipsilateral side, the average value of tooth crown height and amount of alveolar bone resorption were slightly higher in upper arch than those in lower arch, but there was not a statistically significant difference. 3. The ratio of height of tooth crown to amount of alveolar bone resorption was decreased with age, and which depended mainly upon the change of amount of alveolar bone resorption rather than the change of tooth crown height.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.808-810
• /
• 2004

왜소증 조기진단을 위한 왼쪽 손의 방사선 영상을 통한 방법은 일반적으로 나이와 성별에 따른 방사선 영상들과 비교하여 의사가 직접 눈으로 비슷한 영상을 찾아 뼈 나이를 추정한다. 하지만 나이, 성별, 민족 등 여러 요인에 따라서 측정결과가 달라질 수 있고 각 나라별로 독자적인 기준이 필요하므로 본 논문에서는 한국인의 Carpal bone 분석과 이에 따른 Computerized Bone Age System을 제안한다. 뼈 나이 측정을 위해 6개의 연골을 측정하고, 분석할 6개의 연골 ROI(Region of Interest)를 찾기 위하여 연골들의 에지를 검출하였다. 영상의 에지를 검출하기 위하여 DoG (Difference of Gaussian) Filtering을 사용하였으며, Carpal Bone을 분석한 뒤 2차원 특징들로 ㅂW 나이 추정에 대한 진단의 정확도를 확인 할 수 있었다.

• Journal of Nutrition and Health
• /
• v.24 no.1
• /
• pp.30-39
• /
• 1991

This study was designed to investigate the effects of dietary calcium. serum estrogen level and physical activity on the bone status of 116 healthy elderly women living in urban area. Current calcium intake was assessed by convenient method(refered to as Ca intake) and calcium containing food frequency method(refered to as Ca index) Daily activity record was used for the estimation of physical activity level, and serum estrogen level was measured from fasting blood of subjects. The rate of bone resorption was evaluated by the determination of hydroxyproline(Hpr) in fasting urine with correction for creatinine excretion. The results of this study are summarized as follows : 1) Average daily Ca intake of subjects was 621.4$\pm$155.8mg, which is above the Korean recommended dietary allowances. However 44.8% of the subjects consumed Ca below RDA level. Ca index score was significantly correlated with the bone status(P<0.05), Ca intake did not show significant correlation with the bone status although a positive trend of influence was evident. 2) Average serum estrogen level of subjects was 18.7$\pm$9.8pg Contrary to our anticipation. estrogen level did not show any significant relation to age and bone status. 3) Daily physical activity was classified into four categories by activity intensity : sedentary. moderate, active and severe. The average physical activity of subjects belong to moderate level. and the bone status was significantly related to the physical activity(P<0.01) 4) Among other influential factors such as age, pocket-money. family type. drinking, smoking and BMI, there was a significant difference between bone status and BMI(P<0.05). 5) Multiple regression analysis of variables showed that physical activity has greater effect than other variables when the entire subjects were taken into account. However. eliminating the subjects whose bone status rated as excellent(Hpr/cr<0.009), Ca index showed higher correlation than physical activity. These results have demonstrated that dietary calcium intake is the primary important factor for keeping good bone health and that bone status of subjects with a sufficient calcium intake is affected by various factors such as physical activity, age, smoking. BMI and others.

• Anatomy and Cell Biology
• /
• v.56 no.1
• /
• pp.86-93
• /
• 2023

Age at death estimation has always been a crucial yet challenging part of identification process in forensic field. The use of human skeletons have long been explored using the principle of macro and micro-architecture change in correlation with increasing age. The clavicle is recommended as the best candidate for accurate age estimation because of its accessibility, time to maturation and minimal effect from weight. Our study applies pre-trained convolutional neural network in order to achieve the most accurate and cost effective age estimation model using clavicular bone. The total of 988 clavicles of Thai population with known age and sex were radiographed using Kodak 9000 Extra-oral Imaging System. The radiographs then went through preprocessing protocol which include region of interest selection and quality assessment. Additional samples were generated using generative adversarial network. The total clavicular images used in this study were 3,999 which were then separated into training and test set, and the test set were subsequently categorized into 7 age groups. GoogLeNet was modified at two layers and fine tuned the parameters. The highest validation accuracy was 89.02% but the test set achieved only 30% accuracy. Our results show that the use of medial clavicular radiographs has a potential in the field of age at death estimation, thus, further study is recommended.

• Journal of Radiation Protection and Research
• /
• v.46 no.1
• /
• pp.1-7
• /
• 2021

Background: The use of computed tomography (CT) device has increased in the past few decades in Japan. Dose optimization is strongly required in pediatric CT examinations, since there is concern that an unreasonably excessive medical radiation exposure might increase the risk of brain cancer and leukemia. To accelerate the process of dose optimization, continual assessment of the dose levels in actual hospitals and medical facilities is necessary. This study presents organ dose estimation using pediatric cerebral CT scans in the Kyushu region, Japan in 2012 and the web-based calculator, WAZA-ARI (https://waza-ari.nirs.qst.go.jp). Materials and Methods: We collected actual patient information and CT scan parameters from hospitals and medical facilities with more than 200 beds that perform pediatric CT in the Kyushu region, Japan through a questionnaire survey. To estimate the actual organ dose (brain dose, bone marrow dose, thyroid dose, lens dose), we divided the pediatric population into five age groups (0, 1, 5, 10, 15) based on body size, and inputted CT scan parameters into WAZA-ARI. Results and Discussion: Organ doses for each age group were obtained using WAZA-ARI. The brain dose, thyroid dose, and lens dose were the highest in the Age 0 group among the age groups, and the bone marrow and thyroid doses tended to decrease with increasing age groups. All organ doses showed differences among facilities, and this tendency was remarkable in the young group, especially in the Age 0 group. This study confirmed a difference of more than 10-fold in organ doses depending on the facility and CT scan parameters, even when the same CT device was used in the same age group. Conclusion: This study indicated that organ doses varied widely by age group, and also suggested that CT scan parameters are not optimized for children in some hospitals and medical facilities.