The BoneXpert method for automated determination of skeletal maturity

GnRH receptor gene mutations in adolescents and young adults presenting with signs of partial gonadotropin deficiency

Biallelic, partial loss-of-function mutations in GNRHR cause a wide spectrum of reproductive phenotypes from constitutional delay of growth and puberty to complete congenital hypogonadotropic hypogonadism. We studied the frequency of GNRHR, FGFR1, TAC3, and TACR3 mutations in nine adolescent and young adult females with clinical cues consistent with partial gonadotropin deficiency (stalled puberty, unexplained secondary amenorrhea), and describe phenotypic features and molecular genetic findings of monozygotic twin brothers with stalled puberty.

Two girls out of nine (22%, 95%CI 6–55%) carried biallelic mutations in GNRHR. The girl with compound heterozygous c.317A>G p.(Gln106Arg) and c.924_926delCTT p.(Phe309del) GNRHR mutations displayed incomplete puberty and clinical signs of hypoestrogenism. The patient carrying a homozygous c.785G>A p.(Arg262Gln) mutation presented with signs of hypoestrogenism and unexplained secondary amenorrhea. None of the patients exhibited mutations in FGFR1, TAC3, or TACR3. The twin brothers, compound heterozygous for GNRHR mutations c.317A>G p.(Gln106Arg) and c.785G>A p.(Arg262Gln), presented with stalled puberty and were discordant for weight, and the heavier of them had lower testosterone levels.

These results suggest that genetic testing of the GNRHR gene should be offered to adolescent females with low-normal gonadotropins and unexplained stalled puberty or menstrual dysfunction. In male patients with partial gonadotropin deficiency, excess adipose tissue may suppress hypothalamic-pituitary-gonadal axis.

Performance of a Deep-Learning Neural Network Model in Assessing Skeletal Maturity on Pediatric Hand Radiographs

Purpose To compare the performance of a deep-learning bone age assessment model based on hand radiographs with that of expert radiologists and that of existing automated models. Materials and Methods The institutional review board approved the study. A total of 14 036 clinical hand radiographs and corresponding reports were obtained from two children's hospitals to train and validate the model. For the first test set, composed of 200 examinations, the mean of bone age estimates from the clinical report and three additional human reviewers was used as the reference standard. Overall model performance was assessed by comparing the root mean square (RMS) and mean absolute difference (MAD) between the model estimates and the reference standard bone ages. Ninety-five percent limits of agreement were calculated in a pairwise fashion for all reviewers and the model. The RMS of a second test set composed of 913 examinations from the publicly available Digital Hand Atlas was compared with published reports of an existing automated model. Results The mean difference between bone age estimates of the model and of the reviewers was 0 years, with a mean RMS and MAD of 0.63 and 0.50 years, respectively. The estimates of the model, the clinical report, and the three reviewers were within the 95% limits of agreement. RMS for the Digital Hand Atlas data set was 0.73 years, compared with 0.61 years of a previously reported model. Conclusion A deep-learning convolutional neural network model can estimate skeletal maturity with accuracy similar to that of an expert radiologist and to that of existing automated models. ^© RSNA, 2017 An earlier incorrect version of this article appeared online. This article was corrected on January 19, 2018.

Fourier-based quantification of renal glomeruli size using Hough transform and shape descriptors

BACKGROUND AND OBJECTIVE

Analysis of glomeruli geometry is important in histopathological evaluation of renal microscopic images. Due to the shape and size disparity of even glomeruli of same kidney, automatic detection of these renal objects is not an easy task. Although manual measurements are time consuming and at times are not very accurate, it is commonly used in medical centers. In this paper, a new method based on Fourier transform following usage of some shape descriptors is proposed to detect these objects and their geometrical parameters.

METHODS

Reaching the goal, a database of 400 regions are selected randomly. 200 regions of which are part of glomeruli and the other 200 regions are not belong to renal corpuscles. ROC curve is used to decide which descriptor could classify two groups better. f_measure, which is a combination of both tpr (true positive rate) and fpr (false positive rate), is also proposed to select optimal threshold for descriptors. Combination of three parameters (solidity, eccentricity, and also mean squared error of fitted ellipse) provided better result in terms of f_measure to distinguish desired regions. Then, Fourier transform of outer edges is calculated to form a complete curve out of separated region(s).

RESULTS

The generality of proposed model is verified by use of cross validation method, which resulted tpr of 94%, and fpr of 5%. Calculation of glomerulus' and Bowman's space with use of the algorithm are also compared with a non-automatic measurement done by a renal pathologist, and errors of 5.9%, 5.4%, and 6.26% are resulted in calculation of Capsule area, Bowman space, and glomeruli area, respectively.

CONCLUSIONS

Having tested different glomeruli with various shapes, the experimental consequences show robustness and reliability of our method. Therefore, it could be used to illustrate renal diseases and glomerular disorders by measuring the morphological changes accurately and expeditiously.

Managing the Pediatric Spine: Growth Assessment

Management of pediatric spinal deformities requires an accurate prediction of growth spurts to allow for timely initiation of treatment and prevention of curve progression. Determining remaining growth potential is also important for avoiding prolonged unnecessary treatment, e.g. bracing for patients nearing skeletal maturity. Many clinical and radiological growth parameters have been developed to aid clinicians in growth prediction. Of these, several commonly used measures such as height and arm span growth trends, timing of menarche, and the Risser sign are mostly retrospective and lack strong predictive utility. Bone age assessments, such as digital skeletal age and the distal radius and ulna classification, are more accurate parameters, but further research is required to determine interethnic variations and develop their role in management decisions.

Joint cartilage thickness and automated determination of bone age and bone health in juvenile idiopathic arthritis

BACKGROUND

BoneXpert is an automated method to calculate bone maturation and bone health index (BHI) in children with juvenile idiopathic arthritis (JIA). Cartilage thickness can also be seen as an indicator for bone health and arthritis damage. The objective of this study was to evaluate the relation between cartilage thickness, bone maturation and bone health in patients with JIA.

METHODS

Patients with JIA diagnosed according ILAR criteria included in a previous ultrasonography (US) study were eligible if hand radiographs were taken at the same time as the US examination. Of the 95 patients 67 met the inclusion criteria.

RESULTS

Decreased cartilage thickness was seen in 27% of the examined joints. Decreased BHI was seen in half of the JIA patient, and delayed bone maturation was seen in 33% of patients. A combination of decreased BHI and bone age was seen in 1 out of 5 JIA patients. Decreased cartilage thickness in the knee, wrist and MCP joint was negatively correlated with delayed bone maturation but not with bone health index.

CONCLUSION

Delayed bone maturation and decreased BHI were not related to a thinner cartilage, but a thicker cartilage. No relation with JADAS 10 was found. The rheumatologist should remain aware of delayed bone maturation and BHI in JIA patients with cartilage changes, even in the biologic era.

Fully Automated Deep Learning System for Bone Age Assessment

Skeletal maturity progresses through discrete phases, a fact that is used routinely in pediatrics where bone age assessments (BAAs) are compared to chronological age in the evaluation of endocrine and metabolic disorders. While central to many disease evaluations, little has changed to improve the tedious process since its introduction in 1950. In this study, we propose a fully automated deep learning pipeline to segment a region of interest, standardize and preprocess input radiographs, and perform BAA. Our models use an ImageNet pretrained, fine-tuned convolutional neural network (CNN) to achieve 57.32 and 61.40% accuracies for the female and male cohorts on our held-out test images. Female test radiographs were assigned a BAA within 1 year 90.39% and within 2 years 98.11% of the time. Male test radiographs were assigned 94.18% within 1 year and 99.00% within 2 years. Using the input occlusion method, attention maps were created which reveal what features the trained model uses to perform BAA. These correspond to what human experts look at when manually performing BAA. Finally, the fully automated BAA system was deployed in the clinical environment as a decision supporting system for more accurate and efficient BAAs at much faster interpretation time (<2 s) than the conventional method.

Determinants of Advanced Bone Age in Childhood Obesity

BACKGROUND

Childhood obesity is associated with advanced bone age (BA). Previous studies suggest that androgens, oestrogens, sex hormone-binding globulin, and insulin are responsible for this phenomenon, but results are contradictory and might be biased by confounders. We aim to elucidate this matter by applying a multivariate approach.

METHOD

We performed a correlation analysis of BA standard deviation score (SDS) with age- and sex-specific SDS for androgens, oestrogens, and with indicators of insulin secretion derived from oral glucose tolerance testing, in a group of obese children. A multivariate analysis was performed to investigate which parameters were independently predictive of BA SDS.

RESULTS

In this cohort (n = 101; mean age 10.9 years; mean BA 11.8 years; mean BMI SDS 3.3), BMI SDS was significantly correlated to BA SDS (r = 0.55, p < 0.001). In a regression analysis in the total cohort (B = 0.27, p < 0.001) as well as in females (B = 0.34, p = 0.042), males (B = 0.31, p = 0.006), and pubertal children (B = 0.32, p = 0.046), dehydroepiandrosterone sulphate (DHEAS) showed a positive, independent association with BA SDS. No association with indicators of insulin secretion was found.

CONCLUSION

BMI SDS is highly correlated to BA SDS in obese children. Increased DHEAS has a central role in advanced BA in obese children.
.

Automatic Determination of the Greulich-Pyle Bone Age as an Alternative Approach for Chinese Children with Discordant Bone Age

BACKGROUND

Automated bone age (BA) rating using BoneXpert is being adopted worldwide. This study investigated whether manual matching of hand radiographs could be replaced by BoneXpert for BA ratings of Chinese children with delayed or advanced BA.

METHODS

482 left-hand radiographs from 482 children (aged 2-16 years) with discordant BA were evaluated by BoneXpert and manually by 4 radiology residents using the Greulich and Pyle atlas. Radiographs whose BoneXpert BA deviated by >1 year from manual assessment were rerated by 2 attending radiologists in a blinded manner.

RESULTS

Among all 482 radiographs, 46 (9.5%) radiographs were rerated and no radiographs were rejected. Differences between BoneXpert and manual rating of 28 (5.8%) cases were >1 year. The manual BAs of the 28 radiographs were all >10 years and greater than the BoneXpert BAs. The root mean square deviation between the residents and BoneXpert was 0.56 for these children (95% CI 0.53-0.61).

CONCLUSION

BoneXpert agreed with manual BA rating in 94.2% of the images. Therefore, BoneXpert could be used as an alternative for the radiology residents to make an initial BA estimation. Modification of BoneXpert should provide greater accuracy for the estimation of BA in children aged >10 years with discordant BA.

Prevalence of SHOX haploinsufficiency among short statured children

BACKGROUND

The aim of this clinical study was to determine the prevalence of SHOX haploinsufficiency in a population of short stature patients and describe their anthropometric measurements.

METHODS

574 short statured patients were evaluated in a single center (1992-2015). SHOX copy number was detected by quantitative polymerase chain reaction (qPCR) in 574 subjects, followed by multiplex ligation-dependent probe amplification (MLPA) and DNA sequencing in subjects with SHOX haploinsufficiency. We evaluated anthropometric measurements at birth, and at first examination. Skeletal abnormalities were recorded for patients with SHOX haploinsufficiency.

RESULTS

Thirty-two patients were excluded due to Turner syndrome (n = 28), SRY-positive 46,XX male karyotype (n = 1), or lacked clinical follow-up information (n = 3). The prevalence of SHOX haploinsufficiency was 9 out of 542 (1.7%). The nine children had decreased height -2.85 (0.6) SD scores (SDS) (mean (SD)) and weight -2.15 (1.36) SDS, P < 0.001 and P = 0.001, respectively. The sitting height/height ratio was increased, P = 0.04. Madelung deformity was diagnosed in three patients. Mean height was -2.9 (0.4) SDS at baseline and increased by 0.25 (0.2) SDS, P = 0.046, after 1 y of growth hormone (GH) treatment.

CONCLUSION

The prevalence of SHOX haploinsufficiency was 1.7%. The clinical findings indicating SHOX haploinsufficiency among the nine children were disproportionate short stature and forearm anomalies.

Metacarpal bone loss in patients with rheumatoid arthritis estimated by a new Digital X-ray Radiogrammetry method - initial results

BACKGROUND

The Digital X-ray Radiogrammetry (DXR) method measures the cortical bone thickness in the shafts of the metacarpals and has demonstrated its relevance in the assessment of hand bone loss caused by rheumatoid arthritis (RA). The aim of this study was to validate a novel approach of the DXR method in comparison with the original version considering patients with RA.

METHOD

The study includes 49 patients with verified RA. The new version is an extension of the BoneXpert method commonly used in pediatrics which has these characteristics: (1) It introduces a new technique to analyze the images which automatically validates the results for most images, and (2) it defines the measurement region relative to the ends of the metacarpals. The BoneXpert method measures the Metacarpal Index (MCI) at the metacarpal bone (II to IV). Additionally, the MCI is quantified by the DXR X-posure System.

RESULTS

The new version correctly analyzed all 49 images, and 45 were automatically validated. The standard deviation between the MCI results of the two versions was 2.9% of the mean MCI. The average Larsen score was 2.6 with a standard deviation of 1.3. The correlation of MCI to Larsen score was -0.81 in both versions, and there was no significant difference in their ability to detect erosions.

CONCLUSION

The new DXR version (BoneXpert) validated 92% of the cases automatically, while the same good correlation to RA severity could be presented compared to the old version.

Skeletal development of the hand and wrist: digital bone age companion-a suitable alternative to the Greulich and Pyle atlas for bone age assessment?

PURPOSE

To assess reader performance and subjective workflow experience when reporting bone age studies with a digital bone age reference as compared to the Greulich and Pyle atlas (G&P). We hypothesized that pediatric radiologists would achieve equivalent results with each method while digital workflow would improve speed, experience, and reporting quality.

MATERIALS AND METHODS

IRB approval was obtained for this HIPAA-compliant study. Two pediatric radiologists performed research interpretations of bone age studies randomized to either the digital (Digital Bone Age Companion, Oxford University Press) or G&P method, generating reports to mimic clinical workflow. Bone age standard selection, interpretation-reporting time, and user preferences were recorded. Reports were reviewed for typographical or speech recognition errors. Comparisons of agreement were conducted by way of Fisher's exact tests. Interpretation-reporting times were analyzed on the natural logarithmic scale via a linear mixed model and transformed to the geometric mean. Subjective workflow experience was compared with an exact binomial test. Report errors were compared via a paired random permutation test.

RESULTS

There was no difference in bone age determination between atlases (p = 0.495). The interpretation-reporting time (p < 0.001) was significantly faster with the digital method. The faculty indicated preference for the digital atlas (p < 0.001). Signed reports had fewer errors with the digital atlas (p < 0.001).

CONCLUSIONS

Bone age study interpretations performed with the digital method were similar to those performed with the Greulich and Pyle atlas. The digital atlas saved time, improved workflow experience, and reduced reporting errors relative to the Greulich and Pyle atlas when integrated into electronic workflow.

Congenital hypogonadotropic hypogonadism, functional hypogonadotropism or constitutional delay of growth and puberty? An analysis of a large patient series from a single tertiary center

STUDY QUESTION

What diagnoses underlie delayed puberty (DP) and predict its outcome?

SUMMARY ANSWER

A multitude of different diagnoses underlie DP, and in boys a history of cryptorchidism, small testicular size and slow growth velocity (GV) predict its clinical course.

WHAT IS KNOWN ALREADY

DP is caused by a variety of underlying etiologies. Hormonal markers can be used in the differential diagnosis of DP but none of them have shown complete diagnostic accuracy.

STUDY DESIGN, SIZE, DURATION

Medical records of 589 patients evaluated for DP in a single tertiary care center between 2004 and 2014 were retrospectively reviewed.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Clinical and biochemical data of 174 boys and 70 girls who fulfilled the criteria of DP were included in the analyses. We characterized the frequencies of underlying conditions and evaluated the predictive efficacy of selected clinical and hormonal markers.

MAIN RESULTS AND THE ROLE OF CHANCE

Thirty etiologies that underlie DP were identified. No markers of clinical value could be identified in the girls, whereas a history of cryptorchidism in the boys was associated with an increase in the risk of permanent hypogonadism (odds ratio 17.2 (95% CI; 3.4-85.4, P < 0.001)). The conditions that cause functional hypogonadotropic hypogonadism were more frequent in boys with a GV below 3 cm/yr than in those growing faster (19% vs 4%, P < 0.05). In this series, the most effective markers to discriminate the prepubertal boys with constitutional delay of growth and puberty (CDGP) from those with congenital hypogonadotropic hypogonadism (CHH) were testicular volume (cut-off 1.1 ml with a sensitivity of 100% and a specificity of 91%), GnRH-induced maximal LH (cut-off 4.3 IU/L; 100%, 75%) and basal inhibin B (INHB) level (cut-off 61 ng/L; 90%, 83%).

LIMITATIONS, REASONS FOR CAUTION

The main limitation of the study is the retrospective design.

WIDER IMPLICATIONS OF THE FINDINGS

Prior cryptorchidism and slow GV are two important clinical cues that may help clinicians to predict the clinical course of DP in boys, whereas markers of similar value could not be identified in girls. In prepubertal boys, testicular size appeared as effective as INHB and GnRH-induced LH levels in the differential diagnosis between CHH and CDGP.

STUDY FUNDING/COMPETING INTERESTS

This study was supported by the Academy of Finland (268356), Foundation for Pediatric Research (7495), Sigrid Juselius Foundation (2613) and the Finnish Medical Foundation (011115). The authors have no competing interests to report.

TRIAL REGISTRATION NUMBER

Not applicable.

Evaluation and phenotypic characteristics of 293 Danish girls with tall stature: effects of oral administration of natural 17β-estradiol

BACKGROUND

Reduction of adult height by sex steroid treatment was introduced decades ago in tall statured children, but controlled trials are lacking and treatment is controversial. In this study, we wanted to evaluate the phenotypic characteristics in girls referred due to tall stature and the effect of oral administration of 17β-estradiol on predicted adult height in girls.

METHODS

A single-centre retrospective observational study of 304 girls evaluated consecutively due to tall stature between 1993 and 2013. 207 patients diagnosed with constitutionally tall stature (CTS), 60 (29%) girls ended up being treated with 17β-estradiol with a duration of 1.7 y (1.2; 2.5) (median (25; 75 percentile)), and final height was available in 26 girls.

RESULTS

At baseline, 20% of girls with CTS had supranormal IGF-I, whereas reproductive hormones were within the normal range. Final adult height was reduced with 1.6 ± 2.1 cm in the girls treated with 17β-estradiol when compared to initial prediction. Chronological age, bone age, estradiol, and IGF-I at baseline or estrogen dose did not predict height reduction.

CONCLUSIONS

Serum IGF-I was elevated tall statured children, but did not predict the effect of treatment with 17β-estradiol, which caused a modest reduction in final adult height.

Psoriatic arthritis is associated with bone loss of the metacarpals

Background

BoneXpert (BX) is a newly developed medical device based on digital X-ray radiogrammetry to measure human cortical bone thickness. The aim of this study was to quantify cortical bone loss of the metacarpals in patients with psoriatic arthritis (PsA) and compare these findings with other radiological scoring methods.

Methods

The study includes 104 patients with verified PsA. The BX method was used to measure the Metacarpal Index (MCI) at the metacarpal bones (II–IV). Additionally, the T-score of the MCI (T-score_MCI) was calculated. Radiographic severity was determined by the Psoriatic Arthritis Ratingen Score (Proliferation Score and Destruction Score) as published by Wassenberg et al. and the Psoriatic Arthritis modified van der Heijde Sharp Score (Joint Space Narrowing Score and Erosion Score).

Results

For the total PsA study cohort, the T-score_MCI was significantly reduced by −1.289 ± 1.313 SD. The MCI negatively correlated with the Proliferation Score (r = −0.732; p < 0.001) and the Destruction Score (r = −0.771; p < 0.001) of the Psoriatic Arthritis Ratingen Score. Lower coefficients of correlations were observed for the Psoriatic Arthritis modified van der Heijde Sharp Score. In this context, a severity-dependent and PsA-related periarticular demineralisation as measured by the MCI was quantified. The strongest reduction of −30.8 % (p < 0.01) was observed for the MCI in the Destruction Score.

Conclusions

The BX MCI score showed periarticular demineralisation and severity-dependent bone loss in patients with PsA. The measurements of the BX technique were able to sensitively differentiate between the different stages of disease manifestation affecting bone integrity and thereby seem to achieve the potential to be a surrogate marker of radiographic progression in PsA.

Automated determination of bone age from hand X-rays at the end of puberty and its applicability for age estimation

The BoneXpert method for automated determination of bone age from hand X-rays was introduced in 2009, covering the Greulich-Pyle bone age ranges up to 17 years for boys and 15 years for girls. This paper presents an extension of the method up to bone age 19 years for boys and 18 years for girls. The extension was developed based on images from the First Zurich Longitudinal Study of 231 healthy children born in 1954-1956 and followed with annual X-rays of both hands until adulthood. The method was validated on two cross-sectional studies of healthy children from Rotterdam and Los Angeles. We found root mean square deviations from manual rating of 0.69 and 0.45 years in these two studies for boys in the bone age range 17-19 years. For girls, the deviations were 0.75 and 0.59 years, respectively, in the bone age range 15-18 years. It is shown how the automated bone age method can be applied to infer the age probability distribution for healthy Caucasian European males. Considering a population with age 15.0-21.0 years, the method can be used to decide whether the subject is above 18 years with a false positive rate (children classified as adults) of 10 % (95% confidence interval = 7-13%) and a false negative rate of 30 % (adults classified as children). To apply this method in other ethnicities will require a study of the average of "bone age - age" at the end of puberty, i.e. how much this population is shifted relative to the Greulich-Pyle standard.

A new implementation of digital X-ray radiogrammetry and reference curves of four indices of cortical bone for healthy European adults

Digital X-ray radiogrammetry performs measurements on a hand radiograph in digital form. We present an improved implementation of the method and provide reference curves for four indices for the amount of bone. We collected 1662 hand radiographs of healthy subjects of age 9-100 years.

PURPOSE

The digital X-ray radiogrammetry (DXR) method has been shown to be efficient for diagnosis of osteoporosis and for assessment of progression of rheumatoid arthritis. The aim of this work is to present a new DXR implementation and reference curves of four indices of cortical bone and to compare their relative SDs in healthy subjects at fixed age and gender.

MATERIALS AND METHODS

A total of 1662 hand radiographs of healthy subjects of age 9-100 years were collected in Jena in 2001-2005. We also used a longitudinal study of 116 Danish children born in 1952 with on average 11 images taken over the age range 7 to 40 years. The new DXR method reconstructs the whole metacarpal contour so that the metacarpal lengths can be measured and used in two of the indices. The new DXR method automatically validates 97 % of the images and is implemented as a local server for PACS users.

RESULTS

The Danish bone health index (BHI) data are consistent with the Jena data and also with the published BHI reference for healthy children. BHI is found to have smaller relative SD than the other three indices in the Jena cohort over the age range 20-80 years.

CONCLUSION

The new DXR method is an extension of the existing BoneXpert method for children, which allows patients to be followed from childhood into adulthood with the same method. By making all four indices of cortical bone available within the same medical device, it becomes possible to decide which index has the best relation to fracture risk in future studies.

Maturation Disparity between Hand-Wrist Bones in a Chinese Sample of Normal Children: An Analysis Based on Automatic BoneXpert and Manual Greulich and Pyle Atlas Assessment

OBJECTIVE

To assess the maturation disparity of hand-wrist bones using the BoneXpert system and Greulich and Pyle (GP) atlas in a sample of normal children from China.

MATERIALS AND METHODS

Our study included 229 boys and 168 girls aged 2-14 years. The bones in the hand and wrist were divided into five groups: distal radius and ulna, metacarpals, proximal phalanges, middle phalanges and distal phalanges. Bone age (BA) was assessed separately using the automatic BoneXpert and GP atlas by two raters. Differences in the BA between the most advanced and retarded individual bones and bone groups were analyzed.

RESULTS

In 75.8% of children assessed with the BoneXpert and 59.4% of children assessed with the GP atlas, the BA difference between the most advanced and most retarded individual bones exceeded 2.0 years. The BA mean differences between the most advanced and most retarded individual bones were 2.58 and 2.25 years for the BoneXpert and GP atlas methods, respectively. Furthermore, for both methods, the middle phalanges were the most advanced group. The most retarded group was metacarpals for BoneXpert, while metacarpals and the distal radius and ulna were the most retarded groups according to the GP atlas. Overall, the BAs of the proximal and distal phalanges were closer to the chronological ages than those of the other bone groups.

CONCLUSION

Obvious and regular maturation disparities are common in normal children. Overall, the BAs of the proximal and distal phalanges are more useful for BA estimation than those of the other bone groups.

Modeling skeletal bone development with hidden Markov models

This paper presents a tool for automatic assessment of skeletal bone age according to a modified version of the Tanner and Whitehouse (TW2) clinical method. The tool is able to provide an accurate bone age assessment in the range 0-6 years by processing epiphysial/metaphysial ROIs with image-processing techniques, and assigning TW2 stage to each ROI by means of hidden Markov models. The system was evaluated on a set of 360 X-rays (180 for males and 180 for females) achieving a high success rate in bone age evaluation (mean error rate of 0.41±0.33 years comparable to human error) as well as outperforming other effective methods. The paper also describes the graphical user interface of the tool, which is also released, thus to support and speed up clinicians' practices when dealing with bone age assessment.

Automated radiogrammetry is a feasible method for measuring bone quality and bone maturation in severely disabled children

BACKGROUND

Children with severe neurological impairment and intellectual disability are prone to low bone quality and fractures.

OBJECTIVE

We studied the feasibility of automated radiogrammetry in assessing bone quality in this specific group of children. We measured outcome of bone quality and, because these children tend to have altered skeletal maturation, we also studied bone age.

MATERIALS AND METHODS

We used hand radiographs obtained in 95 children (mean age 11.4 years) presenting at outpatient paediatric clinics. We used BoneXpert software to determine bone quality, expressed as paediatric bone index and bone age.

RESULTS

Regarding feasibility, we successfully obtained a paediatric bone index in 60 children (63.2%). The results on bone quality showed a mean paediatric bone index standard deviation score of -1.85, significantly lower than that of healthy peers (P < 0.0001). Almost 50% of the children had severely diminished bone quality. In 64% of the children bone age diverged more than 1 year from chronological age. This mostly concerned delayed bone maturation.

CONCLUSION

Automated radiogrammetry is feasible for evaluating bone quality in children who have disabilities but not severe contractures. Bone quality in these children is severely diminished. Because bone maturation frequently deviated from chronological age, we recommend comparison to bone-age-related reference values.

Bone age: assessment methods and clinical applications

The main bone age assessment methods are the Greulich-Pyle and Tanner-Whitehouse 2 methods, both of which involve left hand and wrist radiographs. Several other bone age assessment methods have been developed, including ultrasonographic, computerized, and magnetic resonance (MR) imaging methods. The ultrasonographic method appears unreliable in children with delayed and advanced bone age. MR imaging is noninvasive; however, bone age assessment using MR imaging is relatively new, and further examinations are needed. An automated method for determining bone age, named BoneXpert, has been validated for Caucasian children with growth disorders and children of various ethnic groups. Sex hormones are necessary for bone growth and maturation in children with a bone age corresponding to normal pubertal age, and estrogen is essential for growth plate closure. Bone age is an effective indicator for diagnosing and treating various diseases. A new method for adult height prediction based on bone age has been developed using BoneXpert, in addition to the commonly used Bayley-Pinneau and Tanner-Whitehouse mark II methods. Furthermore, bone age may become a predictor for the timing of peak height velocity and menarche.

What automated age estimation of hand and wrist MRI data tells us about skeletal maturation in male adolescents

BACKGROUND

Age estimation of individuals is important in human biology and has various medical and forensic applications. Recent interest in MR-based methods aims to investigate alternatives for established methods involving ionising radiation. Automatic, software-based methods additionally promise improved estimation objectivity.

AIM

To investigate how informative automatically selected image features are regarding their ability to discriminate age, by exploring a recently proposed software-based age estimation method for MR images of the left hand and wrist.

SUBJECTS AND METHODS

One hundred and two MR datasets of left hand images are used to evaluate age estimation performance, consisting of bone and epiphyseal gap volume localisation, computation of one age regression model per bone mapping image features to age and fusion of individual bone age predictions to a final age estimate.

RESULTS

Quantitative results of the software-based method show an age estimation performance with a mean absolute difference of 0.85 years (SD = 0.58 years) to chronological age, as determined by a cross-validation experiment. Qualitatively, it is demonstrated how feature selection works and which image features of skeletal maturation are automatically chosen to model the non-linear regression function.

CONCLUSION

Feasibility of automatic age estimation based on MRI data is shown and selected image features are found to be informative for describing anatomical changes during physical maturation in male adolescents.

Automated Greulich-Pyle bone age determination in children with chronic kidney disease

BACKGROUND

Growth restriction and retarded bone age are common findings in children with chronic kidney disease (CKD). We compared the automated BoneXpert™ method with the manual assessment of an X-ray of the non-dominant hand.

METHODS

In this retrospective multicenter study, 359 patients with CKD stages 2-5, aged 2-14.5 (girls) or 2.5-17 years (boys) were included. Bone age was determined manually by three experts (according to Greulich and Pyle). Automated determination of bone age was performed using the image analysis software BoneXpert™.

RESULTS

There was a strong correlation between the automatic and the manual method (r = 0.983, p < 0.001). The automatic method tended to generate higher bone age values (0.64 ± 0.73 years) in the younger patients (4-5 years) and to underestimate retardation or acceleration of bone age. The so-called "bone health index" (BHI) was reduced in comparison to the reference population. Bone health index standard deviation score (BHI-SDS) was not related to the stage of CKD, but weakly negatively correlated with plasma PTH concentrations (r = 0.12, p = 0.019).

CONCLUSIONS

BoneXpert™ allows an objective, time-saving, and in general valid bone age assessment in children with CKD. Possible underestimation of retarded or accelerated bone age should be taken into account. Validation of the BHI needs further study.

Fully automatic bone age estimation from left hand MR images

There has recently been an increased demand in bone age estimation (BAE) of living individuals and human remains in legal medicine applications. A severe drawback of established BAE techniques based on X-ray images is radiation exposure, since many countries prohibit scanning involving ionizing radiation without diagnostic reasons. We propose a completely automated method for BAE based on volumetric hand MRI images. On our database of 56 male caucasian subjects between 13 and 19 years, we are able to estimate the subjects age with a mean difference of 0.85 ± 0.58 years compared to the chronological age, which is in line with radiologist results using established radiographic methods. We see this work as a promising first step towards a novel MRI based bone age estimation system, with the key benefits of lacking exposure to ionizing radiation and higher accuracy due to exploitation of volumetric data.

Hand X-ray in pediatric endocrinology: Skeletal age assessment and beyond

Skeletal age assessment (SAA) is a clinical procedure which is used in determining the SA of children and adolescents. Bone development is influenced by a number of factors, including nutrition, hormonal secretions, and genetics. There are several factors to be borne in mind when using methods of assessing skeletal maturity. These include: Variability among methods, degree of variability in the estimation of skeletal maturation, sources of low accuracy, and dispersion of the values of skeletal maturation. Currently, the main clinical methods for SAA are the Greulich and Pyle (GP) and Tanner and Whitehouse (TW) methods. The GP method has the advantage of being quick and easy to use. A well-trained radiologist takes few minutes to determine the bone age (BA) from a single hand radiograph. The method of TW, however, seems to be more reliable than the GP method. In recent years, the increasing speed in computer sciences and reduction of their cost has given the opportunity to create and use computerized BA estimation system. Despite the fact that the number of automated systems for BAA have increased, most are still within the experimental phase. The use of automated BA determination system, cleared for clinical use in Europe (BoneXpert), has been validated for various ethnicities and children with endocrine disorders. Ultrasound imaging has some limitations that include operator dependence, lower intra-rater and inter-rater reliability of assessment and difficulties with standardization of documentation and imaging transfer. Magnetic resonance imaging (MRI) is noninvasive alternative tool for SA assessment in children. However, few studies have been reported on this topic, and further research is needed to evaluate the reliability and validity of MRI BAAs. In conclusion, at present radiographic methods for the assessment of BA remain the gold standards. Whatever method one adopts, it is essential to minimize the causes of imprecision by taking care to consider the quality of the X-ray. Moreover, it is imperative to assume a correct hand positioning because poor positioning can change the appearance of some bones. It is also preferable to employ scoring methods to these techniques and percentiles rather than BA in years and months. In addition, the possible differences in maturation among different population should be kept in mind.

Automated determination of bone age and bone mineral density in patients with juvenile idiopathic arthritis: a feasibility study

Introduction

Chronic inflammation combined with glucocorticoid treatment and immobilization puts juvenile idiopathic arthritis (JIA) patients at risk of impaired growth and reduced bone mineral density (BMD). Conventional methods for evaluating bone age and BMD are time-consuming or come with additional costs and radiation exposure. In addition, an automated measurement of bone age and BMD is likely to be more consistent than visual evaluation. In this study, we aimed to evaluate the feasibility of an automated method for determination of bone age and (cortical) bone mineral density (cBMD) in severely affected JIA patients. A secondary objective was to describe bone age and cBMD in this specific JIA population eligible for biologic treatment.

Methods

In total, 69 patients with standard hand radiographs at the start of etanercept treatment and of calendar age within the reliability ranges (2.5 to 17 years for boys and 2 to 15 years for girls) were extracted from the Dutch Arthritis and Biologicals in Children register. Radiographs were analyzed using the BoneXpert method, thus automatically determining bone age and cBMD expressed as bone health index (BHI). Agreement between measurements of the left- and right-hand radiographs and a repeated measurement of the left hand were assessed with the intraclass correlation coefficient (ICC). Regression analysis was used to identify variables associated with Z-scores of bone age and BHI.

Results

The BoneXpert method was reliable in the evaluation of radiographs of 67 patients (radiographs of 2 patients were rejected because of poor image quality). Agreement between left- and right-hand radiographs (ICC = 0.838 to 0.996) and repeated measurements (ICC = 0.999 to 1.000) was good. Mean Z-scores of bone age (−0.36, P = 0.051) and BHI (−0.85, P < 0.001) were lower compared to the healthy population. Glucocorticoid use was associated with delayed bone age (0.79 standard deviation (SD), P = 0.028), and male gender was associated with a lower Z-score of BHI (0.65 SD, P = 0.021).

Conclusions

BoneXpert is an easy-to-use method for assessing bone age and cBMD in patients with JIA, provided that radiographs are of reasonable quality and patients’ bone age lies within the age ranges of the program. The population investigated had delayed bone maturation and lower cBMD than healthy children.

Electronic supplementary material

The online version of this article (doi:10.1186/s13075-014-0424-1) contains supplementary material, which is available to authorized users.

Impact of ensemble learning in the assessment of skeletal maturity

The assessment of the bone age, or skeletal maturity, is an important task in pediatrics that measures the degree of maturation of children's bones. Nowadays, there is no standard clinical procedure for assessing bone age and the most widely used approaches are the Greulich and Pyle and the Tanner and Whitehouse methods. Computer methods have been proposed to automatize the process; however, there is a lack of exploration about how to combine the features of the different parts of the hand, and how to take advantage of ensemble techniques for this purpose. This paper presents a study where the use of ensemble techniques for improving bone age assessment is evaluated. A new computer method was developed that extracts descriptors for each joint of each finger, which are then combined using different ensemble schemes for obtaining a final bone age value. Three popular ensemble schemes are explored in this study: bagging, stacking and voting. Best results were achieved by bagging with a rule-based regression (M5P), scoring a mean absolute error of 10.16 months. Results show that ensemble techniques improve the prediction performance of most of the evaluated regression algorithms, always achieving best or comparable to best results. Therefore, the success of the ensemble methods allow us to conclude that their use may improve computer-based bone age assessment, offering a scalable option for utilizing multiple regions of interest and combining their output.

Role of growth hormone in enchondroplasia and chondral osteogenesis: evaluation by X-ray of the hand

BACKGROUND

The process of growth and maturation of long (radius and ulna) and short (metacarpals and phalanges) bones of the hand (enchondroplasia) differs from that of the carpal cuboid bones (chondral osteogenesis). This study aimed to assess the impact of growth hormone (GH) on these two processes of bone maturation.

METHODS

Subjects of the study were 95 prepubertal children: 30 children with GH deficiency and 65 children with idiopathic short stature, aged 7.4 ± 1.9 y (mean ± SD) (trial registration number 98-0198-033). Bone maturation was assessed by the Greulich and Pyle method from X-rays obtained at the start and at 1 and 2 y of GH treatment, separately for carpals, long bones, and short bones, and was expressed as years of delay relative to chronological age.

RESULTS

At GH start, the delay in bone maturation in the GH-deficient group was significantly greater for carpals (3.6 ± 1.3 y) than for long (3.0 ± 1.3 y) and short (1.7 ± 1.1 y) bones. The delay was nonsignificantly greater for carpal bones in GH-deficient subjects than in subjects with idiopathic short stature (3.6 ± 1.3 vs. 3.1 ± 1.1 y, respectively) and was normalized after 2 y of GH treatment.

CONCLUSION

The dominant effect of GH was on chondral osteogenesis, with milder effect on enchondroplasia. A distinct delay in carpal and long-bone maturation, which normalizes during 2 y of GH treatment, was typical in GH-deficient children. Therefore, separate carpal bone assessment in bone age reading is needed.

Bone age assessment methods: a critical review

The bone age of a child indicates his/her level of biological and structural maturity better than the chronological age calculated from the date of birth. Radiography of the hand & wrist is the commonest modality used to calculate bone age. Automated methods for evaluation of hand and wrist radiographs are also being developed which reduce inter rater variability compared to manual methods. Non radiation based techniques of visualizing hand & wrist bones such as ultrasonography for bone age calculation have been theorized but are not as accurate as radiographic methods. By the age of 18 years, bone age cannot be computed from hand & wrist radiographs, therefore the medial end of the clavicle is used for bone age calculation in individuals aged 18—22 years. CT visualization of the clavicle has been extensively studied but requires a high dose of radiation. MRI based methods are being developed but require more research. Dental age is an alternate form of bone age determination, which also gives an estimate of skeletal maturity. The iliac bone and femoral head have also been studied for computation of bone age but no standardized methods have yet been generated.

As different modalities of bone age estimation provide different results and their applicability differs in different ethnicities, we need to design studies in order to compare them and select the method best suited to Pakistani children.

Sources of Data/Study Selection: Recent articles published between years 2004-2013 obtained from online search engines Pubmed and Google Scholar were used in preparation of this review.

Towards automatic bone age estimation from MRI: localization of 3D anatomical landmarks

Bone age estimation (BAE) is an important procedure in forensic practice which recently has seen a shift in attention from X-ray to MRI based imaging. To automate BAE from MRI, localization of the joints between hand bones is a crucial first step, which is challenging due to anatomical variations, different poses and repeating structures within the hand. We propose a landmark localization algorithm using multiple random regression forests, first analyzing the shape of the hand from information of the whole image, thus implicitly modeling the global landmark configuration, followed by a refinement based on more local information to increase prediction accuracy. We are able to clearly outperform related approaches on our dataset of 60 T1-weighted MR images, achieving a mean landmark localization error of 1.4 ± 1.5mm, while having only 0.25% outliers with an error greater than 10mm.

Automated bone age assessment: motivation, taxonomies, and challenges

Bone age assessment (BAA) of unknown people is one of the most important topics in clinical procedure for evaluation of biological maturity of children. BAA is performed usually by comparing an X-ray of left hand wrist with an atlas of known sample bones. Recently, BAA has gained remarkable ground from academia and medicine. Manual methods of BAA are time-consuming and prone to observer variability. This is a motivation for developing automated methods of BAA. However, there is considerable research on the automated assessment, much of which are still in the experimental stage. This survey provides taxonomy of automated BAA approaches and discusses the challenges. Finally, we present suggestions for future research.

Validation of automatic bone age determination in children with congenital adrenal hyperplasia

BACKGROUND

Determination of bone age is routinely used for following up substitution therapy in congenital adrenal hyperplasia (CAH) but today is a procedure with significant subjectivity.

OBJECTIVE

The aim was to test the performance of automatic bone age rating by the BoneXpert software package in all radiographs of children with CAH seen at our clinic from 1975 to 2006.

MATERIALS AND METHODS

Eight hundred and ninety-two left-hand radiographs from 100 children aged 0 to 17 years were presented to a human rater and BoneXpert for bone age rating. Images where ratings differed by more than 1.5 years were each rerated by four human raters.

RESULTS

Rerating was necessary in 20 images and the rerating result was closer to the BoneXpert result than to the original manual rating in 18/20 (90 %). Bone age rating precision based on the smoothness of longitudinal curves comprising a total of 327 data triplets spanning less than 1.7 years showed BoneXpert to be more precise (P<0.001).

CONCLUSION

BoneXpert performs reliable bone age ratings in children with CAH.

Bone age assessment: automated techniques coming of age?

Bone age determination from hand radiographs is one of the oldest radiographic procedures. The first atlas was published by Poland in 1898, and to date the Greulich Pyle atlas, although it dates from 1959, is still the most commonly used method. Bone age rating is time-consuming, suffers from an unsatisfactorily high rater variability, and therefore already 25 years ago it was proposed to replace the manual rating by an automated, computerized method, a field nowadays referred to as computer-aided diagnosis (CAD). The pursuit of this goal reached a first stage of accomplishment in 1992-1996 with the presentation of several systems. However, they had limited clinical value, and efforts in CAD research were increasingly focused on lesion detection for cancer screening. It was only in 2008 that a fully-automated bone age method was presented, which appears to be clinically acceptable. In this paper we consider the requirements that should be met by an automated bone age method and review the state of the art. Integration in PACS and saving time are important factors for radiologists. But it is the validation of the methods which poses the greatest challenge, because there is no gold standard for bone age rating, and the direct comparison to manual rating is therefore not sufficient for demonstrating that manual rating can be replaced by automated rating. One needs additional studies assessing the precision of a method and its accuracy when used for adult height prediction, which serves as an objective.

Automated determination of bone age in a modern chinese population

Rationale and Objective. Large studies have previously been performed to set up a Chinese bone age reference, but it has been difficult to compare the maturation of Chinese children with populations elsewhere due to the potential variability between raters in different parts of the world. We re-analysed the radiographs from a large study of normal Chinese children using an automated bone age rating method to establish a Chinese bone age reference, and to compare the tempo of maturation in the Chinese with other populations. Materials and Methods. X-rays from 2883 boys and 3143 girls aged 2–20 years from five Chinese cities, taken in 2005, were evaluated using the BoneXpert automated method. Results. Chinese children reached full maturity at the same age as previously studied Asian children from Los Angeles, but 0.6 years earlier than Caucasian children in Los Angeles. The Greulich-Pyle bone age method was adapted to the Chinese population creating a new bone age scale BX-China05. The standard deviation between BX-China05 and chronologic age was 1.01 years in boys aged 8–14, and 1.08 years in girls aged 7–12. Conclusion. By eliminating rater variability, the automated method provides a reliable and efficient standard for bone age determination in China.

Support vector machine classification based on correlation prototypes applied to bone age assessment

Bone age assessment (BAA) on hand radiographs is a frequent and time consuming task in radiology. We present a method for (semi)automatic BAA which is done in several steps: (i) extract 14 epiphyseal regions from the radiographs, (ii) for each region, retain image features using the IRMA framework, (iii) use these features to build a classifier model (training phase), (iv) evaluate performance on cross validation schemes (testing phase), (v) classify unknown hand images (application phase). In this paper, we combine a support vector machine (SVM) with cross-correlation to a prototype image for each class. These prototypes are obtained choosing one random hand per class. A systematic evaluation is presented comparing nominal- and real-valued SVM with k nearest neighbor (kNN) classification on 1,097 hand radiographs of 30 diagnostic classes (0 19 years). Mean error in age prediction is 1.0 and 0.83 years for 5-NN and SVM, respectively. Accuracy of nominal- and real-valued SVM based on 6 prominent regions (prototypes) is 91.57% and 96.16%, respectively, for accepting about two years age range.

Generic integration of content-based image retrieval in computer-aided diagnosis

Content-based image retrieval (CBIR) offers approved benefits for computer-aided diagnosis (CAD), but is still not well established in radiological routine yet. An essential factor is the integration gap between CBIR systems and clinical information systems. The international initiative Integrating the Healthcare Enterprise (IHE) aims at improving interoperability of medical computer systems. We took into account deficiencies in IHE compliance of current picture archiving and communication systems (PACS), and developed an intermediate integration scheme based on the IHE post-processing workflow integration profile (PWF) adapted to CBIR in CAD. The Image Retrieval in Medical Applications (IRMA) framework was used to apply our integration scheme exemplarily, resulting in the application called IRMAcon. The novel IRMAcon scheme provides a generic, convenient and reliable integration of CBIR systems into clinical systems and workflows. Based on the IHE PWF and designed to grow at a pace with the IHE compliance of the particular PACS, it provides sustainability and fosters CBIR in CAD.

ON THE SEGMENTATION AND CLASSIFICATION OF HAND RADIOGRAPHS

This research is part of a wider project to build predictive models of bone age using hand radiograph images. We examine ways of finding the outline of a hand from an X-ray as the first stage in segmenting the image into constituent bones. We assess a variety of algorithms including contouring, which has not previously been used in this context. We introduce a novel ensemble algorithm for combining outlines using two voting schemes, a likelihood ratio test and dynamic time warping (DTW). Our goal is to minimize the human intervention required, hence we investigate alternative ways of training a classifier to determine whether an outline is in fact correct or not. We evaluate outlining and classification on a set of 1370 images. We conclude that ensembling with DTW improves performance of all outlining algorithms, that the contouring algorithm used with the DTW ensemble performs the best of those assessed, and that the most effective classifier of hand outlines assessed is a random forest applied to outlines transformed into principal components.

Comparison of radiogrammetrical metacarpal indices in children and reference data from the First Zurich Longitudinal Study

BACKGROUND

A number of radiogrammetrical metacarpal indices are in use, some of which have been adapted for children.

OBJECTIVE

The purpose of this study was to compare four known indices-bone mineral density (BMD), relative cortical area, Exton-Smith index, bending breaking resistance index-and the more recently defined pediatric bone index (PBI) according to the two criteria of minimum height dependence and minimum variability in children of equal bone age.

MATERIALS AND METHODS

A total of 3,121 left-hand radiographs from 231 healthy Caucasian children ranging in age from 3 to 19 years old were analysed using BoneXpert®, a programme for automatic analysis of hand radiographs and assessment of bone age.

RESULTS

Dependence on height for chronological age or bone age and the mean relative standard deviation were lowest in the PBI for both genders pooled. The differences in height dependence were statistically significant and are shown to be clinically relevant. Reference data for PBI are presented.

CONCLUSION

PBI may be a better indicator than BMD for bone health in children; however, verification in a clinical group is needed.

The paediatric wrist revisited--findings of bony depressions in healthy children on radiographs compared to MRI

BACKGROUND

The presence of erosions is used for diagnosis and monitoring of disease activity in juvenile idiopathic arthritis (JIA). Assessment of carpal bone erosions in children is challenging due to lack of normal references.

OBJECTIVE

To define normal appearances of bony depressions in the wrist on radiographs and MRI.

MATERIALS AND METHODS

MRI and radiography of the wrist were performed in 88 healthy children, 5-15 years of age. We assessed the number of bony depressions within the carpals/proximal metacarpals on both modalities, separately and combined.

RESULTS

A total of 75 carpal depressions were identified on radiography compared to 715 on MRI. The number of bony depressions identified radiographically showed no statistically significant difference across age-groups. Within the metacarpals, there was no significant difference between bony depressions identified by MRI or radiography, except at the bases of the second metacarpal.

CONCLUSION

Bony depressions that resemble erosions are normal findings in the wrist in children. MRI identifies more depressions than radiographs in the carpus. Some bony depressions occur at typical locations and should be accounted for when assessing the wrist in JIA to avoid overstaging.

Bone age in the 21st century: is Greulich and Pyle's atlas accurate for Israeli children?

BACKGROUND

The applicability today of Greulich and Pyle's Radiographic Atlas of Skeletal Development of the Hand and Wrist (G&P) is uncertain.

OBJECTIVE

The purpose of this study was to determine whether G&P is accurate in Israeli children today.

MATERIALS AND METHODS

Left-hand radiographs of 679 children (375 boys) ranging in age from 1 day to 18 years old were obtained for trauma in the period 2001-2009 and were evaluated for bone age according to G&P. Individual bone age was plotted against calendar age and smoothed to obtain the association between calendar age and bone age. Any difference was assessed with Wilcoxon signed-rank test.

RESULTS

In girls, there was no significant difference between bone age and calendar age (P = 0.188). G&P underestimated bone age in boys <15 years old (median difference, 2.3 months; P < 0.0001) and overestimated bone age in boys ≥15 years old (median difference, 2.9 months; P = 0.0043). The largest median difference (5.4 months; P = 0.0003) was seen in boys 6-10 years old.

CONCLUSION

The differences between calendar age and bone age according to G&P were relatively small compared with normal variance and are unlikely to be of clinical importance.

Computer-aided diagnosis: how to move from the laboratory to the clinic

Computer-aided diagnosis (CAD), encompassing computer-aided detection and quantification, is an established and rapidly growing field of research. In daily practice, however, most radiologists do not yet use CAD routinely. This article discusses how to move CAD from the laboratory to the clinic. The authors review the principles of CAD for lesion detection and for quantification and illustrate the state-of-the-art with various examples. The requirements that radiologists have for CAD are discussed: sufficient performance, no increase in reading time, seamless workflow integration, regulatory approval, and cost efficiency. Performance is still the major bottleneck for many CAD systems. Novel ways of using CAD, extending the traditional paradigm of displaying markers for a second look, may be the key to using the technology effectively. The most promising strategy to improve CAD is the creation of publicly available databases for training and validation. This can identify the most fruitful new research directions, and provide a platform to combine multiple approaches for a single task to create superior algorithms.

A semi-automated method for bone age assessment using cervical vertebral maturation

OBJECTIVE

To propose a semi-automated method for pattern classification to predict individuals' stage of growth based on morphologic characteristics that are described in the modified cervical vertebral maturation (CVM) method of Baccetti et al.

MATERIALS AND METHODS

A total of 188 lateral cephalograms were collected, digitized, evaluated manually, and grouped into cervical stages by two expert examiners. Landmarks were located on each image and measured. Three pattern classifiers based on the Naïve Bayes algorithm were built and assessed using a software program. The classifier with the greatest accuracy according to the weighted kappa test was considered best.

RESULTS

The classifier showed a weighted kappa coefficient of 0.861 ± 0.020. If an adjacent estimated pre-stage or poststage value was taken to be acceptable, the classifier would show a weighted kappa coefficient of 0.992 ± 0.019.

CONCLUSION

Results from this study show that the proposed semi-automated pattern classification method can help orthodontists identify the stage of CVM. However, additional studies are needed before this semi-automated classification method for CVM assessment can be implemented in clinical practice.

Towards case-based medical learning in radiological decision making using content-based image retrieval

BACKGROUND

Radiologists' training is based on intensive practice and can be improved with the use of diagnostic training systems. However, existing systems typically require laboriously prepared training cases and lack integration into the clinical environment with a proper learning scenario. Consequently, diagnostic training systems advancing decision-making skills are not well established in radiological education.

METHODS

We investigated didactic concepts and appraised methods appropriate to the radiology domain, as follows: (i) Adult learning theories stress the importance of work-related practice gained in a team of problem-solvers; (ii) Case-based reasoning (CBR) parallels the human problem-solving process; (iii) Content-based image retrieval (CBIR) can be useful for computer-aided diagnosis (CAD). To overcome the known drawbacks of existing learning systems, we developed the concept of image-based case retrieval for radiological education (IBCR-RE). The IBCR-RE diagnostic training is embedded into a didactic framework based on the Seven Jump approach, which is well established in problem-based learning (PBL). In order to provide a learning environment that is as similar as possible to radiological practice, we have analysed the radiological workflow and environment.

RESULTS

We mapped the IBCR-RE diagnostic training approach into the Image Retrieval in Medical Applications (IRMA) framework, resulting in the proposed concept of the IRMAdiag training application. IRMAdiag makes use of the modular structure of IRMA and comprises (i) the IRMA core, i.e., the IRMA CBIR engine; and (ii) the IRMAcon viewer. We propose embedding IRMAdiag into hospital information technology (IT) infrastructure using the standard protocols Digital Imaging and Communications in Medicine (DICOM) and Health Level Seven (HL7). Furthermore, we present a case description and a scheme of planned evaluations to comprehensively assess the system.

CONCLUSIONS

The IBCR-RE paradigm incorporates a novel combination of essential aspects of diagnostic learning in radiology: (i) Provision of work-relevant experiences in a training environment integrated into the radiologist's working context; (ii) Up-to-date training cases that do not require cumbersome preparation because they are provided by routinely generated electronic medical records; (iii) Support of the way adults learn while remaining suitable for the patient- and problem-oriented nature of medicine. Future work will address unanswered questions to complete the implementation of the IRMAdiag trainer.

Prototypes for content-based image retrieval in clinical practice

Content-based image retrieval (CBIR) has been proposed as key technology for computer-aided diagnostics (CAD). This paper reviews the state of the art and future challenges in CBIR for CAD applied to clinical practice.We define applicability to clinical practice by having recently demonstrated the CBIR system on one of the CAD demonstration workshops held at international conferences, such as SPIE Medical Imaging, CARS, SIIM, RSNA, and IEEE ISBI. From 2009 to 2011, the programs of CADdemo@CARS and the CAD Demonstration Workshop at SPIE Medical Imaging were sought for the key word "retrieval" in the title. The systems identified were analyzed and compared according to the hierarchy of gaps for CBIR systems.In total, 70 software demonstrations were analyzed. 5 systems were identified meeting the criterions. The fields of application are (i) bone age assessment, (ii) bone fractures, (iii) interstitial lung diseases, and (iv) mammography. Bridging the particular gaps of semantics, feature extraction, feature structure, and evaluation have been addressed most frequently.In specific application domains, CBIR technology is available for clinical practice. While system development has mainly focused on bridging content and feature gaps, performance and usability have become increasingly important. The evaluation must be based on a larger set of reference data, and workflow integration must be achieved before CBIR-CAD is really established in clinical practice.