MSADCN:Multi-Scale Attentional Densely Connected Network for Automated Bone Age Assessment

Bone age assessment(BAA)helps doctors determine how a child’s bones grow and develop in clinical medicine.Traditional BAA methods rely on clinician expertise,leading to time-consuming predictions and inaccurate results.Most deep learning-based BAA methods feed the extracted critical points of images into the network by providing additional annotations.This operation is costly and subjective.To address these problems,we propose a multi-scale attentional densely connected network(MSADCN)in this paper.MSADCN constructs a multi-scale dense connectivity mechanism,which can avoid overfitting,obtain the local features effectively and prevent gradient vanishing even in limited training data.First,MSADCN designs multi-scale structures in the densely connected network to extract fine-grained features at different scales.Then,coordinate attention is embedded to focus on critical features and automatically locate the regions of interest(ROI)without additional annotation.In addition,to improve the model’s generalization,transfer learning is applied to train the proposed MSADCN on the public dataset IMDB-WIKI,and the obtained pre-trained weights are loaded onto the Radiological Society of North America(RSNA)dataset.Finally,label distribution learning(LDL)and expectation regression techniques are introduced into our model to exploit the correlation between hand bone images of different ages,which can obtain stable age estimates.Extensive experiments confirm that our model can converge more efficiently and obtain a mean absolute error(MAE)of 4.64 months,outperforming some state-of-the-art BAA methods.

Anti-Interference Study on Radiographic Bone Age Estimation Based on Artificial Intelligence Model

In this paper, the interferences of X-ray image noise on a bone age model, Xception model, were studied. We conduct a comparative experiment test according to the output performance of the neural network model using both the original image training and noise-added (Gaussian noise plus salt-pepper noise) training, and analyze the anti-interference ability of the Xception model, hoping to improve it through noise enhancement training and generalize the application ability of the model. The results show that the model trained with noise-added (Gaussian noise plussalt-pepper noise) images can make predictions that are more robust and less affected by the image disturbances, such as image noise.

Metaheuristic with Deep Learning Enabled Biomedical Bone Age Assessment and Classification Model

The skeletal bone age assessment(BAA)was extremely implemented in development prediction and auxiliary analysis of medicinal issues.X-ray images of hands were detected from the estimation of bone age,whereas the ossification centers of epiphysis and carpal bones are important regions.The typical skeletal BAA approaches remove these regions for predicting the bone age,however,few of them attain suitable efficacy or accuracy.Automatic BAA techniques with deep learning(DL)methods are reached the leading efficiency on manual and typical approaches.Therefore,this study introduces an intellectual skeletal bone age assessment and classification with the use of metaheuristic with deep learning(ISBAAC-MDL)model.The presented ISBAAC-MDL technique majorly focuses on the identification of bone age prediction and classification process.To attain this,the presented ISBAAC-MDL model derives a mask Region-related Convolutional Neural Network(Mask-RCNN)with MobileNet as baseline model to extract features.Followed by,the whale optimization algorithm(WOA)is implemented for hyperparameter tuning of the MobileNet method.At last,Deep Feed-Forward Module(DFFM)based age prediction and Radial Basis Function Neural Network(RBFNN)based stage classification approach is utilized.The experimental evaluation of the ISBAAC-MDL model is tested using benchmark dataset and the outcomes are assessed over distinct factors.The experimental outcomes reported the better performances of the ISBAACMDL model over recent approaches with maximum accuracy of 0.9920.

Computerized geometric features of carpal bone for bone age estimation

Background Bone age development is one of the significant indicators depicting the growth status of children. However, bone age assessment is an heuristic and tedious work for pediatricians. We developed a computerized bone age estimation system based on the analysis of geometric features of carpal bones. Methods The geometric features of carpals were extracted and analyzed to judge the bone age of children by computerized shape and area description. Four classifiers, linear, nearest neighbor, back-propagation neural network, and radial basis function neural network, were adopted to categorize bone age. Principal component and discriminate analyses were employed to improve assorting accuracy. Results The hand X-ray films of 465 boys and 444 girls served as our database. The features were extracted from carpal bone images, including shape, area, and sequence. The proposed normalization area ratio method was effective in bone age classification by simulation. Besides, features statistics showed similar results between the standard of the Greulich and Pyle atlas and our database. Conclusions The bone area has a higher discriminating power to judge bone age. The ossification sequence of trapezium and trapezoid bones between Taiwan Residents and the atlas of the GP method is quite different. These results also indicate that carpal bone assessment with classification of neural networks can be correct and practical.

Bone Density and Mechanical Properties in Femoral Bone of Swim Loaded Aged Mice

Effects of swirnming on bone density and mechanical properties of femur were investigated in aged male and female mice. R/1 strain of senescence accelerated mouse (SAM) at eleven months old was used. Two groups of males and two groups of females each consisting of 7 mice were used. One male and one female groups were loaded with a swim regiment of 40 min a day, 5 days a week for 6 consecutive weeks. The remaining groups were used as the controls. All mice were fed with the standard diet and water ad libitum during the experiments.The results of this study indicated that (i) the hady weight was significantly (P<0.05) lower in the swimming groups than in the control groups in boh sexes. (ii) The bone density was significantly higher (P <0.05) in the swimming groups than in the control groups in boh sexes. However, there was no sighficant difference in cortical thickness index. (iii) In the mechanical properties of bone, there were no significant differences in the level of the maximum breaking force, the ultimate stress and the deformation between the swimndng and the contro groups in beth sexes. However, the elasticity of the bone of the female hoce in the swimming group was significantly higher (P<0.05) than that of the control group.These results suggest that regimented swimming for the aged mice might suppress age-associated bone loss, and the effect of exercise in the females is greater that in the males.

Effects of different doses of long-acting growth hormone in treating children with growth hormone deficiency

BACKGROUND With the improvement of economy and living standards,the attention paid to short stature in children has been increasingly highlighted.Numerous causes can lead to short stature in children,among which growth hormone deficiency(GHD)is a significant factor.AIM To investigate the long-term efficacy and safety of different doses of long-acting polyethylene glycol recombinant human growth hormone(PEG-rhGH)in the treatment of GHD in children.METHODS We selected 44 pediatric patients diagnosed with GHD who were treated at Wuhu First People's Hospital from 2014 to 2018.Total 23 patients were administered a high dose of long-acting PEG-rhGH at 0.2 mg/kg subcutaneously each week,forming the high-dose group.Meanwhile,21 patients were given a lower dose of long-acting PEG-rhGH at 0.14 mg/kg subcutaneously each week,establishing the low-dose Group.The total treatment period was 2 years,during which we monitored the patients’height,annual growth velocity(GV),height standard deviation score(HtSDS),chronological age(CA),bone age(BA),and serum levels of insulin-like growth factor-1(IGF-1)and insulin-like growth factor-binding protein-3(IGFBP-3)before treatment and at 6 mo,1 year,and 2 years after treatment initiation.We also monitored thyroid function,fasting plasma glucose,fasting insulin,and other side effects.Furthermore,we calculated the homeostatic model assessment for insulin resistance.RESULTS After 1 year of treatment,the GV,HtSDS,IGF-1,BA,and IGFBP-3 in both groups significantly improved compared to the pre-treatment levels(P<0.05).Moreover,when comparing GV,HtSDS,IGF-1,BA,and IGFBP-3 between the two groups,there were no statistically significant differences either before or after the treatment(P>0.05).During the treatment intervals of 0-1.0 years and 1.0-2.0 years,both patient groups experienced a slowdown in GV and a decline in HtSDS improvement(P<0.05).CONCLUSION The use of PEG-rhGH in treating GHD patients was confirmed to be effective,with similar outcomes observed in both the high-dose group and low-dose groups,and no significant differences in the main side effects.

Nanomechanical Characterization of Bone Quality Depending on Tissue Age via Bimodal Atomic Force Microscopy

Characterization of bone quality during the healing process is crucial for successful implantation procedures and patient comfort.In this study,a bone implant specimen that underwent a 4-week healing period was investigated.Bimodal atomic force microscopy(AFM)was employed to simultaneously obtain the morphology and elastic modulus maps of the newly formed and pre-existing bone regions within the sample.Results indicate that the new bone matrix possessed lower miner-alization levels and presented larger,uneven mineral grains,exhibiting the attributes of a woven bone.On the other hand,the old bone matrix exhibited a more uniform and mineralized structure,which is characteristic of lamellar bones.The new bone had a lower overall elastic modulus than the old bone.Bimodal AFM further confrmed that the new bone displayed three regions comprising unmineralized,partially mineralized,and fully matured sections,which indicate a turbulent change in its composition.Meanwhile,the old bone exhibited two sections comprising partially mineralized and matured bone parts,which denote the fnal phase of mineralization.This study provides valuable insights into the morphological and nanome-chanical diferences between the old and new bone matrixes and presents a novel approach to investigate bone quality at diferent phases of the bone-healing process.

Short stature associated with a novel mutation in the aggrecan gene:A case report and literature review

BACKGROUND Mutations in the aggrecan(ACAN)gene are identified in patients with:spondyloepiphyseal dysplasia,Kimberley type;short stature with advanced bone age(BA);in the presence or absence of heterozygous ACAN mutation-induced early-onset osteoarthritis and/or osteochondritis dissecans;and spondyloepimetaphyseal dysplasia,ACAN type.Heterozygous mutations contribute to spondyloepiphyseal dysplasia,Kimberley type(MIM#608361),which is a milder skeletal dysplasia.In contrast,homozygous mutations cause a critical skeletal dysplasia,which is called spondyloepimetaphyseal dysplasia,ACAN type(MIM#612813).Lately,investigations on exome and genome sequencing have shown that ACAN mutations can also lead to idiopathic short stature with or without an advanced BA,in the presence or absence of early-onset osteoarthritis and/or osteochondritis dissecans(MIM#165800).We herein reported a heterozygous defect of ACAN in a family with autosomal dominant short stature,BA acceleration,and premature growth cessation.CASE SUMMARY A 2-year-old male patient visited us due to growth retardation.The patient presented symmetrical short stature(height 79 cm,<-2 SD)without facial features and other congenital abnormalities.Whole-exome sequencing revealed a heterozygous pathogenic variant c.871C>T(p.Gln291*)of ACAN,which was not yet reported in cases of short stature.This mutation was also detected in his father and paternal grandmother.According to the Human Gene Mutation Database,67 ACAN mutations are registered.Most of these mutations are genetically inheritable,and very few children with short stature are associated with ACAN mutations.To date,heterozygous ACAN mutations have been reported in approximately 40 families worldwide,including a few individuals with a decelerated BA.CONCLUSION Heterozygous c.871C>T(p.Gln291*)variation of the ACAN gene was the disease-causing variant in this family.Collectively,our newly discovered mutation expanded the spectrum of ACAN gene mutations.

THE ANIMAL BONES FROM A FURTHER GROUP OF EARLY BRONZE AGE PITS AT OSTIANO, S. SALVATORE (Cremona)

The faunal remains from a group of pits excavated at Ostiano, S. Salvatore (Cremona- Northern Italy) are represented by bones of cattle, sheep/goat, pig and hare. Together with the archaeo-botanical and archaeological data, they reveal a well balanced, mixed subsistence strategy, combiningcereal agriculture and stock raising, adapted to the geographical and environmental location of this EarlyBronze Age settlement. I resti faunistici di un altro gruppo di pozzetti del sito del Bronzo antico di Ostiano,S. Salvatore (Cremona). I reperti faunistici di Ostiano, S. Salvatore sono rappresentati da resti di bovini,capra/pecora, maiale e lepre. Unitamente ai reperti archeobotanici ed archeologici, questi docmnentanouna strategia di sussistenza ben bilanciata fra allevamento ed agricoltura che concorda con la localizza-zione geografico-ambientale del sito dell’età del Bronzo antica.