Objective To explore a deep learning-based automatic bone age estimation model for elbow joint X-ray images of Chinese Han adolescents and children and evaluate its performance.Methods A total of 943(517 males and 426 females)elbow joint frontal view X-ray images of Chinese Han ado-lescents and children aged 6.00 to<16.00 years were collected from East,South,Central and North-west China.Three experimental schemes were adopted for bone age estimation.Scheme 1:Directly in-put preprocessed images into the regression model;Scheme 2:Train a segmentation network using"key elbow joint bone annotations"as labels,then input segmented images into the regression model;Scheme 3:Train a segmentation network using"full elbow joint bone annotations"as labels,then in-put segmented images into the regression model.For segmentation,the optimal model was selected from U-Net,UNet++and TransUNet.For regression,VGG16,VGG19,InceptionV2,InceptionV3,ResNet34,ResNet50,ResNet101 and DenseNet121 models were selected for bone age estimation.The dataset was randomly split into 80%(754 samples)for training and validation for model fitting and hyperparameter tuning,and 20%(189 samples)as an internal test set to test the performance of the trained model.An additional 104 elbow joint X-ray images from the same demographic and age group were col-lected and used as an external test set.Model performance was evaluated by comparing the mean ab-solute error(MAE),root mean square error(RMSE),accuracies within±0.7 years(P±0.7 years)and±1.0 years(P±1.0 years)between the estimated age and the actual age,and by drawing radar charts,scat-ter plots,and heatmaps.Results When segmented with Scheme 3,the UNet++model achieved good segmentation performance with a segmentation loss of 0.000 4 and an accuracy of 93.8%at a learning rate of 0.000 1.In the internal test set,the DenseNet121 model with Scheme 3 yielded the best results with MAE,P±0.7 years and P±1.0 years being 0.83 years,70.03%,and 84.30%,respectively.In the external test set,the DenseNet121 model with Scheme 3 also performed best,with an average MAE of 0.89 years and an average RMSE of 1.00 years.Conclusion When performing automatic bone age estima-tion using elbow joint X-ray images in Chinese Han adolescents and children,it is recommended to use the UNet++model for segmentation.The DenseNet121 model with Scheme 3 achieves optimal per-formance.Using segmentation networks,especially that trained with annotation areas encompassing the full elbow joint including the distal humerus,proximal radius,and proximal ulna,can improve the ac-curacy of bone age estimation based on elbow joint X-ray images.

Objective To explore a deep learning network model suitable for bone age estimation using shoulder joint X-ray images in Chinese Han adolescents.Methods A retrospective collection of 1 286 shoulder joint X-ray images of Chinese Han adolescents aged 12.0 to<18.0 years(708 males and 578 females)was conducted.Using random sampling,approximately 80%of the samples(1 032 cases)were selected as the training and validation sets for model learning,selection and optimization,and the other 20%samples(254 cases)were used as the test set to evaluate the model's generalization ability.The original single-channel shoulder joint X-ray images and dual-channel inputs combining original images with segmentation labels(manually annotated shoulder joint regions multiplied pixel-by-pixel with original images,followed by segmentation via the U-Net++network to retain only key shoulder joint region information)were respectively input into four network models,namely VGG16,ResNet18,ResNet50 and DenseNet121 for bone age estimation.Additionally,manual bone age estimation was con-ducted on the test set data,and the results were compared with the four network models.The mean absolute error(MAE),root mean square error(RMSE),coefficient of determination(R2),and Pear-son correlation coefficient(PCC)were used as main evaluation indicators.Results In the test set,the bone age estimation results of the four models with dual-channel input of shoulder joint X-ray images outperformed those with single-channel input in all four evaluation indicators.Among them,DenseNet121 with dual-channel input achieved best results with MAE of 0.54 years,RMSE of 0.82 years,R2 of 0.76,and PCC(r)of 0.88.Manual estimation yielded an MAE of 0.82 years,ranking second only to dual-channel DenseNet121.Conclusion The DenseNet121 model with dual-channel input combined with original images and segmentation labels is superior to manual evaluation results,and can effectively estimate the bone age of Chinese Han adolescents.

Objective To achieve intelligent recognition and segmentation of common craniocerebral inju-ries(hereinafter referred to as"segmentation")by training convolutional neural network DeepLabV3+model based on CT images of blunt craniocerebral injury(BCI),and to explore the value of deep learning in automated diagnosis of BCI in forensic medicine.Methods A total of 5 486 CT images of BCI from living persons were collected as the training set,validation set and test set for model training and performance evaluation.Another 255 CT images of BCI and 156 normal craniocerebral CT images from living persons were collected as the blind test set to evaluate the ability of the model to seg-ment the five types of craniocerebral injuries including scalp hematoma,skull fracture,epidural hema-toma,subdural hematoma,and brain contusion.Another 340 BCI and 120 normal craniocerebral CT images from cadavers were collected as the new blind test set to explore the application value of the model trained by living CT images in the segmentation of BCI in cadavers.The five types CT images of all BCI except the blind test set were manually labeled;then,each dataset was inputted into the model to train the model.The performance of the model was evaluated and optimized based on the loss function and accuracy curves of the training set and validation set,and the generalization ability was evaluated based on the Dice value of the test set.According to the accuracy,precision and F1 value of the blind test set,the segmentation performance of the model for five types of BCI was evaluated.Results After training and optimizing the model,the average Dice values of the final optimal model to scalp hematoma,skull fracture,epidural hematoma,subdural hematoma and brain contusion segmen-tation were 0.766 4,0.812 3,0.938 7,0.782 7 and 0.858 1,respectively,all greater than 0.75,meeting the expected requirements.External validation showed that the F1 values were 93.02%,89.80%,87.80%,92.93%and 86.57%in living CT images,respectively;83.92%,44.90%,76.47%,64.29%and 48.89%in cadaveric CT images,respectively.The above suggested that the model was able to accu-rately segment various types of craniocerebral injury on living CT images,while its segmentation ability was relatively poor on cadaveric CT images,but still able to accurately segment scalp hematoma,epidu-ral hematoma and subdural hematoma.Conclusion Deep learning model trained on CT images can be used for BCI segmentation.However,the direct use of living persons'BCI models for the identifica-tion of cadaveric BCI has some limitations.This study provides a new approach for intelligent segmen-tation of virtual anatomical data for BCI.

Objective To investigate the value of wrist MRI in bone age estimation for male adoles-cents in Shanghai,Zhejiang and Jiangsu.Methods A total of 124 Han male adolescents aged 6.0 to 18.0 years from Shanghai,Zhejiang and Jiangsu were selected as subjects.Their weight and height were measured,and T1WI and T2WI sequences of the wrist were scanned.The distal ends of the ra-dius and ulna,and the first to five metacarpal epiphyses and corresponding metaphyses were selected as observational indexes after MRI images of the wrist were obtained.The development of each index was classified(0-2 grades)by a deputy senior imaging expert,then the maximum width of each in-dex was measured by another deputy senior expert.Height,weight,classification and maximum width of indexes were used as input variables,and age was used as the target variable.Support vector ma-chine,random forest,current reality tree,and linear regression models were established to estimate the bone age,and the model with the highest accuracy was selected.Results The height,weight,classifica-tion of wrist bone epiphysis development,maximum width of each bone metaphysis and epiphysis were all correlated with age(P<0.05).The accuracies of the support vector machine were the highest when the differences between bone age and actual chronological age were within 1.0 and 1.5 years(88.7%and 96.0%,respectively).Conclusion It is feasible to estimate bone age by using MRI images.Quantifying the maximum width of the epiphysis and corresponding metaphysis of bone and combining it with MRI image classification can effectively reduce the estimation error.

Bone development shows certain regularity with age. The regularity can be used to infer age and serve many fields such as justice, medicine, archaeology, etc. As a non-invasive evaluation method of the epiphyseal development stage, MRI is widely used in living age estimation. In recent years, the rapid development of machine learning has significantly improved the effectiveness and reliability of living age estimation, which is one of the main development directions of current research. This paper summarizes the analysis methods of age estimation by knee joint MRI, introduces the current research trends, and future application trend.
Epiphyses/diagnostic imaging* ; Age Determination by Skeleton/methods* ; Reproducibility of Results ; Magnetic Resonance Imaging/methods* ; Knee Joint/diagnostic imaging*

OBJECTIVES: To reduce the dimension of characteristic information extracted from pelvic CT images by using principal component analysis (PCA) and partial least squares (PLS) methods. To establish a support vector machine (SVM) classification and identification model to identify if there is pelvic injury by the reduced dimension data and evaluate the feasibility of its application. METHODS: Eighty percent of 146 normal and injured pelvic CT images were randomly selected as training set for model fitting, and the remaining 20% was used as testing set to verify the accuracy of the test, respectively. Through CT image input, preprocessing, feature extraction, feature information dimension reduction, feature selection, parameter selection, model establishment and model comparison, a discriminative model of pelvic injury was established. RESULTS: The PLS dimension reduction method was better than the PCA method and the SVM model was better than the naive Bayesian classifier (NBC) model. The accuracy of the modeling set, leave-one-out cross validation and testing set of the SVM classification model based on 12 PLS factors was 100%, 100% and 93.33%, respectively. CONCLUSIONS In the evaluation of pelvic injury, the pelvic injury data mining model based on CT images reaches high accuracy, which lays a foundation for automatic and rapid identification of pelvic injuries.
Algorithms ; Bayes Theorem ; Data Mining ; Least-Squares Analysis ; Support Vector Machine

Objective To compare the performance of three deep-learning models （VGG19, Inception-V3 and Inception-ResNet-V2） in automatic bone age assessment based on pelvic X-ray radiographs. Methods A total of 962 pelvic X ray radiographs taken from adolescents （481 males, 481 females） aged from 11.0 to 21.0 years in five provinces and cities of China were collected, preprocessed and used as objects of study. Eighty percent of these X ray radiographs were divided into training set and validation set with random sampling method and used for model fitting and hyper-parameters adjustment. Twenty percent were used as test sets, to evaluate the ability of model generalization. The performances of the three models were assessed by comparing the root mean square error （RMSE）, mean absolute error （MAE） and Bland-Altman plots between the model estimates and the chronological ages. Results The mean RMSE and MAE between bone age estimates of the VGG19 model and the chronological ages were 1.29 and 1.02 years, respectively. The mean RMSE and MAE between bone age estimates of the Inception-V3 model and the chronological ages were 1.17 and 0.82 years, respectively. The mean RMSE and MAE between bone age estimates of the Inception-ResNet-V2 model and the chronological ages were 1.11 and 0.84 years, respectively. The Bland-Altman plots showed that the mean value of differences between bone age estimates of Inception-ResNet-V2 model and the chronological ages was the lowest. Conclusion In the automatic bone age assessment of adolescent pelvis, the Inception-ResNet-V2 model performs the best while the Inception-V3 model achieves a similar accuracy as VGG19 model.
Adolescent ; Adult ; Age Determination by Skeleton ; Child ; China ; Female ; Humans ; Male ; Pelvis ; Radiography ; Young Adult

Objective To realize the automated bone age assessment by applying deep learning to digital radiography(DR)image recognition of left wrist joint in Uyghur teenagers, and explore its practical ap-plication value in forensic medicine bone age assessment. Methods The X-ray films of left wrist joint after pretreatment, which were taken from 245 male and 227 female Uyghur nationality teenagers in Uygur Autonomous Region aged from 13.0 to 19.0 years old, were chosen as subjects. And AlexNet was as a regression model of image recognition. From the total samples above, 60% of male and fe-male DR images of left wrist joint were selected as net train set, and 10% of samples were selected as validation set. As test set, the rest 30%were used to obtain the image recognition accuracy with an error range in ±1.0 and ±0.7 age respectively, compared to the real age. Results The modelling results of deep learning algorithm showed that when the error range was in ±1.0 and ±0.7 age respectively, the accuracy of the net train set was 81.4% and 75.6% in male, and 80.5% and 74.8% in female, respectively. When the error range was in ±1.0 and ±0.7 age respectively, the accuracy of the test set was 79.5% and 71.2% in male, and 79.4% and 66.2% in female, respectively. Conclusion The combination of bone age research on teenagers' left wrist joint and deep learning, which has high accuracy and good feasi-bility, can be the research basis of bone age automatic assessment system for the rest joints of body.

Deep learning and neural network models have been new research directions and hot issues in the fields of machine learning and artificial intelligence in recent years. Deep learning has made a breakthrough in the applications of image and speech recognitions, and also has been extensively used in the fields of face recognition and information retrieval because of its special superiority. Bone X-ray images express different variations in black-white-gray gradations, which have image features of black and white contrasts and level differences. Based on these advantages of deep learning in image recognition, we combine it with the research of bone age assessment to provide basic datum for constructing a forensic automatic system of bone age assessment. This paper reviews the basic concept and network architectures of deep learning, and describes its recent research progress on image recognition in different research fields at home and abroad, and explores its advantages and application prospects in bone age assessment.

OBJECTIVETo explore the effectiveness of absorbable hemostatic fluid gelatin in preventing postoperative cerebrospinal fluid leakage.

METHODSThe clinical data of 17 patients with dura mater tear were retrospectively analyzed from March to September in 2003. There were 16 males and 1 female, aged from 16 to 67 years old with an average of (39.6 ± 15.4) years. The injury site was at cervical vertebrae in 1 case, thoracic vertebrae in 9 cases, thoracolumbar junction in 4 cases, lumbar vertebrae in 3 cases. There were burst fracture in 4 cases and fracture-dislocation in 13 cases. According to ASIA grade, 12 cases were grade A, 2 cases were grade B, 2 cases were grade D, 1 case were grade E. Two cases caused by traffic accident, 10 by high falling, 4 by heavy parts crash, 1 by stairs fell during the earthquake. Absorbable hemostatic fluid gelatins were used to plug the dura mater tear,in order to prevent postoperative cerebrospinal fluid leakage. Postoperative drainage were recorded every day.

RESULTSOf 17 patients, 15 cases did not develop with cerebrospinal fluid leakage. Two cases develop with cerebrospinal fluid leakage after operation and their drainage were removed at 6 to 7 days after operation. In all cases, no complications related with cerebrospinal fluid leakage occurred, such as headache, dizzy, fever,neck resistance, rash, incision disunion, incision infection, hematoma, neurologic symptoms aggravation. No abnormal phenomena was found on incision surrounding at follow-up of 9 months.

CONCLUSIONUsing absorbable hemostatic fluid gelatin to plug the dura mater tear during operation is an effective method in preventing postoperative cerebrospinal fluid leakage.

Adolescent ; Adult ; Aged ; Cerebrospinal Fluid Leak ; prevention & control ; Female ; Gelatin ; administration & dosage ; Hemostatics ; administration & dosage ; Humans ; Male ; Middle Aged ; Postoperative Complications ; prevention & control