[1]苏 叶,李 婧,徐寅林.手骨X光片骨龄预测中图像预处理的研究[J].南京师范大学学报(工程技术版),2021,21(02):054-59.[doi:10.3969/j.issn.1672-1292.2021.02.009]
　Su Ye,Li Jing,Xu Yinlin.Research on Image Preprocessing in Predicting the Bone Age ofHand Bone X-ray Films[J].Journal of Nanjing Normal University(Engineering and Technology),2021,21(02):054-59.[doi:10.3969/j.issn.1672-1292.2021.02.009]
点击复制

手骨X光片骨龄预测中图像预处理的研究
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
21卷
期数:
2021年02期
页码:
054-59
栏目:
计算机科学与技术
出版日期:
2021-06-30

文章信息/Info

Title:
Research on Image Preprocessing in Predicting the Bone Age ofHand Bone X-ray Films
文章编号:
1672-1292(2021)02-0054-06
作者:
苏 叶; 李 婧; 徐寅林
南京师范大学计算机与电子信息学院,江苏 南京 210023
Author(s):
Su Ye; Li Jing; Xu Yinlin
School of Computer and Electronic Information,Nanjing Normal University,Nanjing 210023,China
关键词:
骨龄预测; 预处理; 灰度直方图均衡; U-Net网络; 深度学习
Keywords:
bone age prediction; pretreatment; grayscale histogram equalization; U-Net network; deep learning
分类号:
TP391
DOI:
10.3969/j.issn.1672-1292.2021.02.009
文献标志码:
A
摘要:
骨龄预测时,手骨X光片经常存在标尺、伪影、噪声、曝光不当等缺陷. 采用常规的滤波加深度学习神经网络等模型进行预测往往正确率不高. 提出一种X光片骨龄辅助预测的预处理方法,包括使用专门用于生物医学图像分割的U-Net网络将X光片中手骨分割出来,使用图像二值化对U-Net生成的掩模进行去除背景处理,使用灰度直方图均衡的办法解决图像过亮或过暗的问题. 经上述精细预处理后,再进行深度学习神经网络预测,实验结果表明精细的预处理对实验结果有很好的改进作用.
Abstract:
Problems of scale,artifact and noise in the X-ray pictures of hand bone always exist during the bone age prediction. The accuracy of prediction by normal filter and end-to-end deep learning neural network model is not so high normally. This paper uses the method of U-Net,which is used for biomedical image segmentation,to split hand bone X-ray film. The method uses image binarizaion to remove the background of mask generated by U-Net,and uses grayscale straight square equalization to solve the problem of brightness of images. Deep learning neural network prediction after fine pretreatments mentioned above can significantly improve the results of bone age prediction.

参考文献/References:

[1] WILSON D M. Regular monitoring of bone age is not useful in children treated with growth hormone[J]. Pediatrics,1999,104(Suppl 5):1036-1039.
[2]黄陈力子. 中国儿童青少年乒乓球分龄赛运动员骨龄检测状况的研究[D]. 北京:北京体育大学,2015.
[3]陆慧玲,郑晶,顾学安,等. 青少年活体年龄推断的方法比较[J]. 中国法医学杂志,2002,17(增刊1):27-29.
[4]GREULICH W W,PYLE S I.Radiographic atlas of skeletal development of the hand and wrist[J]. The American Journal of the Medical Sciences,1959,238(3):393.
[5]TANNER J M,WHITEHOUSE R H,CAMERON N,et al. Assessment of skeletal maturity and prediction of adult height(TW 2 method)[M]. London:WB Saunders,2001:1-110.
[6]TANNER J M,HEALY M R J,GOLDSTEIN H,et al. Assessment of skeletal maturity and prediction of adult height(TW 3)[M]. London:WB Saunders,2001:243-254.
[7]KASHIF M,JONAS S,HAAK D,et al. Bone age assessment meets SIFT[C]//Medical Imaging 2015:Computer-Aided Diagnosis. Orlando,USA:International Society for Optics and Photonics,2015.
[8]王燚,钟俊航. 基于手部X光图像的骨龄检测系统设计与实现[J]. 信息系统工程,2015,32(1):28-30.
[9]李新华,赵娟,袁振宇,等. 基于k-余弦曲率和WSVM的骨龄识别方法[J]. 计算机应用与软件,2015,32(8):158-161.
[10]刘洁琳. 计算机辅助桡骨骨龄等级评估[D]. 北京:北京交通大学,2017.
[11]SPAMPINATO C,PALAZZO S,GIORDANO D,et al. Deep learning for automated skeletal bone age assessment in X-ray images[J]. Medical Image Analysis,2017,36:41-51.
[12]LEE H,TAJMIR S,LEE J,et al. Fully automated deep learning system for bone age assessment[J]. Journal of Digital Imaging,2017,30(4):427-441.
[13]MUTASA S,CHANG P D,RUZAL S C,et al. MABAL:a novel deep-learning architecture for machine-assisted bone age labeling[J]. Journal of Digital Imaging,2018,31(4):513-519.
[14]边增亚. 基于深度卷积神经网络的自动骨龄识别方法研究[D]. 北京:北京交通大学,2019.
[15]林珏伟. 基于深度学习的骨龄评估方法研究[D]. 杭州:浙江工业大学,2019.

备注/Memo

备注/Memo:
收稿日期:2020-09-16.
通讯作者:徐寅林,博士,教授,研究方向:精密仪器设计. E-mail:xuyinlin@njnu.edu.cn
更新日期/Last Update: 2021-06-30