Carpal Bone Segmentation Using Fully Convolutional Neural Network

Author(s): Liang Kim Meng, Azira Khalil, Muhamad Hanif Ahmad Nizar, Maryam Kamarun Nisham, Belinda Pingguan-Murphy, Yan Chai Hum, Maheza Irna Mohamad Salim, Khin Wee Lai*.

Journal Name: Current Medical Imaging
Formerly: Current Medical Imaging Reviews

Volume 15 , Issue 10 , 2019

Become EABM
Become Reviewer

Graphical Abstract:


Abstract:

Background: Bone Age Assessment (BAA) refers to a clinical procedure that aims to identify a discrepancy between biological and chronological age of an individual by assessing the bone age growth. Currently, there are two main methods of executing BAA which are known as Greulich-Pyle and Tanner-Whitehouse techniques. Both techniques involve a manual and qualitative assessment of hand and wrist radiographs, resulting in intra and inter-operator variability accuracy and time-consuming. An automatic segmentation can be applied to the radiographs, providing the physician with more accurate delineation of the carpal bone and accurate quantitative analysis.

Methods: In this study, we proposed an image feature extraction technique based on image segmentation with the fully convolutional neural network with eight stride pixel (FCN-8). A total of 290 radiographic images including both female and the male subject of age ranging from 0 to 18 were manually segmented and trained using FCN-8.

Results and Conclusion: The results exhibit a high training accuracy value of 99.68% and a loss rate of 0.008619 for 50 epochs of training. The experiments compared 58 images against the gold standard ground truth images. The accuracy of our fully automated segmentation technique is 0.78 ± 0.06, 1.56 ±0.30 mm and 98.02% in terms of Dice Coefficient, Hausdorff Distance, and overall qualitative carpal recognition accuracy, respectively.

Keywords: Image, segmentation, bone, assessment, extraction, convolutional neural network.

[1]
Manzoor Mughal A, Hassan N, Ahmed A. Bone age assessment methods: a critical review. Pak J Med Sci 2014; 30(1): 211-5.
[PMID: 24639863]
[2]
Creo AL, Schwenk WF. Bone Age: a handy tool for pediatric providers. Pediatrics 2017; 140(6)e20171486
[http://dx.doi.org/10.1542/peds.2017-1486]
[3]
Schmeling A, Reisinger W, Geserick G, Olze A. Age estimation of unaccompanied minors - Part I. General considerations. Forensic Sci Int 2006; 159: S61-4.
[4]
Schmeling A, Dettmeyer R, Rudolf E, Vieth V, Geserick G. Forensic age estimation methods, certainty, and the law. Deutsches Arzteblatt International 2016; 113(4): 44.
[http://dx.doi.org/10.3238/arztebl.2016.0044]
[5]
Lin P, Zheng CX, Zhang F, Yang Y. X-ray carpal-bone image boundary feature analysis using region statistical feature based level set method for skeletal age assessment application. Optica Applicata Article 2005; 35(2): 283-94.
[6]
Chai HY, Swee TT, Seng GH, Wee LK. Multipurpose contrast enhancement on epiphyseal plates and ossification centers for bone age assessment. Biomedical Engineeri Online 2013; 12(27): 19.
[http://dx.doi.org/10.1186/1475-925X-12-27]
[7]
Greulich WW, Pyle SI, Todd TW. Radiographic atlas of skeletal development of the hand and wrist. Stanford: Stanford University press 1959.
[http://dx.doi.org/10.1097/00000441-195909000-00030]
[8]
Carty H. In: Eds. Tanner JM, Healy MJR, Goldstein H, Cameron N. Assessment of skeletal maturity and prediction of adult height (TW3 method). London: WB Saunders Co. 2001; pp. 110.
[9]
Spampinato C, Palazzo S, Giordano D, Aldinucci M, Leonardi R. Deep learning for automated skeletal bone age assessment in X-ray images. Med Image Anal 2017; 36: 41-51.
[http://dx.doi.org/10.1016/j.media.2016.10.010] [PMID: 27816861]
[10]
King DG, Steventon DM, O’Sullivan MP, et al. Reproducibility of bone ages when performed by radiology registrars: an audit of tanner and whitehouse II versus greulich and pyle methods. Br J Radiol 1994; 67(801): 848-51.
[http://dx.doi.org/10.1259/0007-1285-67-801-848] [PMID: 7953224]
[11]
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Communications of the Acm 2017; 60(6): 84-90.
[12]
Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. In: 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York; IEEE 2014 pp. 580-7
[13]
Ren SQ, He KM, Girshick R, Sun J. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Patt Anal Mach Intell 2017; 39(6): 1137-49.
[14]
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv 2014; 1409: 1556.
[15]
He K M, Zhang X Y, Ren S Q, Sun J. Deep residual learning for image recognition. In: EEE Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE 2016; pp. 770-8.
[16]
Prasoon A, Petersen K, Igel C, Lauze F, Dam E, Nielsen M. Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. 2013. In: Mori K, Sakuma I, Sato Y, Barillot C, Navab N, Eds. Medical Image Computing and Computer- Assisted Intervention – MICCAI 2013. MICCAI 2013. Springer: Berlin, Heidelberg: pp. 246-53.
[http://dx.doi.org/10.1007/978-3-642-40763-5_31]
[17]
Faisal A, Ng SC, Goh SL, George J, Supriyanto E, Lai KW. Multiple LREK active contours for knee meniscus ultrasound image segmentation. IEEE Trans Med Imaging 2015; 34(10): 2162-71.
[18]
Milletari F, Navab N, Ahmadi SA. V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: IEEE International Conference on 3D Vision (3DV). Stanford, CA: IEEE 2016; pp. 565-71.
[19]
Abadi M, Barham P, Chen J. et al. Tensorflow: a system for large-scale machine learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16). Savannah, GA: USA. 2016; pp. 265-83.
[20]
He KM, Gkioxari G, Dollar P, Girshick R. Mask R-CNN. In: 16th IEEE International Conference on Computer Vision (ICCV). Venice, Italy. 2017; pp. 2980-8.
[21]
He L, Wang GH, Hu ZY. Learning depth from single images with deep neural network embedding focal length. IEEE Trans Image Process 2018; 27(9): 4676-89.
[22]
Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 2017; 39(4): 640-51.
[http://dx.doi.org/10.1109/TPAMI.2016.2572683] [PMID: 27244717]
[23]
Jia Y, Shelhamer E, Donahue J et al. Caffe: Convolutional architecture for fast feature embedding. Proceedings of the 22nd ACM international conference on Multimedia. ACM: New York, USA 2014; pp. 675-8.
[http://dx.doi.org/10.1145/2647868.2654889]
[24]
Khalil A, Faisal A, Lai KW, Ng SC, Liew YM. 2D to 3D fusion of echocardiography and cardiac CT for TAVR and TAVI image guidance. Med Biol Eng Comput 2017; 55(8): 1317-26.
[25]
Faisal A, Ng SC, Goh SL, Lai KW. Knee cartilage segmentation and thickness computation from ultrasound images. Med Biol Eng Comput 2018; 56(4): 657-69.
[http://dx.doi.org/10.1007/s11517-017-1710-2] [PMID: 28849317]
[26]
Stapleford LJ, et al. Evaluation of automatic atlas-based lymph node segmentation for head-and-neck cancer. Int J Radiat Oncol Biol Phys 2010; 77(3): 959-66.
[http://dx.doi.org/10.1016/j.ijrobp.2009.09.023]
[27]
Benjamin CFA, Singh JM, Prabhu SP, Warfield SK. Optimization of tractography of the optic radiations. Hum Brain Mapp 2014; 35(2): 683-97.
[http://dx.doi.org/10.1002/hbm.22204] [PMID: 23225566]
[28]
Khalil A, Faisal A, Ng SC, Liew YM, Lai KW. Multimodality registration of two-dimensional echocardiography and cardiac CT for mitral valve diagnosis and surgical planning. J Med Imaging 2017; 4(3): 7.
[http://dx.doi.org/10.1117/1.JMI.4.3.037001]
[29]
Faisal A, Ng S-C, Goh S-L, Lai K W. Knee cartilage ultrasound image segmentation using locally statistical level set method. In: Ibrahim F, Usman J, Ahmad M, Hamzah N, Teh S, Eds. In: 2nd International Conference for Innovation in Biomedical Engineering and Life Sciences. Springer, Singapore 2017.
[http://dx.doi.org/10.1007/978-981-10-7554-4_48]
[30]
Mahapatra D, Schuffler PJ, Tielbeek JA, et al. Automatic detection and segmentation of crohn’s disease tissues from abdominal MRI. IEEE Trans Med Imaging 2013; 32(12): 2332-47.
[http://dx.doi.org/10.1109/TMI.2013.2282124] [PMID: 24058021]
[31]
Khalil A, Faisal A, Ng S-C, Liew YM, Lai KW. Mitral valve rigid registration using 2D echocardiography and cardiac computed tomography. International Conference on Applied System Innovation (ICASI) Sapporo, IEEE 2017; pp . 629-32.
[http://dx.doi.org/10.1109/ICASI.2017.7988504]
[32]
Khalil A, Liew YM, Ng SC, Lai K, Hum YC. chocardiography to cardiac CT image registration spatial and temporal registration of the 2D planar echocardiography images with cardiac CT. IEEE 18th International Conference on E-Health Networking, Applications and Services (Healthcom). Munich, Germany; IEEE 2016; pp. 574-8.


Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 15
ISSUE: 10
Year: 2019
Page: [983 - 989]
Pages: 7
DOI: 10.2174/1573405615666190724101600
Price: $58

Article Metrics

PDF: 15
HTML: 1
EPUB: 1
PRC: 1