Murat Ceylan, Mohamad Melad ASHAMES, Rachid Jennane

Deep Transfer Learning and Majority Voting Approaches for Osteoporosis Classification

Osteoporosis is a systemic skeletal disease characterized by low bone mass density and deterioration of the micro-architectural structure of the bone tissue, increasing bone fragility, and the probability of fracture. In this study, we propose a non-invasive method for osteoporosis classification using X-ray images (plain radiographs) of the ankle. Convolutional Neural Networks along with Data Augmentation techniques and Deep Transfer Learning Architectures are combined to classify X-ray images of healthy and osteoporotic patients. The proposed approach achieved an accuracy of 99% using ResNet50, and 100% with GoogleNet.

PDF

___

[1] Tuck SP, Francis RM: Osteoporosis. Postgrad Med J 78(923), 526- 532, 2002 Apr
[2] Christodoulou C, Cooper C: What is osteoporosis?. Postgraduate medical journal 79(929), 133-8, 2003 Mar
[3] Cooper C, Campion G, Melton L3: Hip fractures in the elderly: a world-wide projection. Osteoporosis International 1;2(6):285-9, 1992 Nov
[4] Sözen T, Özışık L, Başaran NÇ: An overview and management of osteoporosis. European journal of rheumatology 4(1) 46, 2017 Mar
[5] National Osteoporosis Foundation. Available at https://www.nof.org/patients/diagnosis-information/bone-densityexamtesting. Accessed 14 June 2020
[6] Jennane R, Harba R, Lemineur G, Bretteil S, Estrade A, Benhamou CL: Estimation of the 3D self-similarity parameter of trabecular bone from its 2D projection. Medical Image Analysis 11.1:91-98, 2007 Feb
[7] Akgundogdu A, Jennane R, Aufort G, Benhamou CL, Ucan ON: 3D image analysis and artificial intelligence for bone disease classification. Journal of medical systems 34.5:815-828, 2010 Oct
[8] Yousfi L, Houam L, Boukrouche A, Lespessailles E, Ros F, Jennane R: Texture Analysis and Genetic Algorithms for Osteoporosis Diagnosis. International Journal of Pattern Recognition and Artificial Intelligence 6;34(05):2057002, 2020 May
[9] Houam L, Hafiane A, Boukrouche A, Lespessailles E, Jennane R: One Dimensional Local Binary Pattern for Bone Texture Characterization. Pattern Analysis and Applications, Springer, Volume 17, Issue 1, pp. 179-193, 2014
[10] İstanbullu M, Aydin M, Benvenı̇ ste R, Uçan ON, Jennane R: Early diagnosis of osteoporosis using artificial neural networks and support vector machines, 2012 20th Signal Processing and Communications Applications Conference (SIU). IEEE, 2012
[11] Harrar K, Hamami L, Akkoul S, Lespessailles E, Jennane R: Osteoporosis assessment using Multilayer Perceptron neural networks, 2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA). IEEE, 2012
[12] Touvier J, Winzenrieth R, Johansson H, Roux JP, Chaintreuil J, Toumi H, Jennane R, Hans D, Lespessailles E: Fracture discrimination by combined bone mineral density (BMD) and microarchitectural texture analysis. Calcified tissue international 96.4:274-83, 2015 Apr
[13] Tafraouti A, El Hassouni M, Jennane R: Evaluation of fractional Brownian motion synthesis methods using the SVM classifier. Biomedical Signal Processing and Control 1;49:48-56, 2019 Mar
[14] Nasser Y, El Hassouni M, Brahim A, Toumi H, Lespessailles E, Jennane R: Diagnosis of osteoporosis disease from bone X-ray images with stacked sparse autoencoder and SVM classifier, 2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP). IEEE, 2017
[15] Ciuşdel CF, Vizitiu A, Moldoveanu F, Suciu C, Itu LM: Towards deep learning based estimation of fracture risk in osteoporosis patients, 2017 40th International Conference on Telecommunications and Signal Processing (TSP). IEEE, 2017
[16] Tomita N, Cheung YY, Hassanpour S: Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Computers in biology and medicine 98:8-15, 2018 Jul
[17] Sela EI, Pulungan R: Osteoporosis identification based on the validated trabecular area on digital dental radiographic images. Procedia Computer Science 157:282- 289, 2019 Jan
[18] Zheng K, Harris CE, Jennane R, Makrogiannis S: Integrative Blockwise Sparse Analysis for Tissue Characterization and Classification. Artificial Intelligence in Medicine 1:101885, 2020 Jun
[19] Su R, Liu T, Sun C, Jin Q, Jennane R, Wei L: Fusing convolutional neural network features with hand-crafted features for osteoporosis diagnoses. Neurocomputing 14;385:300-9, 2020 Apr
[20] Lee KS, Jung SK, Ryu JJ, Shin SW, Choi J: Evaluation of Transfer Learning with Deep Convolutional Neural Networks for Screening Osteoporosis in Dental Panoramic Radiographs. Journal of Clinical Medicine 9.2:392, 2020 Feb
[21] [dataset] Lespessailles E, Gadois C, Kousignian I, Neveu J.P, Fardellone P, Kolta S, Roux C, Do-Huu J.P, Benhamou C.L: Clinical interest of bone texture analysis in osteoporosis: a case control multicenter study. Osteoporosis International 19 1019–1028, 2008 [22] LeCun Y, Bengio Y, Hinton G: Deep learning. Nature 521(7553):436-44, 2015 May
[23] Perez L, Wang J: The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv 1712.04621, 2017 Dec 13.
[24] Cao G, Huang L, Tian H, Huang X, Wang Y, Zhi R: Contrast enhancement of brightness-distorted images by improved adaptive gamma correction. Computers & Electrical Engineering 66: 569- 582, 2018 Feb
[25] Zhang B, Allebach JP: Adaptive bilateral filter for sharpness enhancement and noise removal. IEEE transactions on Image Processing 31;17(5):664-78, 2008 Mar
[26] Rawat W, Wang Z: Deep convolutional neural networks for image classification, A comprehensive review. Neural computation.;29.9: 2352-2449, 2017 Sep
[27] Nwankpa C, Ijomah W, Gachagan A, Marshall S: Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv 1811.03378, 2018 Nov [28] Simonyan K, Zisserman A: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv 1409.1556, 2014 Sep
[29] Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z: Rethinking the inception architecture for computer vision. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016
[30] He K, Zhang X, Ren S, Sun J: Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition pp. 770-778, 2016
[31] Krizhevsky A, Sutskever I, Hinton GE: Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems pp. 1097-1105, 2012
[32] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A: Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition pp. 1-9, 2015
[33] Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC: Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE conference on computer vision and pattern recognition pp. 4510-4520, 2018
[34] Huang G, Liu Z, Van Der Maaten L, Weinberger KQ: Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition pp. 4700- 4708, 2017
[35] Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L: Imagenet A large-scale hierarchical image database. Computer Vision and Pattern Recognition, CVPR 2009. IEEE Conference on pp. 248-255, 2009 Jun
[36] Ruder S: An overview of gradient descent optimization algorithms. arXiv preprint arXiv 1609.04747, 2016 Sep
[37] Distill. Available at https://distill.pub/2017/momentum. Accessed 09 May 2020
[38] Qian N: On the momentum term in gradient descent learning algorithms. Neural networks 12.1: 145-151, 1999 Jan
[39] Sagi O, Rokach L: Ensemble learning: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 8(4):e1249, 2018
[40] Opitz D, Maclin R: Popular ensemble methods: An empirical study. Journal of artificial intelligence research 1;11:169-98, 1999
[41] Atheel Sabih Shaker, “Detection and Segmentation of Osteoporosis in Human Body using Recurrent Neural Network”, International Journal of Advanced Science and Technology 2020;29(02):1055 1066.
[42] Shahzad M, Khan TF, Bashir M, Ayub M, Ashraf F, Hashmi S, Zahoor F, Jaskani FH. DETECTION OF OSTEOPOROSIS IN DEFECTED BONES USING RADTORCH AND DEEP
LEARNING TECHNIQUES. International Journal of Engineering Applied Sciences and Technology, 2021 Vol. 6, Issue 4, ISSN No. 2455-2143, Pages 115-123
[43] Ho CS, Chen YP, Fan TY, Kuo CF, Yen TY, Liu YC, Pei YC. Application of deep learning neural network in predicting bone mineral density from plain X-ray radiography. Archives of Osteoporosis. 2021 Dec;16(1):1-2.
[44] Hsieh CI, Zheng K, Lin C, Mei L, Lu L, Li W, Chen FP, Wang Y, Zhou X, Wang F, Xie G. Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning. Nature communications. 2021 Sep 16;12(1):1-9.