[KSCI] Korea Science Citation Index Service

http://dx.doi.org/10.9708/jksci.2021.26.12.045

Efficient Osteoporosis Prediction Using A Pair of Ensemble Models

Choi, Se-Heon (Dept. of Computer Science and Engineering, Kangwon National University)
Hwang, Dong-Hwan (Department of Research and Development, ZIOVISION Co. Ltd)
Kim, Do-Hyeon (Dept. of Computer Science and Engineering, Kangwon National University)
Bak, So-Hyeon (Dept. of Radiology, Kangwon National University School of Medicine)
Kim, Yoon (Dept. of Computer Science and Engineering, Kangwon National University)

Publication Information

Journal of the Korea Society of Computer and Information / v.26, no.12, 2021 , pp. 45-52 More about this Journal

Abstract

In this paper, we propose a prediction model for osteopenia and osteoporosis based on a convolutional neural network(CNN) using computed tomography(CT) images. In a single CT image, CNN had a limitation in utilizing important local features for diagnosis. So we propose a compound model which has two identical structures. As an input, two different texture images are used, which are converted from a single normalized CT image. The two networks train different information by using dissimilarity loss function. As a result, our model trains various features in a single CT image which includes important local features, then we ensemble them to improve the accuracy of predicting osteopenia and osteoporosis. In experiment results, our method shows an accuracy of 77.11% and the feature visualize of this model is confirmed by using Grad-CAM.

Keywords

CT; Osteopenia; Osteoporosis; Dissimilarity loss function; Feature map; CNN;

Citations & Related Records

Reference

1	Yasaka K, Akai H, Kunimatsu A, Kiryu S, Abe O. Prediction of bone mineral density from computed tomography: application of deep learning with a convolutional neural network. Eur Radiol. 2020 Jun;30(6):3549-3557. doi: 10.1007/s00330-020-06677-0. Epub 2020 Feb 14. PMID: 32060712. DOI
2	GEIRHOS, Robert, et al. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231, 2018.
3	Kim M., Park J., Na S., Park C.M., Yoo D. (2020) Learning Visual Context by Comparison. In: Vedaldi A., Bischof H., Brox T., Frahm JM. (eds) Computer Vision - ECCV 2020. ECCV 2020. Lecture Notes in Computer Science, vol 12350. Springer, Cham. https://doi.org/10.1007/978-3-030-58558-7_34 DOI
4	CHOLLET, Francois. Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. p. 1251-1258.
5	Wani IM, Arora S. Computer-aided diagnosis systems for osteoporosis detection: a comprehensive survey. Med Biol Eng Comput. 2020 Sep;58(9):1873-1917. doi: 10.1007/s11 517-020-02171-3. Epub 2020 Jun 25. PMID: 32583141. DOI
6	TAN, Mingxing; LE, Quoc. Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning. PMLR, 2019. p. 6105-6114.
7	Pan Y, Shi D, Wang H, Chen T, Cui D, Cheng X, Lu Y. Automatic opportunistic osteoporosis screening using low-dose chest computed tomography scans obtained for lung cancer screening. Eur Radiol. 2020 Jul;30(7):4107-4116. doi: 10.1007/s00330-020-06679-y. Epub 2020 Feb 19. PMID: 32072260; PMCID: PMC7305250. DOI
8	Smith AD. Screening of Bone Density at CT: An Overlooked Opportunity. Radiology. 2019 May;291(2):368- 369. doi: 10.1148/radiol.2019190434. Epub 2019 Mar 26. PMID: 309 17293. DOI
9	HE, Kaiming, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 770-778.
10	DOSOVITSKIY, Alexey, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
11	SZEGEDY, Christian, et al. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 2818-2826.
12	SELVARAJU, Ramprasaath R., et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision. 2017. p. 618-626.
13	Ferizi U, Honig S, Chang G. Artificial intelligence, osteoporosis and fragility fractures. Curr Opin Rheumatol. 2019 Jul;31(4):368-375. doi: 10.1097/BOR.000000000000060 7. PMID: 31045948; PMCID: PMC7282383. DOI
14	Sozen T, Ozisik L, Basaran NC. An overview and management of osteoporosis. Eur J Rheumatol. 2017 Mar;4(1):46-56. doi: 10.5152/eurjrheum.2016.048. Epub 2016 Dec 30. PMID: 28293453; PMCID: PMC5335887. DOI
15	Mitchell PJ. Fracture Liaison Services: the UK experience. Osteoporos Int. 2011 Aug;22 Suppl 3:487-94. doi: 10.1007/s00198-011-1702-2. Epub 2011 Aug 17. PMID: 21847771. DOI
16	Wu J, Qu Y, Wang K, Chen Y. Healthcare Resource Utilization and Direct Medical Costs for Patients With Osteoporotic Fractures in China. Value Health Reg Issues. 2019 May;18:106-111. doi: 10.1016/j.vhri.2018.11.008. Epub 2019 Mar 23. PMID: 30909083. DOI
17	Lee, JaeWon, DoHyeon Kim, and Yoon Kim. "Online Video Synopsis via Multiple Object Detection.", Journal of the Korea Society of Computer and Information, Vol. 24, No. 8, pp. 19-28, Aug. 2019. DOI: https://doi.org/10.9708/jksci.2019.24.08.019 DOI
18	D.-H. Hwang, G.-S. Moon, and Y. Kim, "SKU-Net: Improved U-Net using Selective Kernel Convolution for Retinal Vessel Segmentation," Journal of the Korea Society of Computer and Information, vol. 26, no. 4, pp. 29-37, Apr. 2021. DOI
19	ISLAM, Md Amirul, et al. Shape or texture: Understanding discriminative features in cnns. arXiv preprint arXiv:2101.11604, 2021.