Automatic Prediction of SENS Score of Rhemutoid Arthritis using CNN-SVM
Keywords:
CNN-SVM, CNN-Softmax, Deep Learning (DL), Machine Learning (ML), Rheumatoid Arthritis, SENS ScoreAbstract
The early detection of Rheumatoid Arthritis (RA) using precise or automated detection techniques can improve the quality of life for arthritis patients. In this study, a novel Customized Convolutional Neural Network (CCNN) along with SVM was developed to automatically and accurately identify the SENS score in RA disease. The CCNN-SVM model used 250 radiographs as sample images for identification accuracy. Experiments were conducted comparing the identification results on our self-designed CNN model with standard classifier models as softmax and SVM based on the same image dataset. The system calculates the erosion of joint images called as Erosion Model. The training experiment results with and without data augmentation while keeping the same parameters of the simulation showed that the accuracy of the self-designed CNN with Softmax and CNN with SVM, models were 89%, and 91.22%, respectively. The results confirmed the feasibility and effectiveness of our proposed CNN model for automatic SENS scores.
References
X. Shao, H. Zhang, J. Rajian, “125I-Labeled Gold Nanorods for Targeted Imaging of Inflammation,” ACS Nano, vol. 5, no. 11, pp. 8967–8973, Oct. 2011, doi: https://doi.org/10.1021/nn203138t
S. L. Thomas, C. J. Edwards, L. Smeeth, C. Cooper, and A. J. Hall, “How accurate are diagnoses for rheumatoid arthritis and juvenile idiopathic arthritis in the general practice research database,” Arthritis & Rheumatism, vol. 59, no. 9, pp. 1314–1321, Sep. 2008, doi: https://doi.org/10.1002/art.24015
Y. Huo, K. L. Vincken, M. A. Viergever, and F. P. Lafeber, “Automatic joint detection in rheumatoid arthritis hand radiographs,” In2013 IEEE 10th International Symposium on Biomedical Imaging, vol. 34, pp. 125–128, Apr. 2013, doi: https://doi.org/10.1109/isbi.2013.6556428
G. Langs, P. Peloschek, H. Bischof, and F. Kainberger, “Automatic Quantification of Joint Space Narrowing and Erosions in Rheumatoid Arthritis,” IEEE Transactions on Medical Imaging, vol. 28, no. 1, pp. 151–164, Jan. 2009, doi: https://doi.org/10.1109/tmi.2008.2004401
F. Joseph, “A study on Deep Machine Learning Algorithms for diagnosis of diseases,” International Journal of Applied Engineering Research, vol. 12, pp. 6338–6346, 2017. [Online]. Available: https://www.ripublication.com/ijaer17/ijaerv12n17_03.pdf
Y. Kim, H. C. Oh, J. E. Park, “Diagnosis and Treatment of Inflammatory Joint Disease,” Hip & Pelvis, vol. 29, no. 4, pp. 211–222, Dec. 2017, doi: https://doi.org/10.5371/hp.2017.29.4.211
J. Smolen, R. Landewé, J. Bijlsma, “EULAR recommendations for the management of rheumatoid arthritis with synthetic and biological disease-modifying antirheumatic drugs: 2019 update,” Ann Rheum Dis, vol. 0, no. 6, pp. 1–15, 2020, doi: https://doi.org/10.1136/annrheumdis-2019-216655
J. T. Sharp, “An overview of radiographic analysis of joint damage in rheumatoid arthritis and its use in metaanalysis,” The Journal of Rheumatology, vol. 27, no. 1, pp. 254–60, Jan. 2000, Available: https://pubmed.ncbi.nlm.nih.gov/10648050/
A. Larsen, “How to apply Larsen score in evaluating radiographs of rheumatoid arthritis in long-term studies,” The Journal of rheumatology, vol. 22, no. 10, pp. 1974–5, Oct. 1995, Available: https://pubmed.ncbi.nlm.nih.gov/8992003/
J. M. Sharp, M. D. Lidsky, L. Collins, and J. Moreland, “Methods of scoring the progression of radiologic changes in rheumatoid arthritis. Correlation of radiologic, clinical and laboratory abnormalities,” Arthritis & Rheumatism, vol. 14, no. 6, pp. 706–720, Nov. 1971, doi: https://doi.org/10.1002/art.1780140605
R. R and W. S, “A new method of scoring radiographic change in rheumatoid arthritis.,” Europepmc.org, 2016. https://europepmc.org/article/med/9818650
D. van Der Heijde, “How to read radiographs according to the Sharp/van der Heijde method,” The Journal of Rheumatology, vol. 27, no. 1, pp. 261–3, Jan. 2000, Available: https://pubmed.ncbi.nlm.nih.gov/10648051/
S. Ichikawa, T. Kamishima, K. Sutherland, T. Okubo, and K. Katayama, “Performance of computer-based analysis using temporal subtraction to assess joint space narrowing progression in rheumatoid patients,” Rheumatology International, vol. 36, no. 1, pp. 101–108, Aug. 2015, doi: https://doi.org/10.1007/s00296-015-3349-3
B. Norgeot, “Assessment of a Deep Learning Model Based on Electronic Health Record Data to Forecast Clinical Outcomes in Patients with Rheumatoid Arthritis,” JAMA Network Open, vol. 2, no. 3, p. e190606, Mar. 2019, doi: https://doi.org/10.1001/jamanetworkopen.2019.0606
S. Nair, R. J. French, D. Laroche, and E. A. Thomas, “The Application of Machine Learning Algorithms to the Analysis of Electromyographic Patterns from Arthritic Patients,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 18, no. 2, pp. 174–184, Apr. 2010, doi: https://doi.org/10.1109/tnsre.2009.2032638
K. Cao, D. M. Mills, R. G. Thiele, and K. A. Patwardhan, “Toward Quantitative Assessment of Rheumatoid Arthritis Using Volumetric Ultrasound,” IEEE Transactions on Biomedical Engineering, vol. 63, no. 2, pp. 449–458, Feb. 2016, doi: https://doi.org/10.1109/tbme.2015.2463711
J. Duryea, Y. Jiang, M. Zakharevich, and H. K. Genant, “Neural network-based algorithm to quantify joint space width in joints of the hand for arthritis assessment,” Medical Physics, vol. 27, no. 5, pp. 1185–1194, May 2000, doi: https://doi.org/10.1118/1.598983
E. Allander, P. O. Forsgren, H. Pettersson, and P. Seideman, “Computerized Assessment of Radiological Changes of the Hand in Rheumatic Diseases,” Scandinavian Journal of Rheumatology, vol. 18, no. 5, pp. 291–296, Jan. 1989, doi: https://doi.org/10.3109/03009748909095032
