An Iterative Two-Step Method using Thresholding and SVM to Segment Bones from Knee Magnetic Resonance Images

Norouzi, Alireza; Habibi, Narges; Nourbakhsh, Zahra; Mohd Rahim, Mohd Shafry

doi:10.30486/mjee.2023.1973270.1011

Document Type : Reseach Article

Authors

¹ Department of Computer Engineering, Khomeinishahr Branch, Islamic Azad University, Isfahan, Iran

² Department of Computer Engineering, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran

³ Department of Software Engineering, Universiti Teknologi Malaysia, Malaysia

https://doi.org/10.30486/mjee.2023.1973270.1011

Abstract

Automatic and accurate bone segmentation has important medical applications. Thresholding-based segmentation is the most widely used method to segment the object of interest from the background. Although bone tissue is among the brightest tissues in MRI T2 images, bone has a similar intensity and comparable characteristics to particular other tissues, such as fat, which may cause misclassifications and undesirable results. We have proposed an automatic, accurate, and rapid, with less computational complexity and time segmentation method for the knee bone using iterative thresholding and Support Vector Machines (SVMs). The initial threshold value is first obtained by Otsu Thresholding to partition the image into two classes: bone and non-bone candidate areas. The SVM detected the bone region from the bone candidate areas based on location and shape. The iterative process significantly improved the thresholding value until the bone was identified. The post-processing step utilized a Canny edge filter and image opening to eliminate the undesired area and to more accurately extract the bone. The proposed segmentation technique distinguished between bone and similar structures, such as fat. The object (bone) detection rate was 1, and the average segmentation accuracy was 0.96 using the Dice Similarity Index.

Keywords

References

[1] Swanson, M.S., et al., "Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees". Osteoarthritis and cartilage / OARS, Osteoarthritis Research Society, pp. 344-53,2010.
[2] Prescott, J.W., et al. "An Automated Method to Segment the Femur for Osteoarthritis". in Conf Proc IEEE Eng Med Biol Soc. 2009.
[3] Fripp, S.C., S.K. Warfield, S. Ourselin, "Automatic segmentation of the bone and extraction of the bone–cartilage interface from magnetic resonance images of the knee". Physics in medicine and Biology, Vol. 52(6), pp. 1617–1631, 2007.
[4] Schmid, K.J., N. Magnenat-thalmann, "Robust statistical shape models for MRI bone segmentation in presence of small field of view". Medical Image Analysis, Vol. 15(1), pp. 155-168, 2011.
[5] Rudra, M.S., A. Chowdhury, A. Elnakib, A. El-baz, "3D Graph cut with new edge weights for cerebral white matter segmentation". Pattern Recognition Letters, Vol. 32(7), pp. 941-947m, 2011.
[6] Dubey, M.H., S. Gupta, "The brain MR image segmentation techniques and use of diagnostic packages". Academic radiology, Vol. 17(5), pp. 658-671, 2010.C. Köse, O.G., U. Şevik, "An automatic diagnosis method for the knee meniscus tears in MR images". Expert Systems with Applications, Vol. 36(2), pp. 1208-1216, 2009.
[7] D. Cheng, X.J.S., R. Min, L.M. Hu, X.P. Cai, H.N. Du, Approaches, "Approaches for automated detection and classification of masses in mammograms". Pattern Recognition, Vol. 39 (4), pp. 646 – 668.
[8] Ramezanpour and N. Najafabadi, "Mass center direction-based decision method for intraprediction in HEVC standard," Journal of Real-Time Image Processing, Vol. 17, No. 5, pp. 153–1168, 2020.
[9] Heidari and M. Ramezanpour, "Reduction of intra-coding time for HEVC based on temporary direction map," Journal of Real-Time Image Processing, Vol. 17, pp. 567-579, 2020.
[10] S. Swanson, J.W.P., T.M. Best, K. Powell, R.D. Jackson, F. Haq, M.N. Gurcan, "Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees". Osteoarthritis and Cartilage, Vol. 18(3), pp. 344-53, 2010.
[11] Rathnayaka, T.S., M. Schuetz, B. Schmutz, "Effects of CT image segmentation methods on the accuracy of long bone 3D reconstructions 2011". Medical engineering & physics, Vol. 33(2), pp. 226-33, 2011.
[12] R. Buie, G.M.C., R.J. Klinck, J.A. MacNeil, S.K. Boyd, "Automatic segmentation of cortical and trabecular compartments based on a dual threshold technique for in vivo micro-CT bone analysis". Bone, Vol. 41(4), pp. 505-15, 2007
[13] Liu, C.T., J. Liu, C. Yu, S. Yu, "A pectoral muscle segmentation algorithm for digital mammograms using Otsu thresholding and multiple regression analysis". Computers & Mathematics with Applications, Vol. 64(5), pp. 1100-1107, 2012.
[14] Kom, A.T., M. Kom, "Automated detection of masses in mammograms by local adaptive thresholding". Computers in Biology and Medicine, Vol. 37(1), pp. 37-48, 2007.
[15] ANDREW J. BURGHARDT, G.J.K., and SHARMILA MAJUMDAR, "A local adaptive threshold strategy for high resolution peripheral quantitative computed tomography of trabecular bone". Annals of biomedical engineering, Vol. 35(10), pp. 1678-1686, 2007.
[16] Sang, H.L., W. Peng , T. Zhang "Knowledge-based adaptive thresholding segmentation of digital subtraction angiography images". Image and Vision Computing, Vol. 25(8), pp. 1263-1270, 2007.
[17] Zhang, C.H.Y., C.K. Chui, S.H. Ong, "Fast segmentation of bone in CT images using 3D adaptive thresholding Computers" in Biology and Medicine, Vol. 40(2), pp. 231-236, 2010.
[18] Tanoori, Z.A., A. Shakibafar, S. Katebi, Brain volumetry: "An active contour model-based segmentation followed by SVM-based classification". Computers in biology and medicine, Vol. 41(8), pp. 619-632, 2011.
[19] Bourgeat, J.F., P. Stanwell, S. Ramadan, S. Ourselin, "MR image segmentation of the knee bone using phase information". Medical image analysis, Vol. 11(4), pp. 325–335, 2007.
[20] B. Sampaio, E.M.D., A. C. Silva, A.C. De Paiva, M. Gattass, "Detection of masses in mammogram images using CNN, geostatistic functions and SVM". Computers in biology and medicine, Vol. 41(8), pp. 653–664, 2011.
[21] Zhang, K., W. Lu, and P. Marziliano, "The unified extreme learning machines and discriminative random fields for automatic knee cartilage and meniscus segmentation from multi-contrast MR images". Machine vision and applications, Vol. 24(7), pp. 1459-1472, 2013.
[22] Thengade, A. and B.H. Mutha. "Image segmentation for detection of knee cartilage". in 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA). 2018. IEEE.
[23] Kumar, V.A. and A. Jayanthy. "Classification of MRI images in 2D coronal view and measurement of articular cartilage thickness for early detection of knee osteoarthritis". in 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT). 2016. IEEE.
[24] Hegadi, R.S., U.P. Chavan, and D.I. Navale, "Identification of knee osteoarthritis using texture analysis, in Data Analytics and Learning". Springer. pp. 121-129, 2019.
[25] Öztürk, C.N. and S. Albayrak, "Automatic segmentation of cartilage in high-field magnetic resonance images of the knee joint with an improved voxel-classification-driven region-growing algorithm using vicinity-correlated subsampling". Computers in biology and medicine, Vol. 72, pp. 90-107,2016.
[26] Felfeliyan, B., et al., "Improved-Mask R-CNN: Towards an accurate generic MSK MRI instance segmentation platform (data from the Osteoarthritis Initiative)". Computerized Medical Imaging and Graphics, Vol. 97, pp. 102056, 2022.
[27] Felfeliyan, B., et al. "MRI knee domain translation for unsupervised segmentation by CycleGAN (data from osteoarthritis initiative (OAI))". in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). 2021. IEEE.
[28] Gatti, A.A. and M.R. Maly, "Automatic knee cartilage and bone segmentation using multi-stage convolutional neural networks: data from the osteoarthritis initiative". Magnetic Resonance Materials in Physics, Biology and Medicine, Vol. 34(6), pp. 859-875, 2021.
[29] Khan, S., et al., "Multipath CNN with alpha matte inference for knee tissue segmentation from MRI". arXiv preprint arXiv:2109.14249, 2021.
[30] Khan, S., et al., "Deep collaborative network with alpha matte for precise knee tissue segmentation from MRI". Computer Methods and Programs in Biomedicine, Vol. 222, 106963, 2022.
[31] Burton II, W., C. Myers, and P. Rullkoetter, "Semi-supervised learning for automatic segmentation of the knee from MRI with convolutional neural networks". Computer Methods and Programs in Biomedicine, 189, pp. 105328, 2020.
[32] Dai, W., et al., "CAN3D: Fast 3D medical image segmentation via compact context aggregation". Medical Image Analysis, Vol. 82, 102562, 2022.
[33] Peng, Y., et al., "KCB-Net: A 3D knee cartilage and bone segmentation network via sparse annotation". Medical Image Analysis, Vol. 82, 102574, 2022.
[34] Ahn, C., et al., "Fully automated, level set-based segmentation for knee MRIs using an adaptive force function and template: data from the osteoarthritis initiative". Biomedical engineering online, Vol. 15(1), pp. 1-14,2016.
[35] Kessler, D.A., et al., "Segmentation of knee MRI data with convolutional neural networks for semi-automated three-dimensional surface-based analysis of cartilage morphology and composition". Osteoarthritis Imaging, Vol. 2(2), pp. 100010,2022.
[36] Sengara, S.S., et al., "UNet Architectures in Multiplanar Volumetric Segmentation--Validated on Three Knee MRI Cohorts". arXiv preprint arXiv:2203.08194, 2022.
[37] More, S. and J. Singla, "Discrete-MultiResUNet: Segmentation and feature extraction model for knee MR images". Journal of Intelligent & Fuzzy Systems, pp. 1-11, 2021.
[38] Almajalid, R., et al. "Knee bone segmentation on three-dimensional MRI". in 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). 2019. IEEE.
[39] Kemnitz, J., et al., "Clinical evaluation of fully automated thigh muscle and adipose tissue segmentation using a U-Net deep learning architecture in context of osteoarthritic knee pain". Magnetic Resonance Materials in Physics, Biology and Medicine, Vol. 33(4), pp. 483-493, 2020.
[40] Do, N.-T., et al. "Knee bone tumor segmentation from radiographs using Seg-Unet with dice loss. in Proceedings of the 25th International Workshop on Frontiers of Computer Vision (IW-FCV)", Gangneung, Korea. 2019.
[41] Vapnik, V., "An overview of statistical learning theory". Verlag: Springer, 1995.
[42] Vapnik, V., "Estimation of Dependences Based on Empirical Data".Verlag: Springer, 1982.
[43] R. Webb, K.D.C., "Statistical Pattern Recognition, ed. S. Edition" Malvern, UK: John Wiley & Sons, Ltd, 2002.
[44] Wu, C.L., R.C. Weng, "Probability Estimates for Multi-class Classification by Pairwise Coupling". Journal of Machine Learning Research, Vol. 5, pp. 975–1005, 2004.
[45] Otsu, N., "A threshold selection method from gray-level histograms". EEE Transactions on Systems,Man and Cybernetics, pp. 62-66, 1995.
[46] C. Nevitt, D.T.F., G. Lester, "The Osteoarthritis Initiative: Protocol for the Cohort Study". 2006, <http://www.oai.ucsf.edu/datarelease/>.
[47] Y. Ababneh , J.W.P., M.N. Gurcan, "Automatic graph-cut based segmentation of bones from knee magnetic resonance images for osteoarthritis research". Medical Image Analysis, Vol. 15(4), pp. 438–448, 2011.
[48] Dice, L., "Measure of the amount of ecologic association between species". Ecology, Vol. 26, 297–302, 1945.
[49] Ambellan, A. Tack, M. Ehlke and S. Zachow, "Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: Data from the Osteoarthritis Initiative", Medical image analysis. Vol. 52, pp. 109-118, 2019.
[50] Liu, H. J. Zhaoye Zhou, A. Samsonov, G. Zhao and R. Kijowski, "Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging", Magnetic resonance in medicine. Vol. 79(4), pp. 2379-2391, 2018.
[51] Gatti, Anthony A., and Monica R. Maly. "Automatic knee cartilage and bone segmentation using multi-stage convolutional neural networks: data from the osteoarthritis initiative." Magnetic Resonance Materials in Physics, Biology and Medicine. Vol. 34(6), pp.859-875, 2021.

Majlesi Journal of Electrical Engineering

An Iterative Two-Step Method using Thresholding and SVM to Segment Bones from Knee Magnetic Resonance Images

References

References

Volume 17, Issue 3
September 2023
Pages 83-95

An Iterative Two-Step Method using Thresholding and SVM to Segment Bones from Knee Magnetic Resonance Images

References

References

Volume 17, Issue 3September 2023Pages 83-95

Volume 17, Issue 3
September 2023
Pages 83-95