A Hybrid Semantic Model for MRI Kidney Object Segmentation with Stochastic Features and Edge Detection Techniques

A Hybrid Semantic Model for MRI Kidney Object Segmentation with Stochastic Features and Edge Detection Techniques

© 2022 by IJETT Journal
Volume-70 Issue-9
Year of Publication : 2022
Authors : Sitanaboina S L Parvathi, Harikiran Jonnadula
DOI : 10.14445/22315381/IJETT-V70I9P242

How to Cite?

Sitanaboina S L Parvathi, Harikiran Jonnadula, "A Hybrid Semantic Model for MRI Kidney Object Segmentation with Stochastic Features and Edge Detection Techniques" International Journal of Engineering Trends and Technology, vol. 70, no. 9, pp. 411-420, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I9P242

Because of its importance in disease diagnosis, medical image analysis has been a prominent researchtopic for over a decade. Advancements in deep learning methodologies made computer-aided disease diagnosis feasible from medical images. Object semantic segmentation is the primary activity in medical image analysis. Various deterministic deep learning models for semantic segmentation of objects (organs) from medicalimages are introduced. Generally, the medical image objects (i.e., kidneys) contain the routine shape, size, and brightness which help the deterministic models for efficient segmentation. In the case of chronic diseases such ascancer, the objects in medical images contain tumors, which appear with a high degree of uncertainty in object properties. Due to the uncertainty in object shape, size, and brightness, former deep learning models performed less accurately in diseased object segmentation. In this paper, we proposed a hybrid semantic segmentation model with stochastic feature mapping techniques for the accurate segmentation of medical image objects underuncertainty. The location-dependent split method is used for seeded region marking and approximating object location. Stochastic neural networks with feature mapping techniques are introduced to localize the target objectswithout deterministic modeling. The recursive block-wide segmentation process is used to lineate the target objects from boundary elements. We tested the proposed stochastic segmentation model and its deep learning counterparts on a human kidney tumor MRI dataset. The experimental results show that the proposed stochastic segmentation model outperformed the segmentation of diseased kidney tumor objects with high accuracy and reliability.

Stochastic Feature Mapping, Block Segmentation, Kidney Object Segmentation, Deep Neural Networks, Medical Image Analysis.

[1] World Kidney Day- 12th March 2020, “2020 WKD Theme”, https://www.Worldkidneyday.org/2020-Campaign/2020-Wkd-Theme/
[2] GBD Chronic Kidney Disease Collaboration, “Global, Regional, and National Burden of Chronic Kidney Disease, 1990– 2017: A Systematic Analysis for the Global Burden of Disease Study 2017,” 2020, DOI: https://doi.org/10.1016/S0140-6736(20)30045-3
[3] N. M. Selby Et Al., ‘‘Magnetic Resonance Imaging Biomarkers for Chronic Kidney Disease: A Position Paper from the European Cooperation in Science and Technology Action PARENCHIMA,’’ Nephrology Dialysis Transplantation, vol. 33, no. 2, pp. 4–14, 2018.
[4] Choi H, Jin KH, “Fast and Robust Segmentation of the Striatum Using Deep Convolutional Neural Networks,” Journal of Neuroscience Methods, vol. 274, pp. 146-153, 2016. DOI: 10.1016/J.Jneumeth.2016.10.007. PMID: 27777000.
[5] Y. Guo, Y. Gao and D. Shen, "Deformable MR Prostate Segmentation Via Deep Feature Learning and Sparse Patch Matching," In IEEE Transactions on Medical Imaging, vol. 35, no. 4, pp. 1077-1089, 2016. Doi: 10.1109/TMI.2015.2508280.
[6] Ibragimov B, Xing L, “Segmentation of Organs-At-Risks in Head and Neck CT Images Using Convolutional Neural Networks,” Medical Physics, vol. 44, no. 2, pp. 547-557, 2017. Doi: 10.1002/Mp.12045. PMID: 28205307; PMCID: PMC5383420.
[7] Kline TL, Korfiatis P, Edwards ME, Blais JD, Czerwiec FS, Harris PC, King BF, Torres VE, Erickson BJ, “ Performance of an Artificial Multi-Observer Deep Neural Network for Fully Automated Segmentation of Polycystic Kidneys,” Journal of Digit Imaging, vol. 30, no.4, pp. 442-448, 2017. Doi: 10.1007/S10278-017-9978-1. PMID: 28550374; PMCID: PMC5537093.
[8] Ronneberger, Olaf & Fischer, Philipp & Brox, Thomas, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” 2015.
[9] Daza, Laura & Gomez, Catalina & Arbelaez, Pablo, “Semantic Segmentation of Kidney Tumor Using Convolutional Neural Networks,” 2019. 10.24926/548719.077.
[10] N. Goceri and E. Goceri, "A Neural Network Based Kidney Segmentation From MR Images," 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), pp. 1195-1198, 2015. Doi: 10.1109/ICMLA.2015.229.
[11] W. Thong, S. Kadoury, N. Piché, C.J. Pal, W. Thong, S. Kadoury, N. Piché, C.J. Pal, “Convolutional Networks for Kidney Segmentation in Contrast-Enhanced CT Scans,” Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization , vol. 1163, pp. 1–6, 2016.
[12] R. Prevost, B. Mory, R. Cuingnet, J.M. Correas, L.D. Cohen, R. Ardon, “Kidney Detection and Segmentation in Contrast-Enhanced Ultrasound 3D Images,” Abdomen and Thoracic Imaging: An Engineering & Clinical Perspective, pp. 37–67, 2014.
[13] B. Mory, O. Somphone, R. Prevost, R. Ardon, “Real-Time 3D Image Segmentation By User-Constrained Template Deformation,” In: Medical Image Computing and Computer Assisted Intervention, pp. 561–568, 2012.
[14] R. Ardon, R. Cuingnet, K. Bacchuwar, V. Auvray, “Fast Kidney Detection and Segmentation with Learned Kernel Convolution and Model Deformation In 3D Ultrasound Images,” In: International Symposium on Biomedical Imaging, pp. 268–271, 2015.
[15] Abubakar, Fari, “A Study of Region-Based and Contour Based Image Segmentation,” Signal & Image Processing :An International Journal, vol. 3, pp. 15-22, 2012. 10.5121/Sipij.2012.3602.
[16] Wahba Marian, “ An Automated Modified Region Growing Technique for Prostate Segmentation” In Trans Rectal Ultrasound Images, Master’s Thesis, Department of Electrical and Computer Engineering, University of Waterloo, Waterloo,Ontario, Canada, 2008.
[17] Zhang L, Gao Y, Xia Y, Et Al, “Representative Discovery of Structure Cues for Weakly-Supervised Image Segmentation,” IEEE Transactions on Multimedia, vol. 16, no. 2, pp. 470-479, 2014.
[18] Zhu, Guopu & Zhang, Shuqun & Zeng, Qingshuang & Wang, Changhong, “Boundary-Based Image SegmentationUsing Binary Level Set Method,” Optical Engineering - OPT ENG. 46. 10.1117/1.2740762. 2007.
[19] El-Baz, Ayman & Gimel’farb, Georgy & Suri, Jasjit, “Stochastic Modeling for Medical Image Analysis,” 10.1201/B19253.
[20] I.N. Manousakas, P.E. Undrill, G.G. Cameron, T.W. Redpath, “Split-and-Merge Segmentation of Magnetic Resonance Medical Images: Performance Evaluation and Extension to Three Dimensions, Computers and Biomedical Research,” vol. 31, no. 6, pp. 393- 412, 1998. ISSN 0010-4809, https://doi.org/ 10.1006/Cbmr.1998.1489.
[21] Szenasi, Sandor, “Medical Image Segmentation with Split-and-Merge Method,” Óbuda University, John Von Neumann Faculty of Informatics, Budapest, Hungary, 2013.
[22] Gómez, Octavio & Gonzalez, Jesus & Morales, Eduardo, “Image Segmentation Using Automatic Seeded Region Growing and Instance-Based Learning,” vol. 4756, pp. 192-201, 2007. 10.1007/978-3-540-76725-1_21.
[23] Fan, Minjie & Lee, Thomas, “Variants of Seeded Region Growing,” IET Image Processing, vol. 9, 2015. 10.1049/IetIpr.2014.0490.
[24] M. Welling and Y. W. Teh, “Bayesian Learning Via Stochastic Gradient Langevin Dynamics,” In Proceedings of the 28th International Conference on International Conference on Machine Learning, Ser. ICML’11. Omnipress, pp. 681–688, 2011.
[25] G. Wang, W. Li, M. Aertsen, J. Deprest, S. Ourselin, and T. Vercauteren, “Aleatoric Uncertainty Estimation with Test-Time Augmentation for Medical Image Segmentation with Convolutional Neural Networks,” Neurocomputing, vol. 338, pp. 34–45, 2019.
[26] Yuan, X.; Huang, T, “Spatial Domain-Based Nonlinear Residual Feature Extraction for Identification of Image Operations,” Applied Science, vol. 10, pp. 5582, 2020. https://doi.org/10.3390/App10165582
[27] Tang, Yichuan and Ruslan Salakhutdinov, “Learning Stochastic Feed Forward Neural Networks,” Advances in Neural Information Processing Systems-26, NIPS , 2013.
[28] Hinton, G. E, “Training Products of Experts By Minimizing Contrastive Divergence,” Neural Computation, vol. 14, pp. 1771– 1800, 2002.
[29] A.Pushpa Athisaya Sakila Rani, "Reversible Data Hiding for Medical Images Using Segmentation and Prediction," SSRG International Journal of Computer Science and Engineering, vol. 6, no. 11, pp. 70-77, 2019. Crossref, https://doi.org/10.14445/23488387/IJCSE-V6I11P115.
[30] Bhalerao, A. and R. Wilson, "Unsupervised Image Segmentation Combining Region and Boundary Estimation," Image andVision Computing, vol. L9, pp. 353-368, 2001.
[31] Nageswari P, Rajan S, Manivel K, "Medical Image Segmentation Approaches: A Survey," SSRG International Journal of Electronics and Communication Engineering, vol. 7, no. 7, pp. 1-3, 2020. Crossref, https://doi.org/10.14445/23488549/IJECE-V7I7P101.
[32] Akin, O., Elnajjar, P., Heller, M., Jarosz, R., Erickson, B. J., Kirk, Filippini, J, “Radiology Data From the Cancer Genome Atlas Kidney Renal Clear Cell Carcinoma [TCGA-KIRC] Collection,” The Cancer Imaging Archive. .http://doi.org/10.7937/K9/TCIA.2016.V6PBVTDR
[33] Shivani, Er. Harjeet Singh, "The Performance Analysis of Edge Detection Algorithms for Image Processing Based on Improved Canny Operator," International Journal of Computer Trends and Technology , vol. 68, no. 10, pp. 29-34, 2020. Crossref, 10.14445/22312803/IJCTT-V68I10P106.
[34] Cardenes R, De Luis-Garcia R, Bach-Cuadra M, “A Multidimensional Segmentation Evaluation for Medical Image Data,” Computer Methods and Programs in Biomedicine, vol. 96, no. 2, pp. 108–24, 2009.
[35] Zou KH, Warfield SK, Baharatha A, Tempany C, Kaus MR, Haker SJ, et al, “ Statistical Validation of Image Segmentation Quality Based on a Spatial Overlap Index,” Academic Radiology, vol. 11, pp. 178–89, 2004.
[36] Kumar, K. K., Ramaraj, E., & Geetha, P, “Multi-Sensor Data Fusion for an Efficient Object Tracking in Internet of Things (Iot),” Applied Nanoscience, pp. 1-11, 2021.
[37] Tomasi, Carlo, “Convolution, Smoothing, and Image,” 2003. Derivativeshttps://Courses.Cs.Duke.Edu/Compsci527/Fall14/Notes/Filtering.Pdf.
[38] Won, C.S., "A Block-Based MAP Segmentation for Image Compressions," IEEE Transaction Circuit and Systems for Video Technology, vol. 8, no. 5, pp. 592-601, 1998.
[39] Taha AA, Hanbury A, “Metrics for Evaluating 3D Medical Image Segmentation: Analysis, Selection, and Tool,” BMC Med Imaging, vol. 15, no. 29, 2015. Doi: 10.1186/S12880-015-0068-X. PMID: 26263899; PMCID: PMC4533825.