[Frontiers in Bioscience, Landmark, 25, 1746-1764, June 1, 2020]

Machine learning paradigm for dynamic contrast-enhanced MRI evaluation of expanding bladder

Dee H. Wu1, Zhongning Chen2, Justin C. North1, Mainak Biswas2, Jonathan Vo1, Jasjit S. Suri4

1Radiological Sciences, University of Oklahoma Health Sciences Center, Oklahoma City, Oklahoma, USA, 2University of Arkansas for Medical Sciences, AR, USA, 3JIS University, Agarpara, Kolkata, India, 4Advanced Knowledge Engineering Center, Global Biomedical Technologies, Inc., CA, USA and Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, USA


1. Abstract
2. Introduction
3. Materials and methods
4. Results
5. Discussion
6. Conclusions
7. Acknowledgments
8. References


Delineation of the bladder under a dynamic contrast enhanced (DCE)-MRI protocol requires robust segmentation. However, this method is subject to errors due to variations in the content of fluid within the bladder, as well as presence of air and similarity of signal intensity in adjacent organs. Introduction of the contrast media into the bladder also causes signal errors due to alterations in the shape of the bladder. To circumvent such errors, and to improve the accuracy, we adapted a machine learning paradigm that utilizes the global bladder shape. The ML system first uses the combination of low level image processing tools such as filtering, and mathematical morphology as preprocessing step. We use neural network for training the network using extracted features and application of trained model on test slices to compute the delineated bladder shapes. This ML-based integrated system has an accuracy of 90.73% and time reduction of 65.2% in over manual delineation and can be used in clinical settings for IC/BPS patient care. Finally, we apply Jaccard Similarity Measure which we report to have a mean score of 0.933 (95% Confidence Interval 0.923, 0.944)


1. DH. Wu, NA. Mayr, Y. Karatas, R. Karatas, M. Adli, SM. Edwards, JD. Wolff, A. Movahed, JF. Montebello, WT. Yuh: Interobserver Variation in Cervical Cancer Tumor Delineation for Image-Based Radiotherapy Planning among and within Different Specialties. J Appl Clin Med Phys 6, 106-110 (2005)
DOI: 10.1120/jacmp.2026.25364

2. RA. Towner, AB. Wisniewski, DH. Wu, SBV. Gordon, N. Smith, JC. North, R. McElhaney, CE. Aston, SA. Shobeiri, BP. Kropp, MB. Greenwood-Van, RE. Hurst: A Feasibility Study to Determine Whether Clinical Contrast Enhanced Magnetic Resonance Imaging Can Detect Increased Bladder Permeability in Patients with Interstitial Cystitis. J Urol 195, 631-638 (2016),
DOI: 10.1016/j.juro.2015.08.077

3. I. Offiah, SB. McMahon, BA. O'Reilly: Interstitial Cystitis/Bladder Pain Syndrome: Diagnosis and Management. Int Urogynecol J 24, 1243-1256 (2013)
DOI: 10.1007/s00192-013-2057-3

4. JM. Sanches, JM. Lane, AF. Laine, JS Suri. In: Ultrasound Imaging: Advances and Applications. Eds: JM. Sanches, JM. Lane, AF. Laine, JS Suri, New York City, New York: Springer-Verlag (2012)

5. RC. Gonzalez, RE. Woods. In: Digital Image Processing. Eds: RC. Gonzalez, RE. Woods, New York City, New York: Pearson (2006)

6. AS. El-Baz, UR Acharya, M. Mirmehdi, JS. Suri. In: Multi Modality State-of-the-Art Medical Image Segmentation and Registration Methodologies. Eds: AS. El-Baz, UR Acharya, M. Mirmehdi, JS. Suri, New York City, New York: Springer (2011)
DOI: 10.1007/978-1-4419-8195-0

7. AS. El-Baz, X. Jiang X, JS. Suri. In: Biomedical Image Segmentation: Advances and Trends. Eds: AS. El-Baz, X. Jiang X, JS. Suri, New York City, New York, CRC Press (2016).

8. Z. Ma, JM. Tavares, RN. Jorge, T. Mascarenhas: A Review of Algorithms for Medical Image Segmentation and Their Applications to the Female Pelvic Cavity. Comput Methods Biomech Biomed Engin 13, 235-246 (2010),
DOI: 10.1080/10255840903131878

9. JC. Bezdek, LO. Hall, LP. Clarke: Review of MR Image Segmentation Techniques Using Pattern Recognition. Med Phys 20, 1033-1048 (1993)
DOI: 10.1118/1.597000

10. P. Thangaraj: Segmentation of Calculi from Ultrasound Kidney Images by Region Indictor with Contour Segmentation Method. Global Journal of Computer Science and Technology (2012)

11. B. Padmapriya, T. Kesavamurthi, HW. Ferose: Edge Based Image Segmentation Technique for Detection and Estimation of the Bladder Wall Thickness. Procedia Engineering 30, 828-835 (2012)
DOI: 10.1016/j.proeng.2012.01.934

12. JA. Canny: Computational Approach to Edge Detection. IEEE Trans Pattern Analysis and Machine Intelligence 8, 679–698 (1986)
DOI: 10.1109/TPAMI.1986.4767851

13. F. Gibou, D. Levy, C. Cardenas, P. Liu, A. Boyer: Partial Differential Equations-Based Segmentation for Radiotherapy Treatment Planning. Math Biosci Eng 2, 209-226 (2005)
DOI: 10.3934/mbe.2005.2.209

14. C. Xu, Pham D, J. Prince. Image Segmentation Using Deformable Models.129,129-145. In: Handbook of Medical Imaging Vol2 Medical Image Processing and Analysis. Eds: C. Xu, DL. Pham, JL. Prince, Bellingham, WA: SPIE (2000)
DOI: 10.1117/3.831079.ch3

15. A. El-Baz, JS. Suri. In: Level Set Method in Medical Imaging Segmentation. Eds: A. El-Baz, JS. Suri, CRC Press (2019)
DOI: 10.1201/b22435

16. M. Kass, A. Witkin, D. Terzopoulos: Snakes: Active Contour Models. International Journal of Computer Vision 1, 321-331 (1988)
DOI: 10.1007/bf00133570

17. JS. Suri, D. Wu, L. Reden, J. Gao, S. Singh, S. Laxminarayan: Modeling segmentation via geometric deformable regularizers, pde and level sets in still and motion imagery: a revisit. International Journal of Image and Graphics, 1, 681-734 (2001).
DOI: 10.1142/S0219467801000402

18. JS. Suri, K. Liu, S. Singh, SN. Laxminarayan, X. Zeng, L. Reden: Shape recovery algorithms using level sets in 2-D/3-D medical imagery: a state-of-the-art review. IEEE Transactions on information technology in biomedicine 6 , 8-28 (2002)
DOI: 10.1109/4233.992158

19. DH. Wu, AD. Shaffer, DM. Thompson, Z. Yang, VA. Magnotta, R. Alam, JS. Suri., WT. Yuh, NA. Mayr: Iterative Active Deformational Methodology for Tumor Delineation: Evaluation across Radiation Treatment Stage and Volume. J Magn Reson Imaging 28, 1188-1194 (2008)
DOI: 10.1002/jmri.21500

20. GA. Giraldi, PS. Rodrigues, RL. Silva, AL.Apolinario, JS. Suri. In: Level Set Formulation for Dual Snake Models in Deformable Models: Biomedical and Clinical Applications 195-233. Eds: GA. Giraldi, PS. Rodrigues, RL. Silva, AL.Apolinario, JS. Suri, New York City, New York, Springer (2007).
DOI: 10.1007/978-0-387-68413-0_7

21. C. Duan, Z. Liang, S. Bao, H. Zhu, S. Wang, G. Zhang, JJ. Chen, H. Lu: A Coupled Level Set Framework for Bladder Wall Segmentation with Application to MR Cystography. IEEE Trans Med Imaging 29, 903-915 (2010)
DOI: 10.1109/tmi.2009.2039756

22. H. Han, L. Li, C. Duan, H. Zhang, Y. Zhao, Z. Liang: A Unified Em Approach to Bladder Wall Segmentation with Coupled Level-Set Constraints. Med Image Anal 17, 1192-1205 (2013)
DOI: 10.1016/j.media.2013.08.002

23. AS. El-Baz, UR. Acharya, M. Mirmehdi, JS. Suri. In: Multi Modality State-of-the-Art Medical Image Segmentation and Registration Methodologies. Eds: AS. El-Baz, UR. Acharya, M. Mirmehdi, JS. Suri, New York City, New York: Springer (2011)
DOI: 10.1007/978-1-4419-8195-0

24. DG. Luenberger , Y. Ye. In: Linear and Nonlinear Programming. Eds: DG. Luenberger , Y. Ye, New York City, New York: Springer, 2016

25. VK. Shrivastava, ND. Londhe, RS. Sonawane, JS. Suri: A novel and robust Bayesian approach for segmentation of psoriasis lesions and its risk stratification. Comput Methods Programs Biomed 150, 9–22 (2017)
DOI: 10.1016/j.cmpb.2017.07.011).

26. Y. Lin, P. Mattila: Menger Curvature and C1 Regularity of Fractals. Proceedings of the American Mathematical Society 129, 1755-1762 (2001)
DOI: 10.1090/S0002-9939-00-05814-7

27. Y. Feng, I. Kawrakow, J. Olsen, PJ. Parikh, C. Noel, O. Wooten, D. Du, S. Mutic, Y. Hu: A Comparative Study of Automatic Image Segmentation Algorithms for Target Tracking in Mr-Igrt. J Appl Clin Med Phys 17, 5820 (2016)
DOI: 10.1120/jacmp.v17i2.5820

28. KH. Cha, L. Hadjiiski, RK. Samala, HP. Chan, EM. Caoili, RH. Cohan: Urinary Bladder Segmentation in Ct Urography Using Deep-Learning Convolutional Neural Network and Level Sets. Med Phys 43, 1882 (2016)
DOI: 10.1118/1.4944498

29. AN. Viswanathan, ED. Yorke, LB. Marks, PJ. Eifel, WU. Shipley: Radiation Dose-Volume Effects of the Urinary Bladder. Int J Radiat Oncol Biol Phys 76:S116-122 (2010)
DOI: 10.1016/j.ijrobp.2009.02.090

30. S. Hafeez, R. Huddart: Advances in Bladder Cancer Imaging. BMC Med 11, 104 (2013)
DOI: 10.1186/1741-7015-11-104

31. S. Verma, R. Arumugam Rajesh, RP.Srinivasa, K. Gaitonde, GL. Chandana, V. Mouraviev, G. Aeron, RB. Bracken, K. Sandrasegaran, Urinary Bladder Cancer: Role of Mr Imaging. Genitourinary Imaging 32, (2011)
DOI: 10.1148/rg.322115125

Abbreviations: Dynamic Contrast Enhanced: DCE, Magnetic Resonance Imaging: MRI, Interstitial Cystitis: IC, Bladder Pain Syndrome: BPS, Machine Learning: ML, Ultrasound: US, DTPA) Gadolinium diethylenetriaminepentacetate: GD, Region of Interest: ROI, Menger Curvature: MC, Dot Product Angle: DPA, Maximum first order difference of the curvature: MDC, Second Order numerical differential estimate of the angle: SOA

Key Words: Machine Learning, Image Segmentation, Hollow Organs, Rim Contrast Enhancement

Send correspondence to: Dee H. Wu, Department of Radiological Sciences, Nicholson Tower Room 3910, 940 NE 13th Street, Stanton L. Young, University of Oklahoma Health Sciences Center, Oklahoma City, OK 73104, Tel: 405-271-8001 Fax: 405-271-3462 E-mail: dee-wu@ouhsc.edu