DOI QR코드

DOI QR Code

Combining Hough Transform and Fuzzy Unsupervised Learning Strategy in Automatic Segmentation of Large Bowel Obstruction Area from Erect Abdominal Radiographs

  • Kwang Baek Kim (Department of Artificial Intelligence, Silla University) ;
  • Doo Heon Song (Department of Computer Games, Yong-in Art & Science University) ;
  • Hyun Jun Park (Department of Artificial Intelligence Software, Cheongju University)
  • Received : 2023.09.22
  • Accepted : 2023.10.25
  • Published : 2023.12.31

Abstract

The number of senior citizens with large bowel obstruction is steadily growing in Korea. Plain radiography was used to examine the severity and treatment of this phenomenon. To avoid examiner subjectivity in radiography readings, we propose an automatic segmentation method to identify fluid-filled areas indicative of large bowel obstruction. Our proposed method applies the Hough transform to locate suspicious areas successfully and applies the possibilistic fuzzy c-means unsupervised learning algorithm to form the target area in a noisy environment. In an experiment with 104 real-world large-bowel obstruction radiographs, the proposed method successfully identified all suspicious areas in 73 of 104 input images and partially identified the target area in another 21 images. Additionally, the proposed method shows a true-positive rate of over 91% and false-positive rate of less than 3% for pixel-level area formation. These performance evaluation statistics are significantly better than those of the possibilistic c-means and fuzzy c-means-based strategies; thus, this hybrid strategy of automatic segmentation of large bowel suspicious areas is successful and might be feasible for real-world use.

Keywords

Acknowledgement

This manuscript is a partial result of a study on the "Leaders in Industry-university Cooperation 3.0" Project, supported by the Ministry of Education and National Research Foundation of Korea.

References

  1. R. M. Gore, R. I. Silvers, K. H. Thakrar, D. R. Wenzke, U. K. Mehta, G. M. Newmark, and J. W. Berlin, "Bowel obstruction," Radiologic Clinics, vol. 53, no. 6, pp. 1225-1240, Nov. 2015. DOI: 10.1016/j.rcl.2015.06.008.
  2. C.-h. Jeon and C.-s. Cho, "Postoperative adhesive small bowel obstruction treated using acupuncture and moxibustion: A case report," The Journal of Internal Korean Medicine, vol. 41, no. 2, pp. 233-240, May 2020. DOI: 10.22246/jikm.2020.41.2.233.
  3. Healthcare Bigdata Hub. Health insurance review & assessment Service, [Online], Available: http://opendata.hira.or.kr/op/opc/olap3thDsInfo.do.
  4. F. Catena, B. De Simone, F. Coccolini, S. Di Saverio, M. Sartelli, and L. Ansaloni, "Bowel obstruction: a narrative review for all physicians," World Journal of Emergency Surgery, vol. 14, no. 1, pp. 1-8, Apr. 2019. DOI: 10.1186/s13017-019-0240-7.
  5. S. M. Bahouth, "Mechanical Obstruction: Large Bowel Obstruction (LBO)," in Essential Radiology Review, Springer, Cham, pp. 289-290. 2019. DOI: 10.1007/978-3-030-26044-6_86. 
  6. R. Frago, E. Ramirez, M. Millan, E. Kreisler, E. del Valle, and S. Biondo, "Current management of acute malignant large bowel obstruction: a systematic review," The American Journal of Surgery, vol. 207, no. 1, pp. 127-138, Jan. 2014. DOI: 10.1016/j.amjsurg.2013.07.027.
  7. A. K. Pujahari, "Decision making in bowel obstruction: a review," Journal of clinical and diagnostic research: Journal of Clinical and Diagnostic Research, vol. 10, no. 12, pp. PE07-PE12, Dec. 2016. DOI: 10.7860/JCDR/2016/22170.8923.
  8. P. Taourel, N. Kessler, A. Lesnik, J. Pujol, L. Morcos, and J.-M. Bruel, "Helical CT of large bowel obstruction," Abdom Imaging, vol. 28, no. 2, pp. 267-275, Mar. 2003. DOI: 10.1007/s00261-002-0038-y.
  9. Y. Tamyalew, A. O. Salau, and A. M. Ayalew, "Detection and classification of large bowel obstruction from X-ray images using machine learning algorithms," International Journal of Imaging Systems and Technology, vol. 33, no. 1, pp. 158-174, Sep. 2022. DOI: 10.1002/ima.22800.
  10. R. M. Gore and M. S. Levine, Textbook of gastrointestinal radiology. 3rd ed. Philadelphia, PA: Saunders/Elsevier, 2008.
  11. D. W. Nelms and B. R. Kann, "Imaging modalities for evaluation of intestinal obstruction," Clinics in colon and rectal surgery, vol. 34, no. 4, pp. 205-218, Jun. 2021. DOI: 10.1055/s-0041-1729737.
  12. R. E. Kottler and G. K. Lee, "The threatened caecum in acute large-bowel obstruction," The British Journal of Radiology, vol. 57, no. 683, pp. 989-990, Nov. 1984. DOI: 10.1259/0007-1285-57-683-989.
  13. P. Taourel, F. Garibaldi, J. Arrigoni, V. Le Guen, A. Lesnik, and J. M. Bruel, "Cecal pneumatosis in patients with obstructive colon cancer: correlation of CT findings with bowel viability," American Journal of Roentgenology, vol. 183, no. 6, pp. 1667-1671, Dec. 2004. DOI: 10.2214/ajr.183.6.01831667.
  14. L. Plastaras, L. Vuitton, N. Badet, S. Koch, V. Di Martino, and E. Delabrousse, "Acute colitis: Differential diagnosis using multidetector CT," Clinical Radiology, vol. 70, no. 3, pp. 262-269, Mar. 2015. DOI: 10.1016/j.crad.2014.11.008.
  15. C. Duffin, S. Mirpour, T. Catanzano, and C. Moore, "Radiologic imaging of bowel infections," Seminars in Ultrasound, CT and MRI, WB Saunders, vol. 41, no. 1, pp. 33-45, Feb. 2020. DOI: 10.1053/j.sult.2019.10.004.
  16. J. D. Patel, H. I. Gale, and K. J. Chang, "Imaging of large bowel with multidetector row CT," in Multislice CT, Springer, Cham, pp. 641-665, Feb. 2017. DOI: 10.1007/174_2017_7.
  17. C. J. Das, S. Manchanda, A. Panda, A. Sharma, and A. K. Gupta, "Recent advances in imaging of small and large bowel," PET clinics, vol. 11, no. 1, pp. 21-37, Jan. 2016. DOI: 10.1016/j.cpet.2015.07.008.
  18. W. Z. Geng, M. Fuller, B. Osborne, and K. Thoirs, "The value of the erect abdominal radiograph for the diagnosis of mechanical bowel obstruction and paralytic ileus in adults presenting with acute abdominal pain," Journal of Medical Radiation Sciences, vol. 65, no. 4, pp. 259-266, Jul. 2018. DOI: 10.1002/jmrs.299.
  19. J. M. Miranda Magalhaes Santos, B. Clemente Oliveira, J. D. A. B. Araujo-Filho, A. N. Assuncao-Jr, F. A. de M. Machado, C. Carlos Tavares Rocha, J. V. Horvat, M. R. Menezes, and N. Horvat, "State-of-the-art in radiomics of hepatocellular carcinoma: a review of basic principles, applications, and limitations," Abdominal Radiology, vol. 45, no. 2, pp. 342-353, Nov. 2019. DOI: 10.1007/s00261-019-02299-3.
  20. A. S. Alyami, "The Role of Radiomics in Fibrosis Crohn's Disease: A Review," Diagnostics, vol. 13, no. 9, p. 1623, May 2023. DOI: 10.3390/diagnostics13091623.
  21. S. Park, J. C. Ye, E. S. Lee, G. Cho, J. W. Yoon, J. H. Choi, I. Joo, and Y. J. Lee, "Deep learning-enabled detection of pneumoperitoneum in supine and erect abdominal radiography: Modeling Using Transfer Learning and Semi-Supervised Learning," Korean Journal of Radiology, vol. 24, no. 6, pp. 541-552, Jun. 2023. DOI: 10.3348/kjr.2022.1032.
  22. W. Bo, W. ying, and C. Lijie, "Fuzzy clustering recognition algorithm of medical image with multi-resolution feature," Concurrency and Computation: Practice and Experience, vol. 32, no. 1, p. e4886, Jan. 2020. DOI: 10.1002/cpe.4886.
  23. K. Xia, X. Gu, and Y. Zhang, "Oriented grouping-constrained spectral clustering for medical imaging segmentation," Multimedia Systems, vol. 26, pp. 27-36, Feb. 2020. DOI: 10.1007/s00530-019-00626-8.
  24. J. Park, D. H. Song, H. Nho, H. Choi, K. A. Kim, H. J. Park, and K. B. Kim, "Automatic segmentation of brachial artery based on fuzzy C-means pixel clustering from ultrasound images," International Journal of Electrical and Computer Engineering, vol. 8, no. 2, pp. 638-643, Apr. 2018. DOI: 10.11591/ijece.v8i2.pp638-643.
  25. K. B. Kim, D. H. Song, and S. S. Yun, "Automatic segmentation of wrist bone fracture area by K-means pixel clustering from X-ray image," International Journal of Electrical and Computer Engineering, vol. 9, no. 6, pp. 5205-5210, Dec. 2019. DOI: 10.11591/ijece.v9i6.pp5205-5210.
  26. F. Cervantes-Sanchez, I. Cruz-Aceves, A. Hernandez-Aguirre, M. A. Hernandez-Gonzalez, and S. E. Solorio-Meza, "Automatic segmentation of coronary arteries in X-ray angiograms using multiscale analysis and artificial neural networks," Applied Sciences, vol. 9, no. 24, p. 5507, Dec. 2019. DOI: 10.3390/app9245507.
  27. K. B. Kim, G. H. Kim, D. H. Song, H. J. Park, and C. W. Kim, "Automatic segmentation of liver/kidney area with double-layered fuzzy C-means and the utility of hepatorenal index for fatty liver severity classification," Journal of Intelligent & Fuzzy Systems, vol. 39, no. 1, pp. 925-936, Jul. 2020. DOI: 10.3233/JIFS-191850.
  28. W. Shen, W. Xu, H. Zhang, Z. Sun, J. Ma, X. Ma, et al., "Automatic segmentation of the femur and tibia bones from X-ray images based on pure dilated residual U-Net," Inverse Problems and Imaging, vol. 15, no. 6, pp. 1333-1346, Dec. 2021. DOI: 10.3934/ipi.2020057.
  29. K. B. Kim, D. H. Song, and H. J. Park, "Robust Automatic Segmentation of Inflamed Appendix from Ultrasonography with Double-Layered Outlier Rejection Fuzzy C-Means Clustering," Applied Sciences, vol. 12, no. 11, p. 5753, Jun. 2022. DOI: 10.3390/app12115753.
  30. K. B. Kim, "Performance evaluation of pixel clustering approaches for automatic detection of small bowel obstruction from abdominal radiographs," Journal of information and communication convergence engineering, vol. 20, no. 3, pp. 153-159, Sep. 2022. DOI: 10.56977/jicce.2022.20.3.153.
  31. R. O. Duda and P. E. Hart, "Use of the Hough transformation to detect lines and curves in pictures," Communication of Association for Computing Machinery (ACM), vol. 15, no. 1, pp. 11-15, Jan. 1972. DOI: 10.1145/361237.361242.
  32. H. M. unver, Y. Kokver, E. Duman, and O. A. Erdem, "Statistical edge detection and circular hough transform for optic disk localization," Applied Sciences, vol. 9, no. 2, p. 350, Jan. 2019. DOI: 10.3390/app9020350.
  33. K. B. Kim, D. H. Song, and Y. W. Woo, "Automatic segmentation of large bowl obstruction area with Hough transform from erect abdominal radiograph images," International Journal of Electrical and Computer Engineering, vol. 11, no. 3, pp. 2674-2649, Jun. 2021. DOI: 10.11591/ijece.v11i3.pp2674-2679.
  34. N. R. Pal, K. Pal, J. M. Keller, and J. C. Bezdek, "A possibilistic fuzzy c-means clustering algorithm," IEEE Transactions on Fuzzy System, vol. 13, no. 4, pp. 517-530, Aug. 2005. DOI: 10.1109/TFUZZ.2004.840099.
  35. M. H. F. Zarandi, S. Sotudian, and O. Castillo, "A new validity index for fuzzy-possibilistic c-means clustering," arXiv preprint arXiv: 2005.09162, May 2020. DOI: 10.48550/arXiv.2005.09162.
  36. C. L. Chowdhary and D. P. Acharjya, "Clustering algorithm in possibilistic exponential fuzzy C-mean segmenting medical images," in Journal of Biomimetics, biomaterials and biomedical engineering, vol. 30, pp. 12-23, Jan. 2017. DOI: 10.4028/www.scientific.net/JBBBE.30.12.
  37. K. B. Kim and D. H. Song, "Intelligent automatic extraction of canine cataract object with dynamic controlled fuzzy C-means based quantization," International Journal of Electrical and Computer Engineering, vol. 8, no. 2, pp. 666-672, Apr. 2018. DOI: 10.11591/ijece.v8i2.pp666-672.
  38. R. Suganya and R. Shanthi, "Fuzzy c-means algorithm-a review," International Journal of Scientific and Research Publications, vol. 2, no. 11, pp. 440-442, Nov. 2012.
  39. R. Krishnapuram and J. M. Keller, "A possibilistic approach to clustering," IEEE Transactions on Fuzzy Systems, vol. 1, no. 2, pp. 98-110, May 1993. DOI: 10.1109/91.227387.