International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

A Novel Whale Optimized TGV-FCMS Segmentation with Modified LSTM Classification for Endometrium Cancer Prediction

  • T. Satya Kiranmai (Department of Information Technology, Chaitanya Bharathi Institute of Technology (A)) ;
  • P.V.Lakshmi (Department of CSE GITAM (Deemed to be University))
  • Received : 2023.05.05
  • Published : 2023.05.30
Download PDF
⟨ Previous Next ⟩

Abstract

Early detection of endometrial carcinoma in uterus is essential for effective treatment. Endometrial carcinoma is the worst kind of endometrium cancer among the others since it is considerably more likely to affect the additional parts of the body if not detected and treated early. Non-invasive medical computer vision, also known as medical image processing, is becoming increasingly essential in the clinical diagnosis of various diseases. Such techniques provide a tool for automatic image processing, allowing for an accurate and timely assessment of the lesion. One of the most difficult aspects of developing an effective automatic categorization system is the absence of huge datasets. Using image processing and deep learning, this article presented an artificial endometrium cancer diagnosis system. The processes in this study include gathering a dermoscopy images from the database, preprocessing, segmentation using hybrid Fuzzy C-Means (FCM) and optimizing the weights using the Whale Optimization Algorithm (WOA). The characteristics of the damaged endometrium cells are retrieved using the feature extraction approach after the Magnetic Resonance pictures have been segmented. The collected characteristics are classified using a deep learning-based methodology called Long Short-Term Memory (LSTM) and Bi-directional LSTM classifiers. After using the publicly accessible data set, suggested classifiers obtain an accuracy of 97% and segmentation accuracy of 93%.

Keywords

References

  1. American Cancer Society. Global Cancer Facts & Figures, 4th ed.; American Cancer Society: Atlanta, GA, USA, 2018.
  2. Lortet-Tieulent, J.; Ferlay, J.; Bray, F.; Jemal, A. International patterns and trends in endometrial cancer incidence, 1978-2013. J. Natl. Cancer Inst. 2018, 110, 354-361. [CrossRef] SGO Clinical Practice Endometrial Cancer Working Group; Burke, W.M.; Orr, J.; Leitao, M.; Salom, E.; https://doi.org/10.1093/jnci/djx214
  3. Gehrig, P.; Olawaiye, A.B.; Brewer, M.; Boruta, D.; Herzog, T.J.; et al. Endometrial cancer: A review an current management strategies: Part I. Gynecol. Oncol. 2014, 134, 385-392. [CrossRef] https://doi.org/10.1016/j.ygyno.2014.05.018
  4. 4. SGO Clinical Practice Endometrial Cancer Working Group; Burke, W.M.; Orr, J.; Leitao, M.; Salom, E.; Gehrig, P.; Olawaiye, A.B.; Brewer, M.; Boruta, D.; Herzog, T.J.; et al. Endometrial cancer: A review and current management strategies: Part II. Gynecol. Oncol. 2014, 134, 393-402. [CrossRef] https://doi.org/10.1016/j.ygyno.2014.06.003
  5. Colombo, N.; Creutzberg, C.L.; Amant, F.; Bosse, T.; Gonzalez-Martin, A.; Ledermann, J.; Marth, C.; Nout, R.; Querleu, D.; Mirza, M.; et al. ESMO-ESGO-ESTRO consensus conference on endometrial cancer: Diagnosis, treatment and follow-up. Int. J. Gynecol. Cancer 2016, 26, 2-30. [CrossRef] https://doi.org/10.1097/IGC.0000000000000609
  6. Meissnitzer, M.; Forstner, R. MRI of endometrium cancer-How we do it. Meissnitzer Forstner Cancer Imaging 2016, 16, 11. [CrossRef]
  7. Larson, D.M.; Connor, G.P.; Broste, S.K.; Krawisz, B.R.; Johnson, K.K. Prognostic significance of gross myometrial invasion with endometrial cancer. Obstet. Gynecol. 1996, 88, 394-398. [CrossRef] https://doi.org/10.1016/0029-7844(96)00161-5
  8. Mitamura, T.; Watari, H.; Todo, Y.; Kato, T.; Konno, Y.; Hosaka, M.; Sakuragi, N. Lymphadenectomy can be omitted for low-risk endometrial cancer based on preoperative assessments. J. Gynecol. Oncol. 2014, 25, 301-305. [CrossRef] [PubMed] https://doi.org/10.3802/jgo.2014.25.4.301
  9. Alcazar, J.L.; Gaston, B.; Navarro, B.; Salas, R.; Aranda, J.; Guerriero, S. Transvaginal ultrasound versus magnetic resonance imaging for preoperative assessment of myometrial infiltration in patients with endometrial cancer: A systematic review and meta-analysis. J. Gynecol. Oncol. 2017, 28, e86. [CrossRef] [PubMed]
  10. Hricak, H.; Rubinstein, L.V.; Gherman, G.M.; Karstaedt, N. MR imaging evaluation of endometrial carcinoma: Results of an NCI cooperative study. Radiology 1991, 179, 829-832. [CrossRef] [PubMed] https://doi.org/10.1148/radiology.179.3.2028000
  11. Choi, H.-J.; Lee, S.; Park, B.K.; Kim, T.-J.; Kim, C.K.; Park, J.J.; Choi, C.H.; Lee, Y.-Y.; Lee, J.-W.; Bae, D.-S.; et al Long-term outcomes of magnetic resonance imaging-invisible endometrial cancer. J. Gynecol. Oncol. 2016, 27, e38. [CrossRef]
  12. Bi, W.L.; Hosny, A.; Schabath, M.B.; Giger, M.L.; Birkbak, N.J.; Mehrtash, A.; Allison, T.; Arnaout, O.; Abbosh, C.; Dunn, I.F.; et al. Artificial intelligence in cancer imaging: Clinical challenges and applications. CA Cancer J. Clin. 2019, 69, 127-157. [CrossRef] [PubMed] https://doi.org/10.3322/caac.21552
  13. Weidlich, V.; Weidlich, G.A. Artificial intelligence in medicine and radiation oncology. Cureus 2018, 10, e2475. [CrossRef] [PubMed]
  14. Mendelson, E.B. Artificial intelligence in breast imaging-Potentials and limitations. AJR Am. J. Roentgenol. 2019, 212, 293-299. [CrossRef] [PubMed] https://doi.org/10.2214/AJR.18.20532
  15. Hwang, D.-K.; Hsu, C.-C.; Chang, K.-J.; Chao, D.; Sun, C.-H.; Jheng, Y.-C.; Yarmishyn, A.A.; Wu, J.-C. Tsai, C.-Y.; Wang, M.-L.; et al. Artificial intelligence-based decision-making for age-related macular degeneration. Theranostics 2019, 9, 232-245. [CrossRef] https://doi.org/10.7150/thno.28447
  16. Esteva, A.; Kuprel, B.; Novoa, R.A.; Ko, J.; Swetter, S.M.; Blau, H.M.; Thrun, S. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017, 542, 115-118. [CrossRef] https://doi.org/10.1038/nature21056
  17. Litjens, G.; Kooi, T.; Bejnordi, B.E.; Setio, A.A.A.; Ciompi, F.; Ghafoorian, M.; Van Der Laak, J.A.; Van Ginneken, B.; Sanchez, C.I. A survey on deep learning in medical image analysis. Med. Image Anal. 2017, 42, 60-88. [CrossRef] https://doi.org/10.1016/j.media.2017.07.005
  18. Doupe P, Faghmous J, Basu S. Machine learning for health services researchers. Value Health. 2019;22(7):808-815. Available from: https://pubmed.ncbi.nlm.nih.gov/31277828/ [Accessed: October 1, 2020] https://doi.org/10.1016/j.jval.2019.02.012
  19. Crown WH. Potential application of machine learning in health outcomes research and some statistical cautions. International Society for Pharmacoeconomics and Outcomes Research (ISPOR). 2015. DOI: 10.1016/j.jval.2014.12.005 [Accessed: October 1, 2020]
  20. Ghassemi M, Naumann T, Schulam P, Beam AL, Chen IY, Ranganath R. A review of challenges and opportunities in machine learning for health. arXivLabs. 2019. Available from: https://arxiv.org/abs/1806.00388 [Accessed: October 1, 2020]
  21. Buch VH, Ahmed I, Maruthappu M. Artificial intelligence in medicine: Current trends and future possibilities. British Journal of General Practice. 2018;68(668):143-144. DOI: 10.3399/bjgp18X695213 [Accessed: October 1, 2020]
  22. Rajkomar A, Lingam S, Taylor AG, Blum M, Mongan J. Highthroughput classification of radiographs using deep convolutional neural networks. Journal of Digital Imaging. 2016;30:95-101. DOI: 10.1007/s10278-016-9914-9
  23. Chen M, Hao Y, Hwang K, Wang L, Wang L. Disease prediction by machine learning over big data from healthcare communities. IEEE. 2017;5:8869-8879. DOI: 10.1109/ACCESS.2017.2694446 [Accessed: October 1, 2020]
  24. Alexandru AG, Radu IM, Bizon ML. Big data in healthcare-Opportunities and challenges. Informatica Economica. 2018;22(2):43-54. DOI: 10.12948/issn14531305/22.2.2018.05
  25. E. Endometriosis: Advances and controversies in classification, pathogenesis, diagnosis, and treatment. Version 1. F1000Research. 2019;8:F1000. DOI: 10.12688/f1000research.14817.1. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6480968/ [Accessed: March 30, 2021]
  26. Chapron C, Fauconnier A, Goffinet F, Breart G, Dubuisson JB. Laparoscopic surgery is not inherently dangerous for patients presenting with benign gynaecologic pathology. Results of a meta-analysis. Human Reproduction. 2002;17:1334-1342 https://doi.org/10.1093/humrep/17.5.1334
  27. Parasar P, Ozcan P, Terry KL. Endometriosis: Epidemiology, diagnosis and clinical management. Current Obstetrics and Gynecology Reports. 2017;6(1):34-41. DOI: 10.1007/s13669-017-0187-1
  28. Hoogeveen M, Dorr PJ, Puylaert JBCM. Endometriosis of the rectovaginal septum: Endovaginal US and MRI findings in two cases. Abdominal Imaging. 2020;28:897-901
  29. Akter S, Xu D, Nagel SC, Bromfield JJ, Pelch KE, Wilshire GB, et al. GenomeForest: An ensemble machine learning classifier for endometriosis. AMIA Joint Summits on Translational Science proceedings. 2020;2020:33-42
  30. Sadia A, Dong X, Nagel Susan C, Bromfield John J, Katherine P, Wilshire Gilbert B, et al. Machine learning classifiers for endometriosis using transcriptomics and methylomics data. Frontiers in Genetics. 2019;10:766. DOI: 10.3389/fgene.2019.00766
  31. Nnoaham KE, Hummelshoj L, Kennedy SH, Jenkinson C, Zondervan KT, World Endometriosis Research Foundation Women's Health Symptom Survey Consortium. Developing symptom-based predictive models of endometriosis as a clinical screening tool: Results from a multicenter study. Fertility and Sterility. 2012;98(3):692-701.e5. DOI: 10.1016/j.fertnstert.2012.04.022. Epub 2012 May 30
  32. Noventa M, Saccardi C, Litta P, Vitagliano A, D'Antona D, Abdulrahim B, et al. Ultrasound techniques in the diagnosis of deep pelvic endometriosis: Algorithm based on a systematic review and meta-analysis. Fertility and Sterility. 2015;104(2):366-383.e2. DOI: 10.1016/j.fertnstert.2015.05.002
  33. Zhang Y, Wang Z, Zhang J, et al. Deep learning model for classifying endometrial lesions. Journal of Translational Medicine. 2021;19:10. DOI: 10.1186/s12967-020-02660-x
  34. Endometriosis signs and symptoms. Available from: https://www.hopkinsmedicine.org/health/conditions-and-diseases/endometriosis [Accessed: October 1, 2020]
  35. PRA Health Sciences. Data Insights. Available from: https://prahs.com/healthcare-intelligence/data-insights
  36. Symphony Health Solutions. Available from: https://symphonyhealth.prahs.com/
  37. N. Z. Tajeddin, and B. M. Asl. "Endometrial carcinoma recognition in dermoscopy images using lesion's peripheral region information." Computer methods and programs in biomedicine 163 (2018): 143-153. https://doi.org/10.1016/j.cmpb.2018.05.005
  38. A. Pennisi, D.D. Bloisi, D. Nardi, A.R. Giampetruzzi, C. Mondino, A. Facchiano, Endometrium lesion image segmentation using Delaunay Triangulation for endometrial carcinoma detection, Comput. Med. Imaging Graphics 52 (2016) 89-103. https://doi.org/10.1016/j.compmedimag.2016.05.002
  39. C. Barata, M.E. Celebi, J.S. Marques, Improving dermoscopy image classification using color constancy, IEEE J. Biomed. Health Inf. 19 (3) (2015) 1146-1152.
  40. T. Y. Satheesha, Satyanarayana, D., Prasad, M. G., &Dhruve, K. D. (2017). Endometrial carcinoma is endometrium deep: a 3D reconstruction technique for computerized Magnetic Resonance endometrium lesion classification. IEEE journal of translational engineering in health and medicine, 5, 1-17.
  41. S. Pathan, K. Gopalakrishna Prabhu, and P. C. Siddalingaswamy. "Automated detection of melanocytes related pigmented endometrium lesions: A clinical framework." Biomedical Signal Processing and Control 51 (2019): 59-72. https://doi.org/10.1016/j.bspc.2019.02.013
  42. S. Pathan, K. Gopalakrishna Prabhu, and P. C. Siddalingaswamy. "A methodological approach to classify typical and atypical pigment network patterns for endometrial carcinoma diagnosis." Biomedical Signal Processing and Control 44 (2018): 25-37. https://doi.org/10.1016/j.bspc.2018.03.017
  43. S. Pathan, Siddalingaswamy, P. C., Lakshmi, L., & Prabhu, K. G. (2017, September). Classification of benign and malignant melanocytic lesions: A CAD tool. In 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 1308-1312). IEEE.
  44. Gohagan, J.K., Prorok, P.C., Hayes, R.B., Kramer, B.S.: The prostate, lung, colorectal and ovarian (plco) cancer screening trial of the national cancer institute: history, organization, and status. Controlled clinical trials 21(6) (2000) 251S-272S https://doi.org/10.1016/S0197-2456(00)00097-0