Sains Malaysiana 44(12)(2015): 1729–1738

 

A Study on Development of Automation Diagnosis of Liquid Based Cytology

(Suatu Kajian Pembangunan Diagnosis Automasi Sitologi berasaskan Cecair)

 

SEONG-HYUN KIM1, HAN-YEONG OH2 & DONG-WOOK KIM*1,3

 

1Division of Biomedical Engineering, Chonbuk National University, 567 Baekje-daero, Deokjin-gu

Jeonju-si, Jeonbuk, South Korea

 

2Department of Healthcare Engineering, Chonbuk National University, 567 Baekje-daero, Deokjin-gu

Jeonju-si, Jeonbuk, South Korea

 

3Research Center of Healthcare & Welfare Instrument for the Aged, Chonbuk National University

567 Baekje-daero, Deokjin-gu, Jeonju-si, Jeonbuk, South Korea

 

Diserahkan: 2 September 2014/Diterima: 23 Jun 2015

 

ABSTRACT

Cervical cancer afflicts women worldwide. The patients’ mortality with cancer has been increased by changing to westernized dietary habit and lifestyle. In order to detect early cervical cancer, a liquid-based cytology (LBC) was used to examine the exfoliated cells collected from the cervix. This procedure helps to decrease the mortality rate. However, this test mostly involves manual examination by the pathologists. This procedure needs to develop more efficient tool in detecting cervical cancer which rate kept increasing. As such, this study was designed to develop some methods to increase the effectiveness of LBC. The diagnosis algorithm was also established to diagnose the processed cell images via an imaging process algorithm based on the diagnosis criteria. A cell diagnosis program based on GUI, combined with the imaging process and the diagnosis algorithms were developed to automate the test process. The results of this studies showed that this new program can be used for effective diagnosis of cervical cancer. Moreover, it was deemed to increase the precision and accuracy of diagnosis and save patient time.

 

Keywords: Automation diagnosis; diagnosis algorithm; image processing algorithm; liquid based cytology (LBC); uterine cervical cancer

 

ABSTRAK

Kanser pangkal rahim menyerang wanita di seluruh dunia. Kematian pesakit kanser telah meningkat akibat penukaran tabiat pemakanan dan gaya hidup yang kebaratan. Untuk pengesanan awal barah pangkal rahim, sitologi berasaskan cecair (LBC) digunakan untuk mengkaji sel-sel yang dikumpul daripada serviks. Prosedur ini membantu mengurangkan kadar kematian. Walau bagaimanapun, ujian ini kebanyakannya melibatkan pemeriksaan secara manual oleh ahli patologi. Prosedur ini perlu membangunkan alat yang lebih cekap untuk mengesan kanser pangkal rahim kerana kadarnya yang semakin meningkat. Oleh yang demikian, kajian ini telah direka untuk mencadangkan beberapa kaedah untuk meningkatkan keberkesanan LBC. Diagnosis algoritma juga dibangunkan untuk mendiagnosis proses imej sel melalui suatu proses pengimejan algoritma berdasarkan kriteria diagnosis. Suatu program sel diagnosis berdasarkan GUI, digabungkan dengan proses pengimejan dan diagnosis algoritma telah dibangunkan untuk mengautomasikan proses ujian. Keputusan kajian ini menunjukkan bahawa program baru ini boleh digunakan untuk diagnosis kanser pangkal rahim dengan berkesan. Selain itu, ia dilihat boleh meningkatkan kepersisan dan ketepatan diagnosis dan menjimatkan masa pesakit.

 

Kata kunci: Algoritma pemprosesan imej; diagnosis algoritma; diagnosis automasi; kanser pangkal rahim; sitologi berasaskan cecair (LBC)

 

RUJUKAN

h t t p : / /www. c a n c e r. g o . k r /mb s / c a n c e r / s u b v i ew. jsp?id=cancer_020302000 000.

http://www.index.go.kr/potal/main/EachDtlPageDetail.do?idx_ cd=1012.

Abulafia, O., Pezzullo, J.C. & Sherer, D.M. 2003. Performance of ThinPrep liquid-based cervical cytology in comparison with conventionally prepared Papanicolaou smears: A quantitative survey. Gynecologic Oncology 90(1): 137-144.

Bracamontes, E.A.M., Rosas, M.E.M., Velasco, M.M.M., Reyes, H.L.M., Sandoval, J.R.M. & Avila, H.C. 2012. Implementation of Hough transform for fruit image segmentation. Procedia Engineering 35: 230-239.

Bumford, P. 2003. Empirical comparison of cell segmentation algorithms using an annotated dataset. Image Processing 2: 1073-1076.

Chankong, T., Umpon, N.T. & Auephanwiriyakul, S. 2014. Automatic cervical cell segmentation and classification in pap smears. Computer Methods and Programs in Bio Medicine 113(2): 539-556.

Chen, Y., Adjouadi, M., Han, C., Wang, J., Barreto, A., Rishe, N. & Andrian, J. 2010. A highly accurate and computationally efficient approach for unconstrained iris segmentation. Image and Vision Computing 28(2): 261-269.

Choi, Y.D., Han, C.W., Kim, J.H., Oh, I.J., Lee, J.S., Nam, J.H., Juhn, S.W. & Park, C.S. 2008. Effectiveness of sputum cytology using ThinPrep method for evaluation of lung cancer. Diagnostic Cytopathology 36(3), 167-171.

Chung, K.L., Lin, Z.W., Huang, S.T., Huang, Y.H. & Liao, H.Y.M. 2010. New orientation-based elimination approach for accurate line-detection. Pattern Recognition Letters 31(1): 11-19.

De, S., Stanley, R.J., Lu, C., Long, R., Antani, S., Thoma, G. & Zuna, R. 2013. A fusion-based approach for uterine cervical cancer histology image classification. Computerized Medical Imaging and Graphics 37(7): 475-487.

Harandi, N.M., Sadri, S., Moghaddam, N.A. & Amirfattahi, R. 2010. An automated method for segmentation of epithelial cervical cells in images of ThinPrep. Journal of Medical Systems 34(6): 1043-1058.

Hausen, H.Z. 1977. Human papillomaviruses and their possible role in squamous cell carcinomas. Current Topic Microbiology Immunology 78: 1-30.

Hoda, R.S. & Hoda, S.A. 2006. Fundamentals of Pap Test Cytology. New York: Humana Press.

Hussin, R., Juhari, M.R., Kang, N.W., Ismail, R.C. & Kamarudin, A. 2012. Digital image processing techniques for object detection from complex background image. Procedia Engineering 41: 340-344.

Hwang, I.S., Kang, Y.N., Kwon, K.Y., Kwon, S.Y., Kim, S.P., Lee, S.S., Jung, H.R. & Choe, M.S. 2011. Comparative study of relative value for diagnostic procedure of surgical pathology in Korea and United States. The Korean Journal of Pathology 45(1): 9-14.

Jang, J.J., Kim, J.S., Cho, K.J., Khang, S.K., Nam, J.H. & Gong, G.Y. 2002. A comparison of autocyte PREP with matched conventional smear in cervicovaginal cytology. The Korean Journal of Cytopathology 13(1): 8-13.

Jeon, Y.K., Kim, O.R., Park, K.W., Kang, S.B. & Park, I.A. 2004. Liquid-based cytology using monoprep 2 system in cervicovaginal cytology: Comparative study with conventional pap smear and histology. The Korean Journal of Cytopathology 15(l): 33-39.

Jeong, Y.K. & Baek, J.S. 2008. Developing a GUI-based standalone application of matlab program for windows. Journal of Korean Data and Information Science Society 19(2): 519-529.

Jiang, L. 2012. Efficient randomized Hough transform for circle detection using novel probability sampling and feature points. Optik 123(20): 1834-1840.

Joo, S.Y., Yang, Y.S., Moon, W.K. & Kim, H.C. 2004. Computer-aided diagnosis of solid breast nodules: Use of an artificial neural network based on multiple sonographic features. IEEE Transactions on Medical Imaging 23(10): 1292-1300.

Kim, Y.T. 2007. Causes and diagnoses of cervical cancer. Journal of the Korean Medical Association 50(9): 769-777.

Koh, J.S., Cho, S.Y., Ha, H.J., Kim, J.S. & Shin, M.S. 2007. Cytologic evaluation of CellPrep® liquid-based cytology in cervicovaginal, body fluid, and urine specimens. The Korean Journal of Cytopathology 18(1): 29-35.

Lee, K.C., Jung, C.K., Lee, A.H., Jung, E.S., Choi, Y.J., Park, J.S. & Lee, K.Y. 2007. A comparision of surepath™ liquid-based smear with a conventional smear for cervicovaginal cytology-with reference to a histological diagnosis. The Korean Journal of Cytopathology 18(1): 20-28.

Lee, S., Park, J.H., Do, S.I., Kim, Y.W., Lee, J.H., Chang, S.G. & Park, Y.K. 2007. Diagnostic value of urine cytology in 236 cases; Comparison of liquid-based preparation and conventional cytospin method. The Korean Journal of Cytopathology 18(2): 119-125.

Li, B., Peng, K., Ying, X. & Zha, H. 2012. Vanishing point detection using cascaded 1D Hough transform from single images. Pattern Recognition Letters 33(1): 1-8.

Li, K., Lu, Z., Liu, W. & Yin, J. 2012. Cytoplasm and nucleus segmentation in cervical smear images using radiating GVF snake. Pattern Recognition 45(4): 1255-1264.

Lin, Z. & Yu, H. 2011. The pupil location based on the OTSU method and Hough transform. Procedia Environmental Sciences 8: 352-356.

Linder, J. 1998. Recent advances in thin-layer cytology. Diagnostic Cytopathology 18(1): 24-32.

Maksem, J.A., Dhanwada, V., Trueblood, J.E., Weidmann, J., Kane, B., Bolick, D.R., Bedrossian, D.F.I., Kurtycz, C.W.M. & Stewart, J. 2006. Testing automated liquid-based cytology samples with a manual liquid-based cytology method using residual cell suspensions from 500 ThinPrep cases. Diagnostic Cytopathology 34(6): 391-396.

Mat-Isa, N.A., Mashor, M.Y. & Othman, N.H. 2008. An automated cervical pre-cancerous diagnostic system. Artificial Intelligence in Medicine 42: 1-11.

Park, J.M., Lee, J.G. & Suh, I.S. 2005. Clinical efficacy of manual liquid-based cervicovaginal cytology preparation: Compratative study with conventional papanicolaou test. The Korean Journal of Cytopathology 16(1): 10-17.

Plissiti, M.E. & Nikou, C. 2011. Automated detection of cell nuclei in pap smear images using morphological reconstruction and clustering. IEEE Transactions on Information Technology in Biomedicine 15(2): 233-241.

Plissiti, M.E., Nikou, C. & Charchanti, A. 2011. Combining shape, texture and intensity features for cell nuclei extraction in pap smear images. Pattern Recognition Letters 32(6): 838-853.

Prasad, D.K., Leung, M.H. & Cho, S.Y. 2012. Edge curvature and convexity based ellipse detection method. Pattern Recognition 45(9): 3204-3221.

Schledermann, D., Ejersbo, D. & Hoelund, B. 2006. Improvement of diagnostic accuracy and screening conditions with liquid-based cytology. Diagnostic Cytopathology 34(11): 780-785.

Zhang, L., Kong, H., Chin, C.T., Liu, S., Chen, Z., Wanga, T. & Chen, S. 2014. Segmentation of cytoplasm and nuclei of abnormal cells in cervicalcytology using global and local graph cuts. Computerized Medical Imaging and Graphics 38(5): 369-380.

 

*Pengarang untuk surat-menyurat; email: biomed@jbnu.ac.kr

 

 

sebelumnya