Perbandingan Segmentasi Luas Nukleus Sel Normal Superfisial papSmear menggunakan Operasi kanal Warna dan deteksi tepi




Assosiasi Perguruan Tinggi Informatika & Ilmu Komputer (APTIKOM) Wilayah 3


This paper presents a comparison of cell nucleus segmentation and area measurement of Pap smear images by means of modification of color canals with Canny edge detection and morphological reconstruction methods. Regular Pap smear screening is the most successful attempt of medical science and practice for the early detection of cervical cancer. Manual analysis of the cervical cells is time consuming, laborious and
error prone. In early detection, cell nucleus characterization plays an important role for classifying the degree of abnormality in cervical cancer. The aim of this work is to find the matched measurement method with the manual nucleus area measurement. In this work, we utilized Pap smear single cell images from Herlev data bank in RGB mode. The cell images were selected from 90 normal and 160 abnormal class subjects that include: Mild (Light) Dysplasia, Moderate Dysplasia, Severe Dysplasia and Carcinoma In Situ classes. The nucleus of each cell image was cropped manually to localize from the cytoplasm. The color canals modification was performed on each cropped nucleus image by, first, separating each R, G, B, and grayscale canals, then implementing addition operation based on color canals (R+G+B, R+G, R+B, G+B, and grayscale). The Canny edge detection was applied on those modifications resulting in binary edge images. The nucleus segmentation was implemented on the edge images by performing region filling based on morphological reconstruction. The area property was calculated based on the segmented nucleus area. The nucleus area from the proposed method was verified to the existing manual measurement (ground truth) of the Herlev data bank. Based on
thorough observation upon the selected color canals and Canny edge detection. It can be concluded that Canny edge detection with canal modification is the most significant for all abnormal classes. While for Normal Superficial, Normal Intermediate, Severe Dysplasia and Moderate Dysplasia, Canny edge detection is significant for all RGB modifications with (r 0.314 – 0.817 range, p-value 0.01), and for Normal Columnar, Mild (Light) Dysplasia and Carsinoma In Situ, Canny edge detection is not sensitive for the three classes.

Kata Kunci: Pap smear images, nucleus, color canals, Canny edge detection, morphological reconstruction

Bidang ilmu
Image Processing


[1] Kusuma, Fitriyadi. Tes Pap dan Cara Deteksi Dini Kanker Serviks
Lainnya,” Departemen Obstetri dan Ginekologi Fakultas Kedokteran
Universitas Indonesia RSUPN dr. Cipto Mangunkusumo, Prevention
and Early Detection of Cervical Cancer (PEACE), Jakarta, 2012.
[2] Kale, As and Aksoy, Selim,” Segmentation of Cervical Cell Images”,
International Conference on Pattern Recognition, IEEE, 2010.
[3] P. Bamford and B. Lovell, “A water immersion algorithm for
cytological image segmentation,” in Proc. APRS Image Segmentation
Workshop, Sydney, Australia, 1996, pp. 7579.
[4] P. Bamford and B. Lovell, “Unsupervised cell nucleus segmentation
with active contours,” Signal Process, vol. 71, no. 2, pp. 203213,
[5] H. S. Wu, J. Barba, and J. Gil, “A parametric fitting algorithm for
segmentation of cell images,” IEEE Trans. Biomed. Eng., vol. 45, no. 3,
pp. 400407, Mar. 1998.
[6] A. Garrido and N. P. de la Blanca, “Applying deformable templates for
cell image segmentation,” Pattern Recognit., vol. 33, no. 5, pp. 821
832, 2000
[7] N. Lassouaoui and L. Hamami, “Genetic algorithms and multifractal
segmentation of cervical cell images,” in Proc. 7th Int. Symp. Signal
Process. Appl., 2003, vol. 2, pp. 14.
[8] E. Bak, K. Najarian, and J. P. Brockway, “Efficient segmentation
framework of cell images in noise environments,” in Proc. 26th Int.
Conf. IEEE Eng. Med. Biol., Sep., 2004, vol. 1, pp. 18021805.
[9] N. A. Mat Isa, “Automated edge detection technique for Pap smear
images usingmoving K-means clustering and modified seed based
region growing algorithm,” Int. J. Comput. Internet Manag., vol. 13,
no. 3, pp. 4559,2005.
[10] C. H. Lin, Y. K. Chan, and C. C. Chen, “Detection and segmentation of
cervical cell cytoplast and nucleus,” Int. J. Imaging Syst. Technol., vol.
19, no. 3, pp. 260270, 2009.
[11] Purwadi, Sigit. “Indonesian Cervical Cancer Challenge”, Divisi
Oncologi Dept Obstetrics Gynecology Faculty of Medicine.
Universitas Indonesia, Prevention and Early Detection of Cervical
Cancer (PEACE) 2012
[12] Koswara, Teja, “Pathological diagnosis of cervical cancer”, Seminar
Club Biomedical Engineering, STEI ITB, Bandung, 2012.
[13] Giri, Endang P. Pap smear Image Classification Based on Association
Rules for Biomedical Image Retrieval System. Thesis. Faculty of
Computer Science, University of Indonesia, 2008
[14] Univesity of Florida Shands Cancer Center. Pathology tests [Online].
2009 [cited 2009 April 15]; Available from:
[15] A. Prayitno, “Cervical Cancer with Human Papilloma Virus and
Epstein Barr Virus Positive,” Journal of Carcinogenesis, vol. 5(13),
May 2006, doi:10.1186/1477-3163-5-13
[16] Winarto, Hariyono, “Kanker Serviks”, Departemen Obstetri dan
Ginekologi Fakultas Kedokteran Universitas Indonesia RSUPN dr.
Cipto Mangunkusumo, Prevention and Early Detection of Cervical
Cancer (PEACE), Jakarta, 2012.
[17] Martin, Erik. Pap-Smear Classification. Technical University of
Denmark DTU.2003.
[18] BustanurRosidi, NorainiJalil, Nur. M. Pista, Lukman H. Ismail,
EkoSupriyantoTati L. Mengko “Classification of Cervical Cells Based
on Labeled Colour Intensity Distribution” International Journal of
Biology and Biomedical Engineering, Issue 4, Volume 5, 2011
[19] J. Jantzen, J. Norup, G. Dounias, and B. Bjerregaard, Pap-smear
Benchmark Data For Pattern Classification, Technical University of
Denmark, Denmark, 2005.
[20] Riana, Dwiza, Ekashanti Octorina Dewi, Dyah, Widyantoro, Dwi H
and Tati, LM, Color Canals Modification with Canny Edge Detection
and Morphological Reconstruction for Cell Nucleus Segmentation and
Area Measurement in Normal Pap Smear Images”. The Fourth
International Conference on Mathematics and Natural Sciences
(ICMNS). 2012
[21] J. Canny, “A computational approch to edge detection,” IEEE
Trans.Pattern Anal. Machine Intell., vol. PAMI-8, pp. 679714, 1986.
[22] J. Canny, “Finding edges and lines in images,” MIT Artif. Intell.
Lab.,Cambridge, MA, Tech. Rep. AI-TR-720, 1983.
[23] Riana, Dwiza, Ekashanti Octorina Dewi, Dyah, Widyantoro, Dwi H
and Tati, LM, Segmentasi Luas Nukeus Sel Normal Superfisial Pap
smear Menggunakan Operasi Kanal Warna dan Deteksi Tepi”. Seminar
Nasional Inovasi Teknologi. 2012
[24] Riana. Dwiza, Ekashanti Octorina Dewi. Dyah, Widyantoro. Dwi H
and Tati. LM, “Segmentation and Area Measurement in Abnormal Pap
Smear Images Using Color Canals Modification with Canny Edge
Detection”. International Conference on Women’s Health in Science &
Engineering (WiSE Health), ITB, Bandung. 2012.
[25] Rafael C. Gonzalez, Richard E. Woods, ”Digital Image Processing”,
Pearson Education, Inc. and Dorling Kindersley Publications, Inc.