Deteksi dan Klasifikasi Data Ultrasonografi Tumor Payudara dengan Menggunakan Adaptive Neuro Fuzzy Inference System (ANFIS)
Abstract
Abstrak. Telah dilakukan identifikasi data ultrasonografi tumor payudara dengan menggunakan Adaptive NeuroFuzzy InferenceSystem (ANFIS). Untuk klasifikasi diberikan pasangan-pasangan input fungsi keanggotaan (MFs) antara O - 0, l dengan output pasien tumor/kaoker sangat parah ; input MFs 0,11 - 0,2, dengan output pasien tumor/kanker parah; input MFs 0,21 - 0,4 dengan output pasien tumor/kanker tidak parah ; dan input 0,4 -1 dengan output pasien sehat. Jdentifikasi dilakukan terhadap data citra ultrasonografi baik pada pasien sehat maupun pada pasien yang memiliki kclainan, dan memberikan persentase kcbenaran data training sebesar 87%. Rule base dibuat dengan menggunakan sistem pakar (expert system) dengan 8 aturan dan training data Fuzzy Inference System (FIS) dilakukan dengan menggunakan metode backpropagation. (JKS 20~0;2:77-86)
Kata kunci: data ultrasonografi, tumor payudara, neuro-fuzzy, membership junction, data training, data testing, FIS, rule base, ANFIS.
Abstract. It bas been done to identify breast tumors with ultrasound data using the Adaptive Neuro Fuzzy Inference System (ANFIS). For the classification given pairs with Membership Functions Score (MFS) 0 - 0.1 for patient output tumor I cancer is very severe; MFS 0.11 - 0.2, for patient tumor I cancer is severe; MFS 0.21 - 0.4 for patient tumor I cancer is not severe, and
MFS 0.4 -1 for healthy patients. Identification of ultrasound image data are made to both healthy
patients and in patients who have the disorder, and gives the percentage of truth training data by
87%. Rule base is created by using an expert system (expert systems) with 8 rules and training data
Fuzzy Inference System (FIS) were calculated using backpropagation. (JKS 2010;2:77-86)
Keywords: ultrasonografi data, breast tumors, neuro-fuzzy, membership junction, data training, data testing, FIS, rule base, ANFIS.
Keywords
References
Daftar Pustaka
I. Mangunkusumo R., Frekuensi Tumor Ganas di Indonesia berdasarkan Pemeriksaan Histopatologi. Dalam Pencegahan dan deteksi dini Penyakit kanker, Susworo HR. Tjarta HA, dkk, Penerbit Universitas Indonesia. 1996.
Jang ,J.S.R, Sun, C.T, Mizutani, E., Neuro- Fuzzy and Soft Computing, Prentice-Hall International, Inc.1997.
Das IJ, Cheng CW, Fein DA, Fowble B., Pattern of Dose Variability in Radiation Prescription of Breast Cancer Radiotherapy and Oncology. 1997.44:83-
Tjindarbumi D, dkk., Breast Cancer : Problem and Management in Indonesia. In
; Tjokronegoro A, ed. Cancer in Asia Pasific. Volume 2 Jakarta, Yayasan Kanker Indonesia. 1988 : 643-651.
Okii, H., T. Uozomi, K. Ono and Y.
Fujisawa, Automatic Detection of Nuclei Regions from HE-Stained Breast Tumor Image Using Arficial organisme, IEEE Trans. Inf. & syst..1998: 401-410.
Pedrycz, Witold. Conditional Fuzzy Clustering in The Design of Radial Basis Function Neural Networks. 1998. 9(4):
-612.
Sung, S, C. and kyung, W. 0. A Vowel Recognition Using Adjusted Fuzzy membership Functions, IEEE tecnology Update Series, "Fuzzy Logic Technology and Aplication". 1992.
Bezdek, J.C., Hall, L.O., Clarke, L.P., Review of MRI Segmentation Techniques Using Pattern Recognition, Medical Physics. 1993.
Tizhoosh, Fuzzy Image Processing, Springer. 1997.
IO.Andrew H.C., Hunt B.R., Digital Image
Restoration, Prentice Hall. 1977.
Duda O'Richard, Hart Peter E., Pattern Classification and Scene Analysis, Thon Wiley. 1973.
Gonzales, Rafael ,C. Digital Image Processing, Addison-Wesley Publishing Company. 1987.
G.J. Klir, Bo Yuan. Fuzzy Sets and Fuzzy Logic; Teory and Aplication, Prentice- HalI. Inc. 1995.
Jang ,J.S.R, Sun, C.T, Mizutani, E. Neuro- Fuzzy and Soft Computing, Prentice-Hall International, Inc. 1997.
Jain Amil K, Fundamental of Digital
Image Processing, Prentice Hall. 1989.
Kusumadewi, Sri. Analisis Desain System Fuzzy Menggunakan Toolbox Mathlab, Graha Ilmu, Yogyakarta. 2002.
Refbacks
- There are currently no refbacks.