Machine learning Technique for detection of
Cervical Cancer using k-NN and Artificial
Neural Network

Priyanka K Malli , Dr. Suvarna Nandyal

Abstract Cervical cancer along with micro classification are one of the 2 major forms of cancer being observed amongst women across the globe. A cervical cancer results in dead nucleus or change in the morphology of the cells in the cervix. Such cells may have multiple nucleuses ,faulty cytoplasm ,lack of cytoplasm ,dissolved lack of cytoplasm and so on. Detection of cervical cancer in a microscopic smear Test (fluid taken from the cervix )smear is analyzed to microscope is extremely challenging because such cells does not offer significant color or texture variations from the normal cells .Therefore high level Digital Image Processing technique are required identify abnormalities in human cell related cancer detection system. Therefore an automated, comprehensive machine learning technique has been proposed in this work. The proposed technique gives that color and shape features of nucleus and cytoplasm of the cervix cell. The nucleus and the cytoplasm are separated from the cell use the advanced fuzzy based technique. KNN and Neural network are trained with the shape features and color features of the segmented units of the cell and then an unknown cervix cell samples are classified by this technique. The classification result have shown an accuracy of 88.04% for KNN and 54% for ANN. The proposed system work can be further enhanced by taking other classifiers. Keywords: Pap smear Images, Feature Extraction, KNN, ANN

Title:	Machine learning Technique for detection of Cervical Cancer using k-NN and Artificial Neural Network
Author Name:	Priyanka K Malli , Dr. Suvarna Nandyal
Abstract:	Abstract Cervical cancer along with micro classification are one of the 2 major forms of cancer being observed amongst women across the globe. A cervical cancer results in dead nucleus or change in the morphology of the cells in the cervix. Such cells may have multiple nucleuses ,faulty cytoplasm ,lack of cytoplasm ,dissolved lack of cytoplasm and so on. Detection of cervical cancer in a microscopic smear Test (fluid taken from the cervix )smear is analyzed to microscope is extremely challenging because such cells does not offer significant color or texture variations from the normal cells .Therefore high level Digital Image Processing technique are required identify abnormalities in human cell related cancer detection system. Therefore an automated, comprehensive machine learning technique has been proposed in this work. The proposed technique gives that color and shape features of nucleus and cytoplasm of the cervix cell. The nucleus and the cytoplasm are separated from the cell use the advanced fuzzy based technique. KNN and Neural network are trained with the shape features and color features of the segmented units of the cell and then an unknown cervix cell samples are classified by this technique. The classification result have shown an accuracy of 88.04% for KNN and 54% for ANN. The proposed system work can be further enhanced by taking other classifiers. Keywords: Pap smear Images, Feature Extraction, KNN, ANN
Cite this article:	Priyanka K Malli , Dr. Suvarna Nandyal , " Machine learning Technique for detection of Cervical Cancer using k-NN and Artificial Neural Network " , International Journal of Emerging Trends & Technology in Computer Science (IJETTCS), Volume 6, Issue 4, July - August 2017 , pp. 145-149 , ISSN 2278-6856.
Full Text [PDF] Home