Computer-assisted image analysis of histopathological breast cancer images using step-DTOCS

Author

Ikonen, Tiia ; Niska, Harri ; Braithwaite, Billy ; Pollanen, Irene ; Haataja, Keijo ; Toivanen, Pekka ; Tolonen, Teemu ; Isola, Jorma

Author_Institution

Sch. of Comput., Univ. of Eastern Finland, Kuopio, Finland

fYear

2014

Firstpage

187

Lastpage

192

Abstract

In this paper, we address the epidemiology and morphology questions of breast cancer with special focus on different cell features created by lesions. In addition, we provide an insight into feature extraction and classification schemes in the image analysis pipeline. Based on our conducted research work, a novel feature extraction approach, a modification of Distance Transform on Curved Space (DTOCS), is proposed for analysis and classification of breast cancer images. The first experimental results suggest that the Step-DTOCS-based MLP-network is capable of discriminating different cell structures in a respectable way. The obtained results are presented and analyzed, and further research ideas are discussed.

Keywords

cancer; cellular biophysics; feature extraction; image classification; medical image processing; multilayer perceptrons; transforms; breast cancer image classification; cell features; cell structures; computer-assisted image analysis; distance transform on curved space; epidemiology questions; feature extraction; histopathological breast cancer images; image analysis pipeline; lesions; morphology questions; multilayer perceptron; step-DTOCS-based MLP-network; Breast cancer; Classification algorithms; Feature extraction; Image analysis; Image segmentation; Support vector machine classification; DTOCS; breast cancer; classification; feature extraction; neural network;

fLanguage

English

Publisher

ieee

Conference_Titel

Hybrid Intelligent Systems (HIS), 2014 14th International Conference on

Print_ISBN

978-1-4799-7632-4

Type

conf

DOI

10.1109/HIS.2014.7086196

Filename

7086196