Mitotic Cell Classification System Based On Supervised Learning for Histopathological Images of Breast Cancer
R. Geetha1, M. Sivajothi2
1R. Geetha, Research Scholar, Department of Computer Science, Manonmaniam Sundaranar University, Abishekapatti, Tirunelveli, India
2Dr. M. Sivajothi, Associate Professor, Department of Computer Science, Sri Parasakthi College for Women, Courtalam, India
Manuscript received on 23 August 2019. | Revised Manuscript received on 05 September 2019. | Manuscript published on 30 September 2019. | PP: 2446-2452 | Volume-8 Issue-11, September 2019. | Retrieval Number: K15520981119/2019©BEIESP | DOI: 10.35940/ijitee.K1552.0981119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Breast cancer is a great threat to the women population throughout the world. Due to the technological advancements in medical science and digital imaging technology, histopathological images are widely utilized for better diagnosis. However, the histopathological images involve complicated structure due to the inconsistent staining, lighting conditions and so on. Considering these challenges, this work presents a mitotic cell classification system based on supervised learning for histopathological images of breast cancer. As the classification solely depends on the effectiveness of nuclei extraction, the proposed approach employs twin stage segmentation for better nuclei extraction. The effectiveness of the proposed mitotic cell classification system is matched with the existing approaches and the proposed approach performs better than the existing works with respect to accuracy, sensitivity, specificity and F-measure rates.
Keywords: Histopathological image, mitotic cell detection, supervised learning.
Scope of the Article: Healthcare Informatics