Title

An automated ovarian tissue detection approach using type P63 counter stained images to minimize pathology experts observation variability

Document Type

Conference Proceeding

Publisher

IADIS

School

School of Science

Comments

Originally published as : Sazzad, T. M. S., Armstrong, L., & Tripathy, A. K. (2017). An automated ovarian tissue detection approach using type P63 counter stained images to minimize pathology experts observation variability. Paper presented at the Proceedings of the International Conferences on Computer Graphics, Visualization, Computer Vision and Image Processing 2017 and Big Data Analytics, Data Mining and Computational Intelligence 2017 - Part of the Multi Conference on Computer Science and Information Systems 2017, 124-130.

Abstract

Pathology experts are more interested to work and analyze microscopic digitized color images in compare to other available image processing modalities especially electronic ultrasound scanners. Ultrasound has the capability to identify larger sized and more mature sized tissues in compare to smaller ones. Ovarian reproductive tissues are smaller in size in compare to other available tissues in the ovary for which it is hard for ultrasound scanners to analyze ovarian reproductive tissues. Microscopic digitized color images are more viable for which at present most appropriate approach to analyze ovarian reproductive tissues remains microscopic analysis process. Manual analysis process is costly, extensive analysis time requires with observation variations between experts. To improve accuracy and reduce processing time computer based approaches have become popular for the last two decades but mostly to analyze cancer cells. To analyze small ovarian reproductive tissues accurately type P63 counter stained images with 3 different magnifications a fully automated approach is presented in this paper. The study's experimental results have higher accuracy rate in compare to manual analysis and electronic scanners. © 2017.

Share

 
COinS