Automatic Leukemia Identification System Using Otsu Image segmentation and MSER Approach for Microscopic Smear Image Database

In the current era of medical image processing, identification of blood disorder through visual observation is the most difficult job. The observation based disorder identification has been the approximation task. The haematological disorders of white blood cells (WBC) are really frequent in medical...

Full description

Saved in:

Bibliographic Details
Published in:	2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT) pp. 267 - 272
Main Authors:	Rege, M.V., Abdulkareem, Mohammed Basil, Gaikwad, Santosh, Gawli, B.W.
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-04-2018
Subjects:	Biomedical imaging Blood FAR Feature extraction FRR Image databases Image segmentation Leukemia Maximally Stable Extremely Region (MSER) Microscopic Microscopy Otsu Smear
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	In the current era of medical image processing, identification of blood disorder through visual observation is the most difficult job. The observation based disorder identification has been the approximation task. The haematological disorders of white blood cells (WBC) are really frequent in medical practices. From the recognition of blood disorders, it can contribute to the categorization of certain diseases related to blood. With automated leukemia identification, medical expert can keep off the complexity of the environment and focus along the important medical information that this image provides. We aim for development of automated identification of leukemia using microscopic blood smear image database. The computer based identification for leukemia detection has reduced the chances of error. The early identification of leukemia dieses plays a significant role because monitoring and prevention is possible in concern patients. This proposed scheme uses the most significant steps of image processing such as pre-processing, segmentation and matching. The leukemia smear image database is segmented using Otsu image segmentation and Maximally Stable Extremely Regions (MSER) technique employed for image pattern matching. The performance of the system is tested using false acceptance rate (FAR) and false rejection Rate (FRR). The proposed system reported accuracy of 95.12% where FAR is 5.0% and FRR is 4.75%. The author recommended the Otsu image segmentation and MSER image matching is the robust and dynamic approach for leukemia identification.
DOI:	10.1109/ICICCT.2018.8473101