Microscopic Blood Smear Segmentation and Classification Using Deep Contour Aware CNN and Extreme Machine Learning

Muhammad Imran Razzak, Saeeda Naz; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 49-55

Abstract


Recent advancement in genomic technologies has opened a new realm for early detection of diseases that shows potential to overcome the drawbacks of manual detection technologies. In this work, we have presented efficient contour aware segmentation approach based based on fully conventional network whereas for classification we have used extreme machine learning based on CNN features extracted from each segmented cell. We have evaluated system performance based on segmentation and classification on publicly available dataset. Experiment was conducted on 64000 blood cells and dataset is divided into 80% for training and 20% for testing. Segmentation results are compared with the manual segmentation and found that proposed approach provided with 98.12% and 98.16% for RBC and WBC respectively whereas classification accuracy is shown on publicly available dataset 94.71% and 98.68% for RBC \& its abnormalities detection and WBC respectively.

Related Material


[pdf]
[bibtex]
@InProceedings{Razzak_2017_CVPR_Workshops,
author = {Imran Razzak, Muhammad and Naz, Saeeda},
title = {Microscopic Blood Smear Segmentation and Classification Using Deep Contour Aware CNN and Extreme Machine Learning},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}