Journal article Open Access

Deep Categorization of Blood Cells using Depthwise Convolutions

T Sudarshan Rao; N Rohan Sai; D Koteswara Rao

Sponsor(s)
Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP)

Modern-day computation has become indispensable in the healthcare industry. From medical image processing to cost reduction, Artificial Intelligence has proved its significance in solving complex healthcare problems. One of the primary areas in which it can be of greater use in hematology. Categorization of white-blood cells is imperative to pre-identify abnormalities. Through this paper, we collected image samples for 4 major White Blood cell groups, which are Neutrophils, Lymphocytes, Monocytes, and Eosinophils. The aim of this research is to put forward an intelligent system that efficiently alleviates the stringent requirement of a cytological study. The proposed system classifies 4 white-blood-cell types based on their morphological variation. With the experimental modulations that we chose to integrate, the presented model attained an accuracy of 97%.

Files (439.8 kB)
Name Size
L957410101221.pdf
md5:baa8ad620a603a6df893c3073e461660
439.8 kB Download
26
22
views
downloads
Views 26
Downloads 22
Data volume 9.7 MB
Unique views 19
Unique downloads 22

Share

Cite as