ABO/Rh Blood Typing Method for Samples in Microscope Slides by Using Image Processing

The correct determination of blood groups is very important to prevent complications during transfusion practices, since cannot exists incompatibility between donor and blood receiver. The ABO and Rh blood group systems currently are the most used, because allow to get results in a simple and low co...

Full description

Saved in:
Bibliographic Details
Published in:Revista IEEE América Latina 2018-03, Vol.16 (3), p.885-890
Main Authors: Porge Xavier, Felipe, de Araujo Silva, Lucas Gabriel, Miranda Regis, Carlos Danilo
Format: Article
Language:English
Subjects:
ABO and Rh Systems
Android
Blood
Blood Groups
Digital Image Processing
Digital imaging
High resolution
IEEE transactions
Image processing
Image resolution
Incompatibility
Irrigation
Microscopy
OpenCV
Pictures
Plasmas
Reagents
Transfusion
Webcams
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The correct determination of blood groups is very important to prevent complications during transfusion practices, since cannot exists incompatibility between donor and blood receiver. The ABO and Rh blood group systems currently are the most used, because allow to get results in a simple and low cost way. This work presents a method for blood typing of lamina samples using digital image processing. During samples analysis (48 samples of 30 different patients with 18 high resolution pictures taken with a 5 Megapixels camera and 30 low resolution pictures taken with a webcam 640x360 pixels), the proposed method presented a hit ratio of 97.92% for Anti- A samples with sensibility of 100% and specificity of 96,3%. The hit ratio presented in Anti-B tests was 89.58% with a sensibility of 83.33% and specificity of 92,86%. During Anti- D reagent analysis, the developed method presented a better efficacy in high resolution pictures analysis, with 88.89% of hit ratio, 84.62% of sensibility and 100% of specificity.
ISSN:1548-0992
1548-0992
DOI:10.1109/TLA.2018.8358669