Title :
A System for Counting Fetal and Maternal Red Blood Cells
Author :
Ji Ge ; Zheng Gong ; Jun Chen ; Jun Liu ; Nguyen, John ; Zongyi Yang ; Chen Wang ; Yu Sun
Author_Institution :
Adv. Micro & Nanosyst. Lab., Univ. of Toronto, Toronto, ON, Canada
Abstract :
The Kleihauer-Betke (KB) test is the standard method for quantitating fetal-maternal hemorrhage in maternal care. In hospitals, the KB test is performed by a certified technologist to count a minimum of 2000 fetal and maternal red blood cells (RBCs) on a blood smear. Manual counting suffers from inherent inconsistency and unreliability. This paper describes a system for automated counting and distinguishing fetal and maternal RBCs on clinical KB slides. A custom-adapted hardware platform is used for KB slide scanning and image capturing. Spatial-color pixel classification with spectral clustering is proposed to separate overlapping cells. Optimal clustering number and total cell number are obtained through maximizing cluster validity index. To accurately identify fetal RBCs from maternal RBCs, multiple features including cell size, roundness, gradient, and saturation difference between cell and whole slide are used in supervised learning to generate feature vectors, to tackle cell color, shape, and contrast variations across clinical KB slides. The results show that the automated system is capable of completing the counting of over 60 000 cells (versus ~2000 by technologists) within 5 min (versus ~15 min by technologists). The throughput is improved by approximately 90 times compared to manual reading by technologists. The counting results are highly accurate and correlate strongly with those from benchmarking flow cytometry measurement.
Keywords :
biomedical equipment; biomedical optical imaging; blood; cellular biophysics; feature extraction; haemodynamics; image classification; image colour analysis; learning (artificial intelligence); medical image processing; obstetrics; optimisation; pattern clustering; separation; vectors; Kleihauer-Betke test; automated RBC counting; benchmarking flow cytometry measurement; blood smear; cell color variation; cell contrast variation; cell roundness feature; cell shape variation; cell size feature; clinical KB slide scanning; cluster validity index maximization; counting time; custom-adapted hardware platform; feature vector generation; fetal RBC classification; fetal RBC identification accuracy; fetal red blood cell counting system; gradient feature; hospital KB test; image capturing; manual RBC counting inconsistency; manual RBC counting unreliability; maternal RBC classification; maternal RBC identification accuracy; maternal care; maternal red blood cell counting system; minimum fetal RBC counting; minimum maternal RBC counting; optimal clustering number; overlapping cell separation; saturation feature; spatial-color pixel classification; spectral clustering; standard fetal-maternal hemorrhage quantitation; supervised learning; time 15 min; time 5 min; total cell number; Blood; Clustering methods; Image color analysis; Image segmentation; Red blood cells; Supervised learning; Throughput; Automation; Kleihauer???Betke (KB) test; fetal red blood cells; fetal-maternal hemorrhage (FMH) quantification; image processing; maternal red blood cells;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
DOI :
10.1109/TBME.2014.2327198
