AUTHOR=Zhao Yongfeng , Huang Tingting , Wang Xian , Chen Qianjun , Shen Hui , Xiong Bei 

TITLE=Measurement for the Area of Red Blood Cells From Microscopic Images Based on Image Processing Technology and Its Applications in Aplastic Anemia, Megaloblastic Anemia, and Myelodysplastic Syndrome

JOURNAL=Frontiers in Medicine

VOLUME=Volume 8 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2021.796920

DOI=10.3389/fmed.2021.796920

ISSN=2296-858X

ABSTRACT=Background: Aplastic anemia (AA), megaloblastic anemia (MA) and myelodysplastic syndrome (MDS) were common anaemic diseases. Sometimes it was difficult to distinguish patients with these diseases.
Methods: In this paper, we proposed one measurement method for the area of RBCs from microscopic images based on image processing technology and analysed the differences of area in 25 AA patients, 64 MA patients and 68 MDS patients. 
Results: The area of RBCs were 44.19±3.88 μm2, 42.09±5.35 μm2, 52.87±7.68 μm2 and 45.75±8.07 μm2 in normal subjects, AA patients, MA patients and MDS patients respectively. The coefficients of variation were 8.78%, 10.05%, 14.53% and 14.00% respectively in these groups. The area of RBCs in MA patients was significantly higher than normal subjects (P<0.001). Compared with AA and MDS patients, the area of RBCs in MA patients was also significantly higher (P<0.001). The results of correlation analysis between the area of RBCs and MCV, MCH, MCHC and RDW showed no significant correlations (P>0.05). The AUC results of ROC curves of RBCs area were 0.421, 0.580, and 0.850 respectively in AA patients (P=0.337), MDS patients (P=0.237) and MA patients (P<0.001).
Conclusion: Identifying the area of RBCs in peripheral blood smears based on the image processing technology could achieve rapid and efficient diagnostic support for MDS and MA patients, especially for MA patients and in combination with MCV. However, a larger sample study is needed to find the cut-off area values.