TY - JOUR
T1 - ErythroidCounter: an automatic pipeline for erythroid cell detection, identification and counting based on deep learning
AU - Zhou, You
AU - Wang, Ye
AU - Wu, Junhui
AU - Hassan, Muhammad
AU - Pang, Wei
AU - Lv, Lili
AU - Wang, Liupu
AU - Cui, Honghua
N1 - Funding Information:
This research is supported by the National Natural Science Foundation of China (Grants Nos. 61772227, 61972174, 61972175), Science and Technology Development Foundation of Jilin Province (No. 20180201045GX, 20200201300JC, 20200401083GX, 20200201163JC), the Jilin Development and Reform Commission Fund (No. 2020C020-2).
Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2022/7
Y1 - 2022/7
N2 - The detection, identification and counting of bone marrow erythroid cells are vital for evaluating the health status and therapeutic schedules of patients with leukemia or hematopathy. However, traditional methods used in hospitals are still based on chemical reagent staining, manual detection and counting with the help of laboratory equipment. And therefore, these methods are time-consuming, laborious, and tedious. The development of deep learning in the field of image processing makes it possible for effective automated detection and classification of erythroid cells. In this research, we proposed a pipeline called ErythroidCounter, which is based on deep learning approaches to perform fully automated detection and classification of erythroid cells. ErythroidCounter is composed of the detection and extraction module (DEM) followed by classification and counting module (CCM). DEM adapts RetinaNet to locate and detect erythroid cells, and it transmits the detected cell images into CCM, while CCM is based on the DenseNet-121 architecture to perform classification and counting., which has close match in terms of classification accuracy compared to manual examination. When classifying erythroid cells, the ErythroidCounter achieved an accuracy of 86.33%, recall of 87.45%, precision of 87.16%, and F1 score of 87.30%. When detecting erythroid cells, ErythroidCounter achieved an precision of 90.7%, recall of 91.3%, and F1 score of 90.9%. EythroidCounter is robust to underlying color images, cell densities, and cell positions. To the best of our knowledge, this is the first automatic approach for erythroid cell detection, classification, and counting in real clinical scenarios, and it can be used as an assistive tool for medical examinations.
AB - The detection, identification and counting of bone marrow erythroid cells are vital for evaluating the health status and therapeutic schedules of patients with leukemia or hematopathy. However, traditional methods used in hospitals are still based on chemical reagent staining, manual detection and counting with the help of laboratory equipment. And therefore, these methods are time-consuming, laborious, and tedious. The development of deep learning in the field of image processing makes it possible for effective automated detection and classification of erythroid cells. In this research, we proposed a pipeline called ErythroidCounter, which is based on deep learning approaches to perform fully automated detection and classification of erythroid cells. ErythroidCounter is composed of the detection and extraction module (DEM) followed by classification and counting module (CCM). DEM adapts RetinaNet to locate and detect erythroid cells, and it transmits the detected cell images into CCM, while CCM is based on the DenseNet-121 architecture to perform classification and counting., which has close match in terms of classification accuracy compared to manual examination. When classifying erythroid cells, the ErythroidCounter achieved an accuracy of 86.33%, recall of 87.45%, precision of 87.16%, and F1 score of 87.30%. When detecting erythroid cells, ErythroidCounter achieved an precision of 90.7%, recall of 91.3%, and F1 score of 90.9%. EythroidCounter is robust to underlying color images, cell densities, and cell positions. To the best of our knowledge, this is the first automatic approach for erythroid cell detection, classification, and counting in real clinical scenarios, and it can be used as an assistive tool for medical examinations.
KW - Bone marrow erythroid cell
KW - Cell classification
KW - Cell detection
KW - Deep learning
UR - http://www.scopus.com/inward/record.url?scp=85126901907&partnerID=8YFLogxK
U2 - 10.1007/s11042-022-12209-3
DO - 10.1007/s11042-022-12209-3
M3 - Article
SN - 1380-7501
VL - 81
SP - 25541
EP - 25556
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
IS - 18
ER -