Automatic Detection and Counting of Blood Cells in Smear Images Using RetinaNet
A complete blood count is one of the significant clinical tests that evaluates overall human health and provides relevant information for disease diagnosis. The conventional strategies of blood cell counting include manual counting as well as counting using the hemocytometer and are tedious and time...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/23/11/1522 |
_version_ | 1797510346798268416 |
---|---|
author | Grzegorz Drałus Damian Mazur Anna Czmil |
author_facet | Grzegorz Drałus Damian Mazur Anna Czmil |
author_sort | Grzegorz Drałus |
collection | DOAJ |
description | A complete blood count is one of the significant clinical tests that evaluates overall human health and provides relevant information for disease diagnosis. The conventional strategies of blood cell counting include manual counting as well as counting using the hemocytometer and are tedious and time-consuming tasks. This research-based paper proposes an automatic software-based alternative method to count blood cells accurately using the RetinaNet deep learning network, which is used to recognize and classify objects in microscopic images. After training, the network automatically recognizes and counts red blood cells, white blood cells, and platelets. We tested a model trained on smear images and found that the trained model has generalized capabilities. We assessed the quality of detection and cell counting using performance measures, such as accuracy, sensitivity, precision, and F1-score. Moreover, we studied the dependence of the confidence thresholds and the number of learning epochs on the obtained results of recognition and counting. We compared the performance of the proposed approach with those obtained by other authors who dealt with the subject of cell counting and show that object detection and labeling can be an additional advantage in the task of counting objects. |
first_indexed | 2024-03-10T05:31:11Z |
format | Article |
id | doaj.art-156ea4456eed438bb1322dcfa9776064 |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-10T05:31:11Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-156ea4456eed438bb1322dcfa97760642023-11-22T23:16:12ZengMDPI AGEntropy1099-43002021-11-012311152210.3390/e23111522Automatic Detection and Counting of Blood Cells in Smear Images Using RetinaNetGrzegorz Drałus0Damian Mazur1Anna Czmil2Department of Electrical and Computer Engineering Fundamentals, Rzeszow University of Technology, 35-959 Rzeszow, PolandDepartment of Electrical and Computer Engineering Fundamentals, Rzeszow University of Technology, 35-959 Rzeszow, PolandDepartment of Electrical and Computer Engineering Fundamentals, Rzeszow University of Technology, 35-959 Rzeszow, PolandA complete blood count is one of the significant clinical tests that evaluates overall human health and provides relevant information for disease diagnosis. The conventional strategies of blood cell counting include manual counting as well as counting using the hemocytometer and are tedious and time-consuming tasks. This research-based paper proposes an automatic software-based alternative method to count blood cells accurately using the RetinaNet deep learning network, which is used to recognize and classify objects in microscopic images. After training, the network automatically recognizes and counts red blood cells, white blood cells, and platelets. We tested a model trained on smear images and found that the trained model has generalized capabilities. We assessed the quality of detection and cell counting using performance measures, such as accuracy, sensitivity, precision, and F1-score. Moreover, we studied the dependence of the confidence thresholds and the number of learning epochs on the obtained results of recognition and counting. We compared the performance of the proposed approach with those obtained by other authors who dealt with the subject of cell counting and show that object detection and labeling can be an additional advantage in the task of counting objects.https://www.mdpi.com/1099-4300/23/11/1522confidence thresholdconvolution neural networksplateletRBCWBC |
spellingShingle | Grzegorz Drałus Damian Mazur Anna Czmil Automatic Detection and Counting of Blood Cells in Smear Images Using RetinaNet Entropy confidence threshold convolution neural networks platelet RBC WBC |
title | Automatic Detection and Counting of Blood Cells in Smear Images Using RetinaNet |
title_full | Automatic Detection and Counting of Blood Cells in Smear Images Using RetinaNet |
title_fullStr | Automatic Detection and Counting of Blood Cells in Smear Images Using RetinaNet |
title_full_unstemmed | Automatic Detection and Counting of Blood Cells in Smear Images Using RetinaNet |
title_short | Automatic Detection and Counting of Blood Cells in Smear Images Using RetinaNet |
title_sort | automatic detection and counting of blood cells in smear images using retinanet |
topic | confidence threshold convolution neural networks platelet RBC WBC |
url | https://www.mdpi.com/1099-4300/23/11/1522 |
work_keys_str_mv | AT grzegorzdrałus automaticdetectionandcountingofbloodcellsinsmearimagesusingretinanet AT damianmazur automaticdetectionandcountingofbloodcellsinsmearimagesusingretinanet AT annaczmil automaticdetectionandcountingofbloodcellsinsmearimagesusingretinanet |