Classification of blood cells into white blood cells and red blood cells from blood smear images using machine learning techniques

Navya, K. T.; Prasad, Keerthana; Singh, Brij Mohan Kumar

doi:10.1109/gcat52182.2021.9587524

“…There are two types of machine learning techniques: supervised and unsupervised. In supervised learning, the correct result or where the model should originate from the data is known; however, in unsupervised learning, the model must deal with unstructured input and no obvious outcome (RASCHKA, 2015) [ 8 ].…”

Section: Theoretical Approachmentioning

confidence: 99%

Detection of WBC, RBC, and Platelets in Blood Samples Using Deep Learning

Alhazmi

¹

2022

BioMed Research International

View full text Add to dashboard Cite

A blood count is one of the most important diagnostic tools in medicine and one of the most common procedures. It can reveal important changes in the body and is commonly used as the first stage in the process of evaluating patients’ health. Even though this is a common practice, delivering examinations in laboratories can be difficult due to the availability of expensive technology that requires frequent maintenance. This study is developing an alternative deep learning computational model capable of automatically detecting cells in images of blood samples. Using object detection libraries, it was possible to train a model that was focused on this task and capable of detecting cells in images with adequate accuracy. When the identification of cells in images of blood samples was taken into account in the best results obtained, it was possible to count white cells with an accuracy of one hundred percent, red cells with an accuracy of 89%, and platelets with an accuracy of 96%, which generated subsidies to develop the primary components of a blood count. The components that were supposed to classify the various types of white cells were not carried out due to the limits of the dataset provided. On the other hand, the study can be broadened to include further works that deal with this issue because it produced satisfactory results.

show abstract

“…Furthermore, high RDW has emerged as a risk factor in clinical nephrology, including patients on hemodialysis and those with acute kidney injury requiring continuous renal replacement treatment. According to Navya et al [4], a gradual increase in RDW predicts mortality and cardiovascular events in end-stage renal disease. Elevated RDW implies more significant size variability in red blood cells, indicating a defective erythrocyte or a shortened erythrocyte life span.…”

Section: Clinical Significance Of Red Blood Cell Analysismentioning

confidence: 99%

Performing Red Blood Cell Count Using Video Capillaroscopy and Analyzing the Data Using MATLAB Software

Fesharakinia

2024

Preprint

0

View full text Add to dashboard Cite

<p>Complete blood cell count (CBC) is one of the most common blood tests. The current CBC is performed invasively through puncture of the skin drawing blood sample, which can put cancer patients and immunocompromised patients at risk of infection and hospitalization. Also, people with Hemophilia might suffer from bleeding after capillary puncture for up to 4 hours. By performing capillaroscopy, (a non-invasive technique to visualize capillaries) and by processing and analyzing the data via software such as MATLAB, we hypothesized that we would be able to provide Red Blood Cell (RBC) counting without skin puncture thus acquiring valuable information about one's health non-invasively. The size of a blood capillary is comparable with a RBC size, which means that we can observe RBC in the capillaries cell by cell. Focusing on nailfold capillaries, we can monitor single capillaries across a field of view (FOV). Separating and quantifying the light absorption gaps in the nail capillaries in vivo is an effective tool for counting the number of red blood cells in the body and diagnosing disorders caused by a deficiency or increase of RBCs. In this project, we have processed video footage of nail fold capillaries via MATLAB and were able to detect and count red blood cells in-vivo.</p>

show abstract

“…Furthermore, high RDW has emerged as a risk factor in clinical nephrology, including patients on hemodialysis and those with acute kidney injury requiring continuous renal replacement treatment. According to Navya et al [4], a gradual increase in RDW predicts mortality and cardiovascular events in end-stage renal disease. Elevated RDW implies more significant size variability in red blood cells, indicating a defective erythrocyte or a shortened erythrocyte life span.…”

Section: Clinical Significance Of Red Blood Cell Analysismentioning

confidence: 99%

Performing Red Blood Cell Count Using Video Capillaroscopy and Analyzing the Data Using MATLAB Software

Fesharakinia

2024

Preprint

0

View full text Add to dashboard Cite

<p>Complete blood cell count (CBC) is one of the most common blood tests. The current CBC is performed invasively through puncture of the skin drawing blood sample, which can put cancer patients and immunocompromised patients at risk of infection and hospitalization. Also, people with Hemophilia might suffer from bleeding after capillary puncture for up to 4 hours. By performing capillaroscopy, (a non-invasive technique to visualize capillaries) and by processing and analyzing the data via software such as MATLAB, we hypothesized that we would be able to provide Red Blood Cell (RBC) counting without skin puncture thus acquiring valuable information about one's health non-invasively. The size of a blood capillary is comparable with a RBC size, which means that we can observe RBC in the capillaries cell by cell. Focusing on nailfold capillaries, we can monitor single capillaries across a field of view (FOV). Separating and quantifying the light absorption gaps in the nail capillaries in vivo is an effective tool for counting the number of red blood cells in the body and diagnosing disorders caused by a deficiency or increase of RBCs. In this project, we have processed video footage of nail fold capillaries via MATLAB and were able to detect and count red blood cells in-vivo.</p>

show abstract

Classification of blood cells into white blood cells and red blood cells from blood smear images using machine learning techniques

Cited by 7 publications

References 11 publications

Detection of WBC, RBC, and Platelets in Blood Samples Using Deep Learning

Detection of WBC, RBC, and Platelets in Blood Samples Using Deep Learning

Performing Red Blood Cell Count Using Video Capillaroscopy and Analyzing the Data Using MATLAB Software

Performing Red Blood Cell Count Using Video Capillaroscopy and Analyzing the Data Using MATLAB Software

Contact Info

Product

Resources

About