An Efficient Convolutional Neural Network to Detect and Count Blood Cells
Blood cell analysis is an important part of the health and immunity assessment. There are three major components of the blood: red blood cells, white blood cells, and platelets. The count and density of these blood cells are used to find multiple disorders like blood infections (anemia, leukemia, am...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | Spanish |
| Published: |
Universidad Nacional, Costa Rica
2022-03-01
|
| Series: | Uniciencia |
| Subjects: | |
| Online Access: | https://www.revistas.una.ac.cr/index.php/uniciencia/article/view/16303 |
| _version_ | 1828217989567086592 |
|---|---|
| author | Rakesh Chandra Joshi Saumya Yadav Malay Kishore Dutta Carlos M. Travieso-González |
| author_facet | Rakesh Chandra Joshi Saumya Yadav Malay Kishore Dutta Carlos M. Travieso-González |
| author_sort | Rakesh Chandra Joshi |
| collection | DOAJ |
| description | Blood cell analysis is an important part of the health and immunity assessment. There are three major components of the blood: red blood cells, white blood cells, and platelets. The count and density of these blood cells are used to find multiple disorders like blood infections (anemia, leukemia, among others). Traditional methods are time-consuming, and the test cost is high. Thus, it arises the need for automated methods that can detect different kinds of blood cells and count the number of cells. A convolutional neural network-based framework is proposed for detecting and counting the cells. The neural network is trained for the multiple iterations, and a model having lower validation loss is saved. The experiments are done to analyze the performance of the detection system and results with high accuracy in the counting of the cells. The mean average precision is achieved when compared to ground truth provided to respective labels. The value of the average precision is found to be ranging from 70% to 99.1%, with a mean average precision value of 85.35%. The proposed framework had much less time complexity: it took only 0.111 seconds to process an image frame with dimensions of 640×480 pixels. The system can also be implemented in low-cost, single-board computers for rapid prototyping. The efficiency of the proposed framework to identify and count different blood cells can be utilized to assist medical professionals in finding disorders and making decisions based on the obtained report. |
| first_indexed | 2024-04-12T15:56:43Z |
| format | Article |
| id | doaj.art-f9c21f3ed4c542cfab97d70c21830a5e |
| institution | Directory Open Access Journal |
| issn | 2215-3470 |
| language | Spanish |
| last_indexed | 2024-04-12T15:56:43Z |
| publishDate | 2022-03-01 |
| publisher | Universidad Nacional, Costa Rica |
| record_format | Article |
| series | Uniciencia |
| spelling | doaj.art-f9c21f3ed4c542cfab97d70c21830a5e2022-12-22T03:26:21ZspaUniversidad Nacional, Costa RicaUniciencia2215-34702022-03-0136111110.15359/ru.36-1.2816303An Efficient Convolutional Neural Network to Detect and Count Blood CellsRakesh Chandra Joshi0Saumya Yadav1Malay Kishore Dutta2Carlos M. Travieso-González3Abdul Kalam Technical UniversityAbdul Kalam Technical UniversityAbdul Kalam Technical UniversityUniversity of Las Palmas de Gran CanariaBlood cell analysis is an important part of the health and immunity assessment. There are three major components of the blood: red blood cells, white blood cells, and platelets. The count and density of these blood cells are used to find multiple disorders like blood infections (anemia, leukemia, among others). Traditional methods are time-consuming, and the test cost is high. Thus, it arises the need for automated methods that can detect different kinds of blood cells and count the number of cells. A convolutional neural network-based framework is proposed for detecting and counting the cells. The neural network is trained for the multiple iterations, and a model having lower validation loss is saved. The experiments are done to analyze the performance of the detection system and results with high accuracy in the counting of the cells. The mean average precision is achieved when compared to ground truth provided to respective labels. The value of the average precision is found to be ranging from 70% to 99.1%, with a mean average precision value of 85.35%. The proposed framework had much less time complexity: it took only 0.111 seconds to process an image frame with dimensions of 640×480 pixels. The system can also be implemented in low-cost, single-board computers for rapid prototyping. The efficiency of the proposed framework to identify and count different blood cells can be utilized to assist medical professionals in finding disorders and making decisions based on the obtained report.https://www.revistas.una.ac.cr/index.php/uniciencia/article/view/16303convolutional neural networkdeep learningplateletsred blood cellswhite blood cells |
| spellingShingle | Rakesh Chandra Joshi Saumya Yadav Malay Kishore Dutta Carlos M. Travieso-González An Efficient Convolutional Neural Network to Detect and Count Blood Cells Uniciencia convolutional neural network deep learning platelets red blood cells white blood cells |
| title | An Efficient Convolutional Neural Network to Detect and Count Blood Cells |
| title_full | An Efficient Convolutional Neural Network to Detect and Count Blood Cells |
| title_fullStr | An Efficient Convolutional Neural Network to Detect and Count Blood Cells |
| title_full_unstemmed | An Efficient Convolutional Neural Network to Detect and Count Blood Cells |
| title_short | An Efficient Convolutional Neural Network to Detect and Count Blood Cells |
| title_sort | efficient convolutional neural network to detect and count blood cells |
| topic | convolutional neural network deep learning platelets red blood cells white blood cells |
| url | https://www.revistas.una.ac.cr/index.php/uniciencia/article/view/16303 |
| work_keys_str_mv | AT rakeshchandrajoshi anefficientconvolutionalneuralnetworktodetectandcountbloodcells AT saumyayadav anefficientconvolutionalneuralnetworktodetectandcountbloodcells AT malaykishoredutta anefficientconvolutionalneuralnetworktodetectandcountbloodcells AT carlosmtraviesogonzalez anefficientconvolutionalneuralnetworktodetectandcountbloodcells AT rakeshchandrajoshi efficientconvolutionalneuralnetworktodetectandcountbloodcells AT saumyayadav efficientconvolutionalneuralnetworktodetectandcountbloodcells AT malaykishoredutta efficientconvolutionalneuralnetworktodetectandcountbloodcells AT carlosmtraviesogonzalez efficientconvolutionalneuralnetworktodetectandcountbloodcells |