Leukemia detection using Artificial Neural Networks in Images of Human Blood Sample
This article presents a preliminary report that uses minuscule images of blood tests to develop a diagnosis of leukemia. Examining through images is crucial since illnesses can be recognized and examined at an earlier stage using the images. The framework will be centered on leukemia and white bloo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Alsalam university college
2024-02-01
|
| Series: | Al-SalamJournal for Medical Science |
| Subjects: | |
| Online Access: | http://journal.alsalam.edu.iq/index.php/ajbms/article/view/235 |
| _version_ | 1797214476308578304 |
|---|---|
| author | Hakar J. Mohamed Salih Jahwar Y. Arif Shaimaa Q. Sabri Ghada A. Taqa Ahmet Çınar |
| author_facet | Hakar J. Mohamed Salih Jahwar Y. Arif Shaimaa Q. Sabri Ghada A. Taqa Ahmet Çınar |
| author_sort | Hakar J. Mohamed Salih |
| collection | DOAJ |
| description |
This article presents a preliminary report that uses minuscule images of blood tests to develop a diagnosis of leukemia. Examining through images is crucial since illnesses can be recognized and examined at an earlier stage using the images. The framework will be centered on leukemia and white blood cell illness. In fact, even the hematologist has trouble organizing the leukemic cells, and manually arranging the platelets takes a long time and is quite loose. In this way, early detection of leukemia recurrence allows the patient to receive the appropriate treatment. In order to address this problem, the framework will make use of the capabilities in small images and examine surface, geometry, shading, and quantifiable investigation modifications. These features' variations will be utilized as the classifier input. has transformed the use of images K proposes that (NN) and agglomeration. Examining a wide range of failure measures and increasing the intricacy of every system, the findings are examined. Utilizing feedforward (NN), image division is accomplished with less noise and a very sluggish conjunction rate. K-means agglomeration and (ANN) are intentionally used in this analysis to create a collection of processes that will work together to produce a much better presentation in (IS). An analysis has been conducted to determine the best rule for (IS).
|
| first_indexed | 2024-04-24T11:14:47Z |
| format | Article |
| id | doaj.art-3fc287f5a7e44a878bc44c451d3934df |
| institution | Directory Open Access Journal |
| issn | 2958-0870 2959-5398 |
| language | English |
| last_indexed | 2024-04-24T11:14:47Z |
| publishDate | 2024-02-01 |
| publisher | Alsalam university college |
| record_format | Article |
| series | Al-SalamJournal for Medical Science |
| spelling | doaj.art-3fc287f5a7e44a878bc44c451d3934df2024-04-11T09:22:11ZengAlsalam university collegeAl-SalamJournal for Medical Science2958-08702959-53982024-02-013210.55145/ajbms.2024.03.02.01Leukemia detection using Artificial Neural Networks in Images of Human Blood SampleHakar J. Mohamed Salih0Jahwar Y. Arif1Shaimaa Q. Sabri2Ghada A. Taqa3Ahmet Çınar4 Department of Computer Sciences, College of Science, University of Zakho, Duhok, IraqDepartment of Computer Sciences, College of Science, University of Zakho, Duhok, IraqDepartment of Computer Sciences, College of Science, University of Zakho, Duhok, IraqDepartment of Dental Basic Sciences, College of Dentistry, University of Mosul, Mosul, IraqDepartment of Computer Engineering, College of Engineering, Fırat, University, Elazığ, Türkiye This article presents a preliminary report that uses minuscule images of blood tests to develop a diagnosis of leukemia. Examining through images is crucial since illnesses can be recognized and examined at an earlier stage using the images. The framework will be centered on leukemia and white blood cell illness. In fact, even the hematologist has trouble organizing the leukemic cells, and manually arranging the platelets takes a long time and is quite loose. In this way, early detection of leukemia recurrence allows the patient to receive the appropriate treatment. In order to address this problem, the framework will make use of the capabilities in small images and examine surface, geometry, shading, and quantifiable investigation modifications. These features' variations will be utilized as the classifier input. has transformed the use of images K proposes that (NN) and agglomeration. Examining a wide range of failure measures and increasing the intricacy of every system, the findings are examined. Utilizing feedforward (NN), image division is accomplished with less noise and a very sluggish conjunction rate. K-means agglomeration and (ANN) are intentionally used in this analysis to create a collection of processes that will work together to produce a much better presentation in (IS). An analysis has been conducted to determine the best rule for (IS). http://journal.alsalam.edu.iq/index.php/ajbms/article/view/235Blood CellsBone MarrowArtificial NervesLook at blood cell |
| spellingShingle | Hakar J. Mohamed Salih Jahwar Y. Arif Shaimaa Q. Sabri Ghada A. Taqa Ahmet Çınar Leukemia detection using Artificial Neural Networks in Images of Human Blood Sample Al-SalamJournal for Medical Science Blood Cells Bone Marrow Artificial Nerves Look at blood cell |
| title | Leukemia detection using Artificial Neural Networks in Images of Human Blood Sample |
| title_full | Leukemia detection using Artificial Neural Networks in Images of Human Blood Sample |
| title_fullStr | Leukemia detection using Artificial Neural Networks in Images of Human Blood Sample |
| title_full_unstemmed | Leukemia detection using Artificial Neural Networks in Images of Human Blood Sample |
| title_short | Leukemia detection using Artificial Neural Networks in Images of Human Blood Sample |
| title_sort | leukemia detection using artificial neural networks in images of human blood sample |
| topic | Blood Cells Bone Marrow Artificial Nerves Look at blood cell |
| url | http://journal.alsalam.edu.iq/index.php/ajbms/article/view/235 |
| work_keys_str_mv | AT hakarjmohamedsalih leukemiadetectionusingartificialneuralnetworksinimagesofhumanbloodsample AT jahwaryarif leukemiadetectionusingartificialneuralnetworksinimagesofhumanbloodsample AT shaimaaqsabri leukemiadetectionusingartificialneuralnetworksinimagesofhumanbloodsample AT ghadaataqa leukemiadetectionusingartificialneuralnetworksinimagesofhumanbloodsample AT ahmetcınar leukemiadetectionusingartificialneuralnetworksinimagesofhumanbloodsample |