Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease.

Recently, the transfer learning technique has proved to be powerful in enhancing the development of deep learning methods for sickle cell disease (SCD) detection as a complement to the clinical method where a hemoglobin electrophoresis machine is used. This is evidenced by some models and algorithms...

Full description

Saved in:
Bibliographic Details
Main Authors: Mabirizi, Vicent, Kawuma, Simon, Kyarisiima, Addah, Bamutura, David, Atwiine, Barnabas, Nanjebe, Deborah, Oyesigye, Adolf Mukama
Format: Article
Language:en_US
Published: Kabale University 2024
Subjects:
Online Access:http://hdl.handle.net/20.500.12493/2001
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1813635238804324353
author Mabirizi, Vicent
Kawuma, Simon
Kyarisiima, Addah
Bamutura, David
Atwiine, Barnabas
Nanjebe, Deborah
Oyesigye, Adolf Mukama
author_facet Mabirizi, Vicent
Kawuma, Simon
Kyarisiima, Addah
Bamutura, David
Atwiine, Barnabas
Nanjebe, Deborah
Oyesigye, Adolf Mukama
author_sort Mabirizi, Vicent
collection KAB-DR
description Recently, the transfer learning technique has proved to be powerful in enhancing the development of deep learning methods for sickle cell disease (SCD) detection as a complement to the clinical method where a hemoglobin electrophoresis machine is used. This is evidenced by some models and algorithms with ≥90% prediction accuracy. From the literature, most of the proposed methods are trained and tested on pre-trained deep learning models like VGG16, VGG19, ResNet, Inception_V3, and ReNet. However, training and testing of these methods are limited to one model and separate datasets which may lead to biased results due to implementation in a variation of these models which affects the results produced. To this end, there exists a need to evaluate the SCD models using the same dataset. Thus, in this research study, we carried out a comparative investigation and evaluated predominate pre-trained models used to detect SCD using the same dataset to ascertain which one has the best accuracy. We used a secondary dataset obtained from an online dataset. In our study, we have discovered that Inception V3 yielded the highest accuracy of 97.3% followed by VGG19 at 97.0%, VGG16 at 91%, ResNet50 at 82% and ReNet at 67%, and the CNN-scratch model achieved 81% accuracy. Results from our study will aid researchers and industry practitioners in making decisions on the best deep-learning model to use while detecting SCD.
format Article
id oai:idr.kab.ac.ug:20.500.12493-2001
institution KAB-DR
language en_US
publishDate 2024
publisher Kabale University
record_format dspace
spelling oai:idr.kab.ac.ug:20.500.12493-20012024-08-01T00:01:18Z Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease. Mabirizi, Vicent Kawuma, Simon Kyarisiima, Addah Bamutura, David Atwiine, Barnabas Nanjebe, Deborah Oyesigye, Adolf Mukama Deep Learning Techniques Models Sickle Cell Disease Detection Recently, the transfer learning technique has proved to be powerful in enhancing the development of deep learning methods for sickle cell disease (SCD) detection as a complement to the clinical method where a hemoglobin electrophoresis machine is used. This is evidenced by some models and algorithms with ≥90% prediction accuracy. From the literature, most of the proposed methods are trained and tested on pre-trained deep learning models like VGG16, VGG19, ResNet, Inception_V3, and ReNet. However, training and testing of these methods are limited to one model and separate datasets which may lead to biased results due to implementation in a variation of these models which affects the results produced. To this end, there exists a need to evaluate the SCD models using the same dataset. Thus, in this research study, we carried out a comparative investigation and evaluated predominate pre-trained models used to detect SCD using the same dataset to ascertain which one has the best accuracy. We used a secondary dataset obtained from an online dataset. In our study, we have discovered that Inception V3 yielded the highest accuracy of 97.3% followed by VGG19 at 97.0%, VGG16 at 91%, ResNet50 at 82% and ReNet at 67%, and the CNN-scratch model achieved 81% accuracy. Results from our study will aid researchers and industry practitioners in making decisions on the best deep-learning model to use while detecting SCD. 2024-05-27T14:29:34Z 2024-05-27T14:29:34Z 2023 Article Mabirizi, V. et al. (2023). Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease. Kabale: Kabale University. http://hdl.handle.net/20.500.12493/2001 en_US application/pdf Kabale University
spellingShingle Deep Learning
Techniques
Models
Sickle Cell Disease
Detection
Mabirizi, Vicent
Kawuma, Simon
Kyarisiima, Addah
Bamutura, David
Atwiine, Barnabas
Nanjebe, Deborah
Oyesigye, Adolf Mukama
Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease.
title Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease.
title_full Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease.
title_fullStr Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease.
title_full_unstemmed Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease.
title_short Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease.
title_sort comparison of deep learning techniques in detection of sickle cell disease
topic Deep Learning
Techniques
Models
Sickle Cell Disease
Detection
url http://hdl.handle.net/20.500.12493/2001
work_keys_str_mv AT mabirizivicent comparisonofdeeplearningtechniquesindetectionofsicklecelldisease
AT kawumasimon comparisonofdeeplearningtechniquesindetectionofsicklecelldisease
AT kyarisiimaaddah comparisonofdeeplearningtechniquesindetectionofsicklecelldisease
AT bamuturadavid comparisonofdeeplearningtechniquesindetectionofsicklecelldisease
AT atwiinebarnabas comparisonofdeeplearningtechniquesindetectionofsicklecelldisease
AT nanjebedeborah comparisonofdeeplearningtechniquesindetectionofsicklecelldisease
AT oyesigyeadolfmukama comparisonofdeeplearningtechniquesindetectionofsicklecelldisease