Enhancing malaria detection and classification using convolutional neural networks-vision transformer architecture
Abstract Malaria remains a significant global health challenge, particularly in sub-Saharan Africa. Despite advancements in treatment and prevention, malaria continues to cause substantial morbidity and mortality, particularly among vulnerable populations such as children and pregnant women. Althoug...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-06-01
|
| Series: | Discover Applied Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s42452-025-06704-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850137832392228864 |
|---|---|
| author | Emmanuel Ahishakiye Fredrick Kanobe Danison Taremwa Bartha Alexandra Nantongo Leonard Nkalubo Shallon Ahimbisibwe |
| author_facet | Emmanuel Ahishakiye Fredrick Kanobe Danison Taremwa Bartha Alexandra Nantongo Leonard Nkalubo Shallon Ahimbisibwe |
| author_sort | Emmanuel Ahishakiye |
| collection | DOAJ |
| description | Abstract Malaria remains a significant global health challenge, particularly in sub-Saharan Africa. Despite advancements in treatment and prevention, malaria continues to cause substantial morbidity and mortality, particularly among vulnerable populations such as children and pregnant women. Although effective, traditional diagnostic methods, such as microscopy, are time-consuming and require skilled personnel prone to human error, leading to delays in diagnosis and treatment. More so, existing machine learning models used in malaria detection and classification have low performance and overfitting issues. This study presents an enhanced malaria detection and classification model using an ensemble of Convolutional Neural Networks (CNN) and Vision Transformers (ViT). The proposed ensemble model, which combines CNN and ViT, outperforms each individual model, achieving an accuracy of 99.64%, precision of 99.23%, recall of 99.75%, F1 score of 99.51%, and a cross-entropy loss of 0.01. The proposed model demonstrated superior performance compared to those reported in the literature. These results highlight the potential of the CNN-ViT ensemble model for accurate and reliable malaria detection, offering a significant improvement over existing methods. |
| format | Article |
| id | doaj-art-3c8c445931044ddab0b6cf0461c602d6 |
| institution | OA Journals |
| issn | 3004-9261 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Springer |
| record_format | Article |
| series | Discover Applied Sciences |
| spelling | doaj-art-3c8c445931044ddab0b6cf0461c602d62025-08-20T02:30:43ZengSpringerDiscover Applied Sciences3004-92612025-06-017612210.1007/s42452-025-06704-zEnhancing malaria detection and classification using convolutional neural networks-vision transformer architectureEmmanuel Ahishakiye0Fredrick Kanobe1Danison Taremwa2Bartha Alexandra Nantongo3Leonard Nkalubo4Shallon Ahimbisibwe5Department of Networks, Data Science and Artificial Intelligence, Kyambogo UniversityDepartment of Computer Science, Kyambogo UniversityDepartment of Computer Science, Kyambogo UniversityDepartment of Computer Science, Kyambogo UniversityDepartment of Networks, Data Science and Artificial Intelligence, Kyambogo UniversityDepartment of Computer Science, Kyambogo UniversityAbstract Malaria remains a significant global health challenge, particularly in sub-Saharan Africa. Despite advancements in treatment and prevention, malaria continues to cause substantial morbidity and mortality, particularly among vulnerable populations such as children and pregnant women. Although effective, traditional diagnostic methods, such as microscopy, are time-consuming and require skilled personnel prone to human error, leading to delays in diagnosis and treatment. More so, existing machine learning models used in malaria detection and classification have low performance and overfitting issues. This study presents an enhanced malaria detection and classification model using an ensemble of Convolutional Neural Networks (CNN) and Vision Transformers (ViT). The proposed ensemble model, which combines CNN and ViT, outperforms each individual model, achieving an accuracy of 99.64%, precision of 99.23%, recall of 99.75%, F1 score of 99.51%, and a cross-entropy loss of 0.01. The proposed model demonstrated superior performance compared to those reported in the literature. These results highlight the potential of the CNN-ViT ensemble model for accurate and reliable malaria detection, offering a significant improvement over existing methods.https://doi.org/10.1007/s42452-025-06704-zConvolutional neural networksVision transformersEnsembleHealth artificial intelligenceMalaria classification |
| spellingShingle | Emmanuel Ahishakiye Fredrick Kanobe Danison Taremwa Bartha Alexandra Nantongo Leonard Nkalubo Shallon Ahimbisibwe Enhancing malaria detection and classification using convolutional neural networks-vision transformer architecture Discover Applied Sciences Convolutional neural networks Vision transformers Ensemble Health artificial intelligence Malaria classification |
| title | Enhancing malaria detection and classification using convolutional neural networks-vision transformer architecture |
| title_full | Enhancing malaria detection and classification using convolutional neural networks-vision transformer architecture |
| title_fullStr | Enhancing malaria detection and classification using convolutional neural networks-vision transformer architecture |
| title_full_unstemmed | Enhancing malaria detection and classification using convolutional neural networks-vision transformer architecture |
| title_short | Enhancing malaria detection and classification using convolutional neural networks-vision transformer architecture |
| title_sort | enhancing malaria detection and classification using convolutional neural networks vision transformer architecture |
| topic | Convolutional neural networks Vision transformers Ensemble Health artificial intelligence Malaria classification |
| url | https://doi.org/10.1007/s42452-025-06704-z |
| work_keys_str_mv | AT emmanuelahishakiye enhancingmalariadetectionandclassificationusingconvolutionalneuralnetworksvisiontransformerarchitecture AT fredrickkanobe enhancingmalariadetectionandclassificationusingconvolutionalneuralnetworksvisiontransformerarchitecture AT danisontaremwa enhancingmalariadetectionandclassificationusingconvolutionalneuralnetworksvisiontransformerarchitecture AT barthaalexandranantongo enhancingmalariadetectionandclassificationusingconvolutionalneuralnetworksvisiontransformerarchitecture AT leonardnkalubo enhancingmalariadetectionandclassificationusingconvolutionalneuralnetworksvisiontransformerarchitecture AT shallonahimbisibwe enhancingmalariadetectionandclassificationusingconvolutionalneuralnetworksvisiontransformerarchitecture |