CT-Malaria Detection via Adaptive-Weighted Deep Learning Models
The integration of augmentation, multiple modelling tracks, and optimal pairwise ensembling yields the highest accuracy in categorising malaria smears. It facilitates further enhancements by incorporating supplementary models, multi-class extensions, and operating-point calibration.
Authors
- S. Yahyaoui (ORCID: https://orcid.org/0009-0001-4041-836X)
- Afrah Alanazi (ORCID: https://orcid.org/0000-0002-2246-5656)
- Sarah Almaghrabi (ORCID: https://orcid.org/0000-0002-2255-494X)
- Karim Gasmi (ORCID: https://orcid.org/0000-0003-0138-2226)
- Sahar Almenwer (ORCID: https://orcid.org/0009-0004-1423-5588)
- Moez Krichen
Institutions
- University of Sfax (TN)
- Jouf University (SA)
- University of Jeddah (SA)
- Al Baha University (SA)
Publication Details
- Journal
- Biomedicines
- Published
- 2026-04-15
- DOI
- https://doi.org/10.3390/biomedicines14040898
- Primary Topic
- Digital Imaging for Blood Diseases
- Type
- article
- Field-Weighted Citation Impact
- 0.00