EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DEEP LEARNING–BASED FRAMEWORK FOR AUTOMATED DETECTION AND LOCALIZATION OF MALARIA IN MICROSCOPIC BLOOD SMEAR IMAGES

Hooria Khan, Muhammad Qasim Khan, Hamail Raza Zaidi, Tauseef Noor, Abdul Aziz

Kashf Journal of Multidisciplinary Research · 27.02.2026 · 3 (02) · 70-83

DOI: 10.71146/kjmr834 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Kashf Journal of Multidisciplinary Research, online erschienen am 27.02.2026. Verfasst von Hooria Khan und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Malaria remains a major global health challenge, particularly in developing regions where timely and accurate diagnosis is critical. Conventional microscopic examination of blood smears is labor-intensive, time-consuming, and highly dependent on expert interpretation, leading to potential diagnostic errors. Recent advances in deep learning have enabled automated malaria detection with promising accuracy; however, most existing approaches are limited to image-level classification and lack parasite localization capability. This paper proposes a robust deep learning framework that integrates Convolutional Neural Network (CNN)-based classification with YOLOv8-based object detection for accurate detection and localization of malaria-infected regions in microscopic blood smear images. The CNN model effectively distinguishes infected and healthy blood cells, achieving an accuracy of 97.19%. To overcome the limitations of classification-only models, YOLOv8 is employed to localize malaria parasites within blood cells, resulting in an improved accuracy of 98% along with precise spatial detection. Experimental results demonstrate that the proposed framework enhances diagnostic accuracy, interpretability, and clinical applicability, offering an efficient and reliable solution for automated malaria diagnosis.

Zitieren

APA

Khan, H., Khan, M. Q., Zaidi, H. R., Noor, T., & Aziz, A. (2026). DEEP LEARNING–BASED FRAMEWORK FOR AUTOMATED DETECTION AND LOCALIZATION OF MALARIA IN MICROSCOPIC BLOOD SMEAR IMAGES. Kashf Journal of Multidisciplinary Research, 3(02), 70-83. https://doi.org/10.71146/kjmr834

Vancouver

Khan H, Khan MQ, Zaidi HR, Noor T, Aziz A. DEEP LEARNING–BASED FRAMEWORK FOR AUTOMATED DETECTION AND LOCALIZATION OF MALARIA IN MICROSCOPIC BLOOD SMEAR IMAGES. Kashf Journal of Multidisciplinary Research. 2026;3(02):70-83. doi:10.71146/kjmr834

BibTeX
@article{Khan2026,
  author = {Khan, Hooria and Khan, Muhammad Qasim and Zaidi, Hamail Raza and Noor, Tauseef and Aziz, Abdul},
  title = {DEEP LEARNING–BASED FRAMEWORK FOR AUTOMATED DETECTION AND LOCALIZATION OF MALARIA IN MICROSCOPIC BLOOD SMEAR IMAGES},
  journal = {Kashf Journal of Multidisciplinary Research},
  year = {2026},
  volume = {3},
  number = {02},
  pages = {70--83},
  doi = {10.71146/kjmr834}
}
Kostenlos starten →