A Review of Deep Learning Techniques for Leukemia Cancer Classification Based on Blood Smear Images DOI Creative Commons

Rakhmonalieva Farangis Oybek Kizi,

Tagne Poupi Theodore Armand, Hee‐Cheol Kim

и другие.

Applied Biosciences, Год журнала: 2025, Номер 4(1), С. 9 - 9

Опубликована: Фев. 5, 2025

This research reviews deep learning methodologies for detecting leukemia, a critical cancer diagnosis and treatment aspect. Using systematic mapping study (SMS) literature review (SLR), thirty articles published between 2019 2023 were analyzed to explore the advancements in techniques leukemia using blood smear images. The analysis reveals that state-of-the-art models, such as Convolutional Neural Networks (CNNs), transfer learning, Vision Transformers (ViTs), ensemble methods, hybrid achieved excellent classification accuracies. Preprocessing including normalization, edge enhancement, data augmentation, significantly improved model performance. Despite these advancements, challenges dataset limitations, lack of interpretability, ethical concerns regarding privacy bias remain barriers widespread adoption. highlights need diverse, well-annotated datasets development explainable AI models enhance clinical trust usability. Additionally, addressing regulatory integration is essential safe deployment technologies healthcare. aims guide researchers overcoming advancing applications improve diagnostics patient outcomes.

Язык: Английский

A Review of Deep Learning Techniques for Leukemia Cancer Classification Based on Blood Smear Images DOI Creative Commons

Rakhmonalieva Farangis Oybek Kizi,

Tagne Poupi Theodore Armand, Hee‐Cheol Kim

и другие.

Applied Biosciences, Год журнала: 2025, Номер 4(1), С. 9 - 9

Опубликована: Фев. 5, 2025

This research reviews deep learning methodologies for detecting leukemia, a critical cancer diagnosis and treatment aspect. Using systematic mapping study (SMS) literature review (SLR), thirty articles published between 2019 2023 were analyzed to explore the advancements in techniques leukemia using blood smear images. The analysis reveals that state-of-the-art models, such as Convolutional Neural Networks (CNNs), transfer learning, Vision Transformers (ViTs), ensemble methods, hybrid achieved excellent classification accuracies. Preprocessing including normalization, edge enhancement, data augmentation, significantly improved model performance. Despite these advancements, challenges dataset limitations, lack of interpretability, ethical concerns regarding privacy bias remain barriers widespread adoption. highlights need diverse, well-annotated datasets development explainable AI models enhance clinical trust usability. Additionally, addressing regulatory integration is essential safe deployment technologies healthcare. aims guide researchers overcoming advancing applications improve diagnostics patient outcomes.

Язык: Английский

Процитировано

0