EUVIMEDEUVIMED entdecken
Crossref

CLAHE-Enhanced Vision Transformer Framework for Early and Accurate Detection of Acute Lymphoblastic Leukemia from Blood Smear Images

P. Yogendra Prasad, M. Sunil Kumar

International Journal of Drug Delivery Technology · 05.06.2026 · 16 (49s)

DOI: 10.25258/ijddt.16.49s.74 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 05.06.2026. Verfasst von P. Yogendra Prasad und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Acute lymphoblastic leukemia (ALL) is a kind of cancer of the bone marrow and blood, the percentage of which is high, and the leukemia is characterized by the immature lymphoid cells. Deep learning and computer vision methods have become more popular in such cases since they can accelerate and simplify the diagnosis process. In order to address these shortcomings, we present the CLAHE-Enhanced Hybrid CNN-Vision Transformer (CLAHE-VIT) system that is specifically developed to detect ALL on blood smears images with high precision and early onset. The system uses Contrast Limited Adaptive Histogram Equalization (CLAHE) as a preprocessing phase to sharpen the image, increase the contrast, and reduce noise before the classification is done based on its diagnostically relevance. The CNNs with the hybrid backbone effectively learn the local morphological features of blood cells and draws the benefits of CNNs and Vision Transformers. The Vision Transformer, however, captures the world space distributions across the image. Using this structure, the CLAHE-VITis able to address the shortcomings of transformer or standalone CNN architecture providing more reliable predictions.CLAHE-VIT was also more effective than CapsNet (accuracy 94.71, F1-score 94.18 ) and ResNet-50 (accuracy 95.42, F1-score 94.97) with 98.27% Accuracy, 99.17% Precision, 98.29% Recall, and 98.73% F1-score on CNMC dataset. CLAHE-VIT also delivered state-of-the-art results with an accuracy of 99.14, precision of 99.44, recall of 99.26 and F1-score of 99.35 on the Mehradaria dataset.

Zitieren

APA

Prasad, P. Y., & Kumar, M. S. (2026). CLAHE-Enhanced Vision Transformer Framework for Early and Accurate Detection of Acute Lymphoblastic Leukemia from Blood Smear Images. International Journal of Drug Delivery Technology, 16(49s). https://doi.org/10.25258/ijddt.16.49s.74

Vancouver

Prasad PY, Kumar MS. CLAHE-Enhanced Vision Transformer Framework for Early and Accurate Detection of Acute Lymphoblastic Leukemia from Blood Smear Images. International Journal of Drug Delivery Technology. 2026;16(49s). doi:10.25258/ijddt.16.49s.74

BibTeX
@article{Prasad2026,
  author = {Prasad, P. Yogendra and Kumar, M. Sunil},
  title = {CLAHE-Enhanced Vision Transformer Framework for Early and Accurate Detection of Acute Lymphoblastic Leukemia from Blood Smear Images},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {49s},
  doi = {10.25258/ijddt.16.49s.74}
}
Kostenlos starten →