Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206680,
        author = {Rahila and Mohammad Nihal and Harshitha H Hegde and Ganesh M S},
        title = {Optimized Deep Ensemble Model for Early Detection of Leukemia Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {175-182},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206680},
        abstract = {A fully automated pipeline for blood cell image recognition and categorization is introduced in this work, built around contemporary deep learning methods. Drawing from several independent repositories, 13,149 microscopic images were assembled into a dataset intentionally diverse enough to challenge the model and improve its real-world generalizability. Three neural architectures VGG16, ResNet50, and a bespoke convolutional design work in concert under an ensemble arrangement, each contributing its own analytical perspective to arrive at predictions more reliable than any single model could produce alone. Raw images are conditioned, meaningful representations are extracted, and a final label is assigned through a sequential processing chain. Fifty training epochs were completed using well-separated training and test partitions. Across all three-evaluation metrics accuracy, precision, and recall the results confirmed the model's ability to reliably differentiate between normal and abnormal cell samples. From a practical standpoint, the framework shortens the path to diagnosis, lightens the analytical workload on laboratory staff, and illustrates how thoughtfully applied artificial intelligence can elevate the standard of care in modern medicine.},
        keywords = {Artificial Intelligence, Blood Cell Classification, Biomedical Image Analysis, Computer Vision, Deep Learning, Ensemble Learning, Convolutional Neural Networks, VGG16, ResNet50.},
        month = {July},
        }