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{182426,
        author = {Ms Ashra Khan and Mr Sarvesh Singh Rai},
        title = {Enhancing Leukemia Diagnosis Through Image Processing and Machine Learning: A KNN-Based Approach},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {2344-2350},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182426},
        abstract = {Leukemia is a mortal form of ancestry cancer that demands correct and early disease to improve patient effects. This belief presents a healthy and efficient order for the categorization of leukemia cells that eat bacteria and fungi cancer by leveraging leading figure processing methods and machine intelligence algorithms. The projected system focuses on beating disadvantages of existing designs, to a degree computational complicatedness and dependency on big datasets, by mixing a K-Nearest Neighbors (KNN) classifier accompanying effective feature distillation and preprocessing procedures.The system workflow involves countenance procurement, preprocessing (normalization, contrast enhancement, and cacophony relocation), segmentation to segregate fault-finding container regions, feature distillation (mathematical color and makeup features), and categorization. By taking advantage of the KNN algorithm, bureaucracy achieves a extraordinary veracity of 97%, effectively classification leukemia into subtypes in the way that ALL-L1, ALL-L2, AML-M2, and AML-M5. Comprehensive performance study utilizing versification like precision, sense, and precision justifies the system's dependability and dispassionate applicability.Compared to existent deep education models, the projected approach offers reduced computational overhead, embellished interpretability, and rapport accompanying resource-forced atmospheres, making it a practical answer for healthcare abilities. This structure represents a important progress in the early and accurate disease of leukemia, conceivably conditional lives and advancing research in hematological oncology.},
        keywords = {Feature Extraction, Image Processing, White Blood Cell Cancer, K-Nearest Neighbors (KNN), Leukemia Classification.},
        month = {July},
        }