• Mr Rajababoo Patel
• Mr. Rajneesh Pachouri
• Mr. Anurag Jain
• Ms. Sadhvi Biltharey

Leukemia is a life-threatening form of blood cancer that demands accurate and early diagnosis to improve patient outcomes. This thesis presents a robust and efficient system for the classification of leukemia white blood cell cancer by leveraging advanced image processing techniques and machine learning algorithms. The proposed system focuses on overcoming limitations of existing methods, such as computational complexity and dependency on large datasets, by integrating a K-Nearest Neighbors (KNN) classifier with effective feature extraction and preprocessing methods. The system workflow includes image acquisition, preprocessing (normalization, contrast enhancement, and noise removal), segmentation to isolate critical cell regions, feature extraction (statistical color and texture features), and classification. By utilizing the KNN algorithm, the system achieves a remarkable accuracy of 97%, effectively categorizing leukemia into subtypes such as ALL-L1, ALL-L2, AML-M2, and AML-M5. Comprehensive performance analysis using metrics like precision, sensitivity, and specificity validates the system's reliability and clinical applicability. Compared to existing deep learning models, the proposed approach offers reduced computational overhead, enhanced interpretability, and compatibility with resource-constrained environments, making it a practical solution for healthcare facilities. This system represents a significant step forward in the early and accurate diagnosis of leukemia, potentially saving lives and advancing research in hematological oncology.

Leukemia is a life-threatening form of blood cancer that demands accurate and early diagnosis to improve patient outcomes. This thesis presents a robust and efficient system for the classification of leukemia white blood cell cancer by leveraging advanced image processing techniques and machine learning algorithms. The proposed system focuses on overcoming limitations of existing methods, such as computational complexity and dependency on large datasets, by integrating a K-Nearest Neighbors (KNN) classifier with effective feature extraction and preprocessing methods. The system workflow includes image acquisition, preprocessing (normalization, contrast enhancement, and noise removal), segmentation to isolate critical cell regions, feature extraction (statistical color and texture features), and classification. By utilizing the KNN algorithm, the system achieves a remarkable accuracy of 97%, effectively categorizing leukemia into subtypes such as ALL-L1, ALL-L2, AML-M2, and AML-M5. Comprehensive performance analysis using metrics like precision, sensitivity, and specificity validates the system's reliability and clinical applicability. Compared to existing deep learning models, the proposed approach offers reduced computational overhead, enhanced interpretability, and compatibility with resource-constrained environments, making it a practical solution for healthcare facilities. This system represents a significant step forward in the early and accurate diagnosis of leukemia, potentially saving lives and advancing research in hematological oncology.

"Advanced Machine Learning Techniques for the Classification of Leukemia White Blood Cell Cancer Using Image ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.g375-g380, January-2025, Available :http://www.jetir.org/papers/JETIR2501640.pdf

"Advanced Machine Learning Techniques for the Classification of Leukemia White Blood Cell Cancer Using Image ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppg375-g380, January-2025, Available at : http://www.jetir.org/papers/JETIR2501640.pdf