V3I4P70

Multimedia Machine Learning Pipeline for Anemia and Leukemia Detection

Vivedha. V^1*, Dr. V. Manikandabalaji² , Dr. R. Sivakumar³

Abstract

Early and accurate detection of hematological disorders such as anemia and leukemia is crucial for timely medical intervention and effective treatment planning. This study proposes a multi-modal machine learning pipeline that integrates both clinical blood test parameters and microscopic blood smear images to enhance diagnostic accuracy. The system combines data preprocessing, feature extraction, and ensemble classification models to analyze complete blood count (CBC) data and image-based morphological patterns of blood cells. Clinical features such as hemoglobin (Hb), hematocrit (HCT), red blood cell count (RBC), mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), and white blood cell (WBC) count are used alongside deep learning models like Convolutional Neural Networks (CNNs) for image feature extraction.

Keywords:

Anemia Detection, Leukemia Diagnosis,Machine Learning in Healthcare