Automated Cancer Detection in Human Blood Samples Using Microscopic Images and Machine Learning Techniques for Enhanced Diagnosis and Classification using MATLAB

This paper presents an automated system for leukemia detection from peripheral blood samples using machine learning techniques implemented primarily in MATLAB, with extensions in Python for advanced processing and a web-based interface for user interaction. Our approach involves image preprocessing, feature extraction using convolutional neural networks (CNNs), and classification via support vector machines (SVM) and deep learning models. The system achieves an accuracy of 98.5% on a dataset of 10,000 blood smear images, outperforming manual methods. Integration with a full-stack web application (HTML, CSS, JavaScript, PHP, MySQL) enables remote access, data storage, and real-time diagnostics. This work contributes to accessible hematology tools, potentially reducing diagnostic delays in resource-limited settings. This study focuses on the techniques used to segment and detect the type of leukemia by analyzing different features of the digital images of the white blood cells. Variations in these features are used as the classifier inputs which give information about different types of leukemia. To understand relative merits and demerits, comparisons of different techniques used for segmentation and classification are given.