This study focuses on classifying breast cancer tissues using various decision tree algorithms, specifically utilizing the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. The classification models, including J48, Random Forest, Reptree, and Randomtree, aim to distinguish between benign and malignant tumors based on diagnostic features, achieving a maximum accuracy of 95.07% with the Random Forest algorithm. The research highlights the importance of data mining techniques in improving clinical decision-making for breast cancer patients.