@article{Zahedi_Karimi Moridani_2022, title={Classification of Breast Cancer Tumors Using Mammography Images Processing Based on Machine Learning: Breast Cancer Tumors Using Mammography Images}, volume={18}, url={https://online-journals.org/index.php/i-joe/article/view/29197}, DOI={10.3991/ijoe.v18i05.29197}, abstractNote={<p><strong> </strong></p> <p><strong>Abstract—</strong> Using intelligent methods to identify and classify a variety of diseases, in particular cancer, has gained tremendous attention today. Tumor classification plays an important role in medical diagnosis. This study’s goal was to classify breast cancer (BC) tumors using software-based numerical techniques. To determine whether breast cancer masses are benign or malignant, we used MATLAB version 2020b to build a neural network. In the first step, the features of the training images and their output classes were used to train the network. Optimal weights were obtained after several repetitions, and the network was trained to produce the best result in the test phase after several repetitions.</p> <p>Because of using effective and accurate features, the method suggested here, which was based on an artificial neural network, delivered the diagnostic accuracy, specificity, and sensitivity of 100%, 100%, and 100%, respectively, to discern benign from malignant BC tumors, showing a better performance compared to previously proposed methods. One of the challenges for imaging-based diagnostic techniques in medicine is the difficulty of processing dense tissues. Breast cancer is one of the most common progressive diseases among females. Early diagnosis makes treatment easier and more effective. Using AI-based methods for automated diagnosis purposes can be valuable and have a reduced error rate because accurate diagnosis by manual means is time-consuming and error-prone.</p>}, number={05}, journal={International Journal of Online and Biomedical Engineering (iJOE)}, author={Zahedi, Farahnaz and Karimi Moridani, Mohammad}, year={2022}, month={Apr.}, pages={pp. 31–42} }