A CNN-based Approach for Breast Cancer Classification from Ultrasound Images

Marta Putri, Dila
Ikhsan, M
Nurjanah, Siti
Fahrizal, Fahrizal
Akramunnas, Bastul Wajhi
Rahmawati, Asde

Jurnal Surya Teknika
Vol. 12 No. 1 (2025): JURNAL SURYA TEKNIKA

Breast cancer is one of the most frequently diagnosed cancers and remains a leading cause of cancer-related mortality among women worldwide. According to WHO Globocan 2020, breast cancer ranks second globally, with 2,262,419 cases out of a total of 19,292,289 cancer cases, accounting for approximately 11.7%. Early detection plays a critical role in reducing breast cancer mortality. In this study, a machine learning-based approach using Convolutional Neural Networks (CNN) was employed to classify breast cancer using ultrasound imaging. The dataset, collected by Al-Dhabyani et al. at Baheya Hospital in 2018, consists of ultrasound images of women aged between 25 and 75 years. The proposed CNN model includes stages of data input, preprocessing, training, testing, and performance evaluation. The model achieved an accuracy of 85%, demonstrating promising results for automated breast cancer detection. Further optimization is recommended to improve classification performance.