Meme Kanseri Sınıflandırması İçin Yeni Bir Yöntem: Ultrason Görüntülerinde Sinyal İşleme Temelli Bir Yaklaşım

Abstract

Breast cancer, a leading cause of mortality among women worldwide, the importance of accurate and efficient diagnostic methods is emphasized. This study contributes to the literature on breast cancer classification, particularly using breast ultrasound images, with a new method using a signal processing approach. It introduces a novel approach by combining features extracted from signals obtained from breast ultrasound images with signals from Variational Mode Decomposition (VMD) sub-bands. The results demonstrate that utilizing features from both preprocessed raw data and VMD sub-band signals can effectively distinguish benign and malignant breast ultrasound images. Classification performance varied depending on the algorithms and data used. According to the numerical results, the highest classification performance was achieved through the study with balanced data using the artificial neural network method, with an area under the curve value of 0.9971 and an accuracy value of 0.9821.