Breast cancer is one of the biggest causes of death for women worldwide. Breast cancer is a metastatic cancer and can spread to other organs, such as bones, liver, lungs and brain. Breast cancer can be detected at an early stage, but it is difficult to find and cases of breast cancer are on the rise. Therefore, this study uses the Half-UNet architecture for breast cancer sonogram dataset. The dataset used consists of 780 breast sonograms which are divided into training data and test data with a ratio of 80:20. The Dice Coefficient results obtained on the Half-UNet architecture is 0.7063. The U-Net value can provide better Dice Coefficient results, but the Half-UNet architecture has comparable values and provides results in a relatively faster time.