BUSC Dataset

The Mendeley ultrasound dataset [1] includes 100 benign images and 150 malignant cancer images. The original resolution of ultrasound images is 64 × 64 pixels, later in our research [2] transformed into 128 × 128 pixels. This dataset is basically classification-based dataset, and no ground truth images are provided. Therefore, with the help of an experienced radiologist, benign and malignant tumor images are annotated for segmentation task. If you use this dataset, Please cite: [1] Rodrigues, Paulo Sergio (2017), "Breast Ultrasound Image", Mendeley Data, V1, doi: 10.17632/wmy84gzngw.1 [2] Ahmed Iqbal, Muhammad Sharif, "PDF-UNet: A semi-supervised method for segmentation of breast tumor images using a U-shaped pyramid-dilated network", Expert Systems with Applications, 2023. https://doi.org/10.1016/j.eswa.2023.119718