BUS_UC

The BUS_UC dataset includes 358 benign tumor images and 453 malignant tumor images. The resolution of Ultrasound images is 256 × 256 pixels. All these images were obtained from the website Ultrasound Cases (ultrasoundcases.info), which does not provide ground truth images. Therefore, with the help of an experienced radiologist, benign and malignant tumor images are annotated for segmentation and classification task. If you use this dataset, Please cite : Ahmed Iqbal, Muhammad Sharif, "Memory-efficient transformer network with feature fusion for breast tumor segmentation and classification task ", Engineering Applications of Artificial Intelligence, 2023.

BUS_UC数据集包含358张良性肿瘤图像与453张恶性肿瘤图像。所有超声图像的分辨率均为256×256像素。本数据集所有图像均采集自Ultrasound Cases（ultrasoundcases.info）网站，该网站未提供标注真值图像。因此，本团队在一名经验丰富的放射科医师的协助下，针对分割与分类任务完成了良、恶性肿瘤图像的标注工作。若使用本数据集，请引用以下文献：Ahmed Iqbal、Muhammad Sharif，《面向乳腺肿瘤分割与分类任务的特征融合记忆高效Transformer网络》，《工程应用人工智能》，2023年。

搜集汇总

背景与挑战

背景概述

BUS_UC是一个包含811张乳腺肿瘤超声图像的数据集（358良性/453恶性），图像分辨率为256×256像素，经专业标注适用于分割和分类研究。数据集采用CC BY 4.0许可，主要应用于乳腺癌诊断相关的计算机视觉任务。