BUSIS
收藏资源简介:
BUSIS数据集由哈尔滨工业大学、爱达荷大学和犹他州立大学等机构合作创建,包含562张乳腺超声图像,用于乳腺超声图像分割的基准测试。数据集中的图像来自多个超声设备,涵盖了从26岁到78岁的女性患者,旨在评估不同分割算法的性能。数据集的标注由四位经验丰富的放射科医生通过标准化程序完成,确保了标注的准确性。该数据集主要用于研究和开发计算机辅助诊断系统,特别是在乳腺肿瘤的自动检测和分割领域。
The BUSIS dataset was collaboratively developed by institutions including Harbin Institute of Technology, University of Idaho, Utah State University, and others. It contains 562 breast ultrasound images, serving as a benchmark for breast ultrasound image segmentation tasks. The images in the dataset were collected from multiple ultrasound devices, covering female patients aged 26 to 78 years old, with the purpose of evaluating the performance of different segmentation algorithms. The annotations of the dataset were finalized by four experienced radiologists through standardized workflows, guaranteeing the accuracy of the labeling. This dataset is primarily utilized for the research and development of computer-aided diagnosis systems, particularly in the domain of automatic detection and segmentation of breast tumors.

- 1BUSIS: A Benchmark for Breast Ultrasound Image Segmentation哈尔滨工业大学计算机科学与技术学院, 爱达荷大学计算机科学系, 犹他州立大学计算机科学系, 哈尔滨工业大学(威海)计算机科学与技术学院, 青岛大学医学院附属医院超声科, 河北医科大学第二医院普通外科 · 2021年



