MMOTU
收藏资源简介:
MMOTU数据集是由北京航空航天大学电子信息工程学院和首都医科大学北京世纪坛医院妇产科联合创建的,包含1639张卵巢肿瘤超声图像,其中1469张为二维超声图像,170张为对比增强超声图像。该数据集旨在解决多模态卵巢肿瘤超声图像的跨域语义分割问题,通过提供像素级和全局级标注,支持无监督跨域语义分割研究。数据集的应用领域包括早期卵巢肿瘤检测和计算机辅助诊断,旨在提高卵巢癌的早期诊断率和降低死亡率。
The MMOTU dataset was jointly developed by the School of Electronic and Information Engineering of Beihang University and the Department of Obstetrics and Gynecology, Beijing Shijitan Hospital Affiliated to Capital Medical University. It comprises 1,639 ultrasound images of ovarian tumors, including 1,469 two-dimensional ultrasound images and 170 contrast-enhanced ultrasound images. This dataset is designed to tackle the cross-domain semantic segmentation issue for multimodal ovarian tumor ultrasound images. By providing pixel-level and global-level annotations, it supports research on unsupervised cross-domain semantic segmentation. Its application fields include early ovarian tumor detection and computer-aided diagnosis, aiming to improve the early diagnosis rate of ovarian cancer and reduce its mortality.




