10K CT scans
收藏资源简介:
10K CT scans数据集是由中国科学技术大学 School of Biomedical Engineering Division of Life Sciences and Medicine等机构创建的,包含10000个CT扫描图像。该数据集用于Hi-End-MAE模型的预训练,该模型通过编码器驱动的掩码自动编码技术,实现医学图像分割。数据集的特点是利用了大规模未标注的医学数据,通过自监督学习的方式学习到丰富的局部特征,适用于医学图像分割等下游任务。
The 10K CT Scans Dataset was developed by institutions including the School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China (USTC), and other relevant organizations, and it comprises 10,000 CT scan images. This dataset is used for pre-training the Hi-End-MAE model, which adopts encoder-driven masked autoencoding technology to accomplish medical image segmentation. The dataset is characterized by leveraging large-scale unannotated medical data to learn rich local features through self-supervised learning, making it applicable to downstream tasks such as medical image segmentation.

- 1Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation中国科学技术大学 · 2025年



