Large pre-trained models with their numerous model parameters and extensive
training datasets have shown excellent performance in various tasks. Many
publicly available medical image datasets do not have a sufficient amount of
data so there are few large-scale models in medical imaging. We propose a
large-scale Tumor Segmentation Foundation Model (TSFM) with 1.6 billion
parameters using Resblock-backbone and Transformer-bottleneck,which has good
transfer ability for downstream tasks. To make TSFM exhibit good performance in
tumor segmentation, we make full use of the strong spatial correlation between
tumors and organs in the medical image, innovatively fuse 7 tumor datasets and
3 multi-organ datasets to build a 3D medical dataset pool, including 2779 cases
with totally 300k medical images, whose size currently exceeds many other
single publicly available datasets. TSFM is the pre-trained model for medical
image segmentation, which also can be transferred to multiple downstream tasks
for fine-tuning learning. The average performance of our pre-trained model is
2% higher than that of nnU-Net across various tumor types. In the transfer
learning task, TSFM only needs 5% training epochs of nnU-Net to achieve similar
performance and can surpass nnU-Net by 2% on average with 10% training epoch.
Pre-trained TSFM and its code will be released soon.

通过使用 Resblock-backbone 和 Transformer-bottleneck 构建 16 亿参数的大规模肿瘤分割基础模型 (TSFM)，我们利用医学影像中肿瘤和器官之间的空间相关性，创新地融合了 7 个肿瘤数据集和 3 个多器官数据集，构建了一个三维医学数据集池，包括 2779 个病例和 30 万张医学图像，其规模目前超过许多其他公开数据集。TSFM 是用于医学影像分割的预训练模型，也可以用于多个下游任务的微调学习。与 nnU-Net 相比，我们的预训练模型的平均性能高出 2%，在迁移学习任务中，TSFM 只需 nnU-Net 的 5% 训练轮次即可达到相似的性能，并且可以在 10% 的训练轮次上平均超过 nnU-Net 2%。预训练的 TSFM 模型及其代码即将发布。