A Segmentation Foundation Model for Diverse-type Tumors

arXiv:2403.06396v1 Announce Type: cross
Abstract: 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, …

abstract arxiv cs.cv data datasets diverse eess.iv foundation foundation model image image datasets imaging large-scale models medical medical imaging parameters performance pre-trained models scale segmentation tasks training training datasets tumors type