MGI: Multimodal Contrastive pre-training of Genomic and Medical Imaging

no code implementations • 2 Jun 2024 • Jiaying Zhou, Mingzhou Jiang, Junde Wu, Jiayuan Zhu, Ziyue Wang, Yueming Jin

We pre-trained on the TCGA dataset using paired gene expression data and imaging data, and fine-tuned it for downstream tumor segmentation tasks.

Contrastive Learning Tumor Segmentation

Uncertainty-Aware Adapter: Adapting Segment Anything Model (SAM) for Ambiguous Medical Image Segmentation

no code implementations • 16 Mar 2024 • Mingzhou Jiang, Jiaying Zhou, Junde Wu, Tianyang Wang, Yueming Jin, Min Xu

The Segment Anything Model (SAM) gained significant success in natural image segmentation, and many methods have tried to fine-tune it to medical image segmentation.

Image Segmentation Medical Image Segmentation +3