Medical Applications of Large Vision Models in Medical Imaging and Diagnostics

This project explores the application of large-scale vision models, such as SAM/SAM2/MedSAM, in the medical field, specifically in medical imaging and diagnostics. By adapting and fine-tuning pre-trained models, we aim to improve the accuracy and efficiency of medical image analysis. The research includes multi-modal image fusion to enhance diagnostic accuracy, developing methods to increase the interpretability of model predictions, and optimizing model architectures to ensure scalability and efficiency in clinical settings. This project has the potential to revolutionize how medical professionals analyze complex medical data, leading to better patient outcomes.
This is a XJTLU-JITRI project. The project has recently been approved. It is being developed in collaboration with Shanghai Melon Technology Co., Ltd. .