Published in Science Bulletin, 2024
We propose a novel neural network framework called Multi-rater Prism (MrPrism) to learn medical image segmentation from multiple labels.
Recommended citation: Wu J, Fang H, Zhu J, et al. Multi-rater prism: Learning self-calibrated medical image segmentation from multiple raters[J]. Science Bulletin, 2024, 69(18): 2906-2919.
Download Paper
Published in IEEE Transactions on Medical Imaging, 2024
We propose a diagnosis-first principle, which is to take disease diagnosis as the criterion to calibrate the inter-observer segmentation uncertainty.
Recommended citation: Wu J, Zhang Y, Fang H, et al. Calibrate the inter-observer segmentation uncertainty via diagnosis-first principle[J]. IEEE Transactions on Medical Imaging, 2024.
Download Paper
Published in Scientific Data, 2024
Recommended citation: Fang H, Li F, Wu J, et al. Open fundus photograph dataset with pathologic myopia recognition and anatomical structure annotation[J]. Scientific Data, 2024, 11(1): 99.
Download Paper
Published in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2024
To improve label utilization efficiency in semantic segmentation models, we propose Diffusion-Enhanced Transformation Consistency Learning (termed as DiffTCL), a semi-supervised segmentation approach.
Recommended citation: Li X, Fang H, Liu M, et al. Diffusion-Enhanced Transformation Consistency Learning for Retinal Image Segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2024: 221-231.
Download Paper
Published in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2024
We introduce Spatial Test-Time Adaptation (STTA), for the first time considering the integration of inter-slice spatial information from 3D volumes with TTA.
Recommended citation: Li X, Fang H, Wang C, et al. Cache-Driven Spatial Test-Time Adaptation for Cross-Modality Medical Image Segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2024: 146-156.
Download Paper
Published in Medical Imaging with Deep Learning, 2024
Inspired by the success of DPM, we propose MedSegDiff, the first DPM-based model for general medical image segmentation tasks.
Recommended citation: Wu J, Fu R, Fang H, et al. Medsegdiff: Medical image segmentation with diffusion probabilistic model[C]//Medical Imaging with Deep Learning. PMLR, 2024: 1623-1639.
Download Paper