In medical image segmentation,it is often necessary to collect opinions from multiple experts to make the final decision.This clinical routine helps to mitigate individual bias.However,when data is annotated by multip...In medical image segmentation,it is often necessary to collect opinions from multiple experts to make the final decision.This clinical routine helps to mitigate individual bias.However,when data is annotated by multiple experts,standard deep learning models are often not applicable.In this paper,we propose a novel neural network framework called Multi-rater Prism(MrPrism)to learn medical image segmentation from multiple labels.Inspired by iterative half-quadratic optimization,MrPrism combines the task of assigning multi-rater confidences and calibrated segmentation in a recurrent manner.During this process,MrPrism learns inter-observer variability while taking into account the image's semantic properties and finally converges to a self-calibrated segmentation result reflecting inter-observer agreement.Specifically,we propose Converging Prism(ConP)and Diverging Prism(DivP)to iteratively process the two tasks.ConP learns calibrated segmentation based on multi-rater confidence maps estimated by DivP,and DivP generates multi-rater confidence maps based on segmentation masks estimated by ConP.Experimental results show that the two tasks can mutually improve each other through this recurrent process.The final converged segmentation result of MrPrism outperforms state-of-the-art(SOTA)methods for a wide range of medical image segmentation tasks.The code is available at https://github.-com/WuJunde/MrPrism.展开更多
基金supported by the Excellent Young Science and Technology Talent Cultivation Special Project of China Academy of Chinese Medical Sciences(CI2023D006)the National Natural Science Foundation of China(82121003 and 82022076)+2 种基金Beijing Natural Science Foundation(2190023)Shenzhen Fundamental Research Program(JCYJ20220818103207015)Guangdong Provincial Key Laboratory of Human Digital Twin(2022B1212010004)。
文摘In medical image segmentation,it is often necessary to collect opinions from multiple experts to make the final decision.This clinical routine helps to mitigate individual bias.However,when data is annotated by multiple experts,standard deep learning models are often not applicable.In this paper,we propose a novel neural network framework called Multi-rater Prism(MrPrism)to learn medical image segmentation from multiple labels.Inspired by iterative half-quadratic optimization,MrPrism combines the task of assigning multi-rater confidences and calibrated segmentation in a recurrent manner.During this process,MrPrism learns inter-observer variability while taking into account the image's semantic properties and finally converges to a self-calibrated segmentation result reflecting inter-observer agreement.Specifically,we propose Converging Prism(ConP)and Diverging Prism(DivP)to iteratively process the two tasks.ConP learns calibrated segmentation based on multi-rater confidence maps estimated by DivP,and DivP generates multi-rater confidence maps based on segmentation masks estimated by ConP.Experimental results show that the two tasks can mutually improve each other through this recurrent process.The final converged segmentation result of MrPrism outperforms state-of-the-art(SOTA)methods for a wide range of medical image segmentation tasks.The code is available at https://github.-com/WuJunde/MrPrism.
