Recently, denoising diffusion probabilistic models (DDPM) have been applied to image segmentation by generating segmentation masks conditioned on images, while the applications were mainly limited to 2D networks without exploiting potential benefits from the 3D formulation. In this work, for the first time, DDPMs are used for 3D multiclass image segmentation. We make three key contributions that all focus on aligning the training strategy with the evaluation methodology, and improving efficiency. Firstly, the model predicts segmentation masks instead of sampled noise and is optimised directly via Dice loss. Secondly, the predicted mask in the previous time step is recycled to generate noise-corrupted masks to reduce information leakage. Finally, the diffusion process during training was reduced to five steps, the same as the evaluation. Through studies on two large multiclass data sets (prostate MR and abdominal CT), we demonstrated significantly improved performance compared to existing DDPMs, and reached competitive performance with non-diffusion segmentation models, based on U-net, within the same compute budget. The JAX-based diffusion framework has been released on https://github.com/mathpluscode/ImgX-DiffSeg.
翻译:最近,通过生成以图像为条件的分解面罩,对图像分化应用了分解扩散概率模型(DDPM),从而将分解扩散概率模型(DDPM)应用于图像分割,而应用主要限于2D网络,而没有利用3D配方的潜在好处。在这项工作中,DDPMM首次用于3D多级图像分解。我们做出了三项关键贡献,这些贡献都侧重于使培训战略与评价方法相一致,并提高效率。首先,模型预测了分解面罩,而不是抽样噪音,直接通过Dice丢失来优化。第二,对前一个步骤的预测面罩进行了再循环,以产生噪音碎裂面罩,以减少信息泄漏。最后,培训过程中的传播过程减少到了五个步骤,与评价相同。通过对两个大型多级数据集(Prostate MMR和 abdminal CT)的研究,我们展示了与现有的DDPMMMS相比的绩效显著提高,并在相同的预算内,以U-net为基础,实现了非分解分化模式的竞争性性性表现。基于JAX-X-rup/Dgscodeg/Diffcomcommmexmmmm/e)的传播框架已在http上发布。基于 httpsmsmsmsmsmsmmmmmmmmmmmmmmmmmmmmmmsmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmm</s>