BerDiff：面向医学图像分割的条件伯努利扩散模型
BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation
AI总结：
针对医学图像分割的模糊性与不确定性问题，提出采用伯努利噪声的条件扩散模型BerDiff，可生成准确多样的分割掩码并加速推理，在多模态数据集上性能优于现有最先进方法。
摘要：
医学图像分割是一项具有固有模糊性和高不确定性的挑战性任务，其成因包括肿瘤边界不清晰、存在多种合理标注等因素。分割掩码的准确性和多样性对于在临床实践中为放射科医生提供有价值的参考都至关重要。尽管现有扩散模型已在各类视觉生成任务中展现出强大能力，但处理分割任务中的离散掩码仍颇具挑战。为获得准确且多样的医学图像分割掩码，我们提出了一种新型医学图像分割条件伯努利扩散模型（BerDiff）。首先，我们未采用高斯噪声，而是提出使用伯努利噪声作为扩散核，以提升扩散模型处理二值分割任务的能力，从而得到更准确的分割掩码。其次，借助扩散模型的随机特性，我们的BerDiff通过对初始伯努利噪声和中间隐变量进行多次随机采样，生成一系列多样化的分割掩码，这些掩码能够凸显关键的感兴趣区域，可作为放射科医生的宝贵参考。此外，我们的BerDiff能够从反向扩散的完整轨迹中高效采样子序列，从而加快分割过程。在两个不同模态的医学图像分割数据集上开展的大量实验结果表明，我们的BerDiff性能优于其他近期发表的最先进方法。我们的研究结果表明，扩散模型可作为医学图像分割的强大骨干网络。
英文摘要：
Medical image segmentation is a challenging task with inherent ambiguity and high uncertainty, attributed to factors such as unclear tumor boundaries and multiple plausible annotations. The accuracy and diversity of segmentation masks are both crucial for providing valuable references to radiologists in clinical practice. While existing diffusion models have shown strong capacities in various visual generation tasks, it is still challenging to deal with discrete masks in segmentation. To achieve accurate and diverse medical image segmentation masks, we propose a novel conditional Bernoulli Diffusion model for medical image segmentation (BerDiff). Instead of using the Gaussian noise, we first propose to use the Bernoulli noise as the diffusion kernel to enhance the capacity of the diffusion model for binary segmentation tasks, resulting in more accurate segmentation masks. Second, by leveraging the stochastic nature of the diffusion model, our BerDiff randomly samples the initial Bernoulli noise and intermediate latent variables multiple times to produce a range of diverse segmentation masks, which can highlight salient regions of interest that can serve as valuable references for radiologists. In addition, our BerDiff can efficiently sample sub-sequences from the overall trajectory of the reverse diffusion, thereby speeding up the segmentation process. Extensive experimental results on two medical image segmentation datasets with different modalities demonstrate that our BerDiff outperforms other recently published state-of-the-art methods. Our results suggest diffusion models could serve as a strong backbone for medical image segmentation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
