摘要
Diffusion probabilistic model (DPM) recently becomes one of the hottest topic in computer vision.
Its image generation application such as Imagen, Latent Diffusion Models and Stable Diffusion have shown impressive generation capabilities, which aroused extensive discussion in the community.
Many recent studies also found it is useful in many other vision tasks, like image deblurring, super-resolution and anomaly detection.
Inspired by the success of DPM, we propose the first DPM based model toward general medical image segmentation tasks, which we named MedSegDiff.
In order to enhance the step-wise regional attention in DPM for the medical image segmentation, we propose dynamic conditional encoding, which establishes the state-adaptive conditions for each sampling step.
We further propose Feature Frequency Parser (FF-Parser), to eliminate the negative effect of high-frequency noise component in this process.
We verify MedSegDiff on three medical segmentation tasks with different image modalities, which are optic cup segmentation over fundus images, brain tumor segmentation over MRI images and thyroid nodule segmentation over ultrasound images.
The experimental results show that MedSegDiff outperforms state-of-the-art (SOTA) methods with considerable performance gap, indicating the generalization and effectiveness of the proposed model.
扩散概率模型(Diffusion probabilistic model, DPM)是近年来计算机视觉研究的热点之一。
它在Imagen、Latent Diffusion Models和Stable Diffusion等图像生成应用中表现出了令人印象深刻的生成能力，引起了社会的广泛讨论。
最近的许多研究还发现，它在许多其他视觉任务中也很有用，比如图像去模糊、超分辨率和异常检测。
受DPM成功的启发，我们提出了第一个基于DPM的一般医学图像分割模型，我们将其命名为MedSegDiff。
为了增强DPM在医学图像分割中的分步区域关注，我们提出了dy动态条件编码，该编码为每个采样步建立状态自适应条件。
我们进一步提出Feature Frequency Parser (FF-Parser)来消除高频噪声分量在此过程中的负面影响。
我们在三种不同图像模式的医学分割任务上验证了MedSegDiff，即眼底图像的视杯分割、MRI图像的脑肿瘤分割和超声图像的甲状腺结节分割。
实验结果表明，MedSegDiff在性能上明显优于最先进的SOTA方法，表明了该模型的gen可实现性和有效性。
