背景:医学图像分析管道通常涉及分割,这需要大量注释的训练数据,这是耗时且昂贵的。为了解决这个问题,我们提出了利用生成模型来实现少拍图像分割。
方法:我们在480,407个骨盆射线照片上训练了去噪扩散概率模型(DDPM),以生成256±256px的合成图像。DDPM以人口统计学和放射学特征为条件,并由领域专家和客观图像质量指标(Frechet起始距离[FID]和起始评分[IS])进行严格验证。下一步,三个地标(大转子[GT],小转子[LT],和闭孔[OF])在45例真实患者的X光片上进行了注释;25例用于训练,20例用于测试。要提取特征,每个图像在三个时间步长和每次通过预先训练的DDPM,从特定块中提取特征。将特征与真实图像连接以形成具有4225个通道的图像。功能集被分成随机补丁,被送到U网。使用骰子相似系数(DSC)与在射线照片上训练的香草U-Net进行性能比较。
结果:确定真实图像与生成图像的专家准确度为57.5%,而模型达到FID=7.2和IS=210。在20个特征集上训练的分割UNet对于OF实现了0.90、0.84和0.61的DSC,GT,和LT分割,分别,至少比天真训练的模型高0.30点。
结论:我们证明了DDPM作为特征提取器的适用性,促进医学图像分割,很少有注释样本。
BACKGROUND: Medical image analysis pipelines often involve segmentation, which requires a large amount of annotated training data, which is time-consuming and costly. To address this issue, we proposed leveraging generative models to achieve few-shot image segmentation.
METHODS: We trained a denoising diffusion probabilistic model (DDPM) on 480,407 pelvis radiographs to generate 256 ✕ 256 px synthetic images. The DDPM was conditioned on demographic and radiologic characteristics and was rigorously validated by domain experts and objective image quality metrics (Frechet inception distance [FID] and inception score [IS]). For the next step, three landmarks (greater trochanter [GT], lesser trochanter [LT], and obturator foramen [OF]) were annotated on 45 real-patient radiographs; 25 for training and 20 for testing. To extract features, each image was passed through the pre-trained DDPM at three timesteps and for each pass, features from specific blocks were extracted. The features were concatenated with the real image to form an image with 4225 channels. The feature-set was broken into random patches, which were fed to a U-Net. Dice Similarity Coefficient (DSC) was used to compare the performance with a vanilla U-Net trained on radiographs.
RESULTS: Expert accuracy was 57.5 % in determining real versus generated images, while the model reached an FID = 7.2 and IS = 210. The segmentation UNet trained on the 20 feature-sets achieved a DSC of 0.90, 0.84, and 0.61 for OF, GT, and LT segmentation, respectively, which was at least 0.30 points higher than the naively trained model.
CONCLUSIONS: We demonstrated the applicability of DDPMs as feature extractors, facilitating medical image segmentation with few annotated samples.