Automatic Pancreas Segmentation Using Coarse-Scaled 2D Model of Deep Learning: Usefulness of Data Augmentation and Deep U-Net
Automatic Pancreas Segmentation Using Coarse-Scaled 2D Model of Deep Learning: Usefulness of Data Augmentation and Deep U-Net
复制标题
DOI：
10.3390/app10103360
复制
发表时间：
2020-05-01
影响因子：
2.7
通讯作者：
Fujimoto, Koji
中科院分区：
文献类型：
--
作者：
Nishio, Mizuho;Noguchi, Shunjiro;Fujimoto, Koji
提出并评估了用于CT图像上自动胰腺分割的数据增强方法和深度学习架构的组合。使用来自胰腺分割的公共CT数据集的图像来评估模型。选择基线U网和深度U网作为胰腺分割的深度学习模型。数据增强的方法包括常规方法、混合和随机图像裁剪和修补（RICAP）。评估了深度学习模型和数据增强方法的十种组合。四重交叉验证进行训练和评估这些模型与数据增强方法。计算自动分割结果和手动注释标签之间的骰子相似系数（DSC），并由两位放射科医生进行视觉评估。深U形网的性能优于基线U形网，平均DSC分别为0.703-0.789和0.686-0.748。在基线U形网和深度U形网中，有数据增强的方法比没有数据增强的方法表现得更好，而mixup和RICAP比常规方法更有用。使用深U形网、mixup和RICAP的组合获得了最佳平均DSC，两位放射科医生对82例病例中的76例和74例的结果进行了良好或完美的评分。
Combinations of data augmentation methods and deep learning architectures for automatic pancreas segmentation on CT images are proposed and evaluated. Images from a public CT dataset of pancreas segmentation were used to evaluate the models. Baseline U-net and deep U-net were chosen for the deep learning models of pancreas segmentation. Methods of data augmentation included conventional methods, mixup, and random image cropping and patching (RICAP). Ten combinations of the deep learning models and the data augmentation methods were evaluated. Four-fold cross validation was performed to train and evaluate these models with data augmentation methods. The dice similarity coefficient (DSC) was calculated between automatic segmentation results and manually annotated labels and these were visually assessed by two radiologists. The performance of the deep U-net was better than that of the baseline U-net with mean DSC of 0.703-0.789 and 0.686-0.748, respectively. In both baseline U-net and deep U-net, the methods with data augmentation performed better than methods with no data augmentation, and mixup and RICAP were more useful than the conventional method. The best mean DSC was obtained using a combination of deep U-net, mixup, and RICAP, and the two radiologists scored the results from this model as good or perfect in 76 and 74 of the 82 cases.