论文标题
3D跨钉监督（3D-CPS）：用于腹部器官分割的半监督NNU-NET结构
3D Cross-Pseudo Supervision (3D-CPS): A semi-supervised nnU-Net architecture for abdominal organ segmentation
论文作者
论文摘要
大型策划数据集是必要的，但是注释医学图像是一个耗时，费力且昂贵的过程。因此，最近的监督方法着重于利用大量未标记的数据。但是，这样做是一项具有挑战性的任务。为了解决这个问题，我们提出了一种新的3D跨伪疑问监督（3D-CPS）方法，这是一种基于NNU-NET的半监督网络体系结构，采用交叉伪造监督方法。我们设计了一种新的基于NNU-NET的预处理。此外，我们将半监督的损失权重设置为与每个时期扩展线性，以防止在早期训练过程中该模型从低质量的伪标签中。我们提出的方法在MICCAI Flare2022验证集（20例）上，平均骰子相似系数（DSC）为0.881，平均归一化表面距离（NSD）为0.913。
Large curated datasets are necessary, but annotating medical images is a time-consuming, laborious, and expensive process. Therefore, recent supervised methods are focusing on utilizing a large amount of unlabeled data. However, to do so, is a challenging task. To address this problem, we propose a new 3D Cross-Pseudo Supervision (3D-CPS) method, a semi-supervised network architecture based on nnU-Net with the Cross-Pseudo Supervision method. We design a new nnU-Net based preprocessing. In addition, we set the semi-supervised loss weights to expand linearity with each epoch to prevent the model from low-quality pseudo-labels in the early training process. Our proposed method achieves an average dice similarity coefficient (DSC) of 0.881 and an average normalized surface distance (NSD) of 0.913 on the MICCAI FLARE2022 validation set (20 cases).
