Featured by a bottleneck structure, autoencoder (AE) and its variants have been largely applied in various medical image analysis tasks, such as segmentation, reconstruction and de-noising. Despite of their promising performances in aforementioned tasks, in this paper, we claim that AE models are not applicable to single image super-resolution (SISR) for 3D CT data. Our hypothesis is that the bottleneck architecture that resizes feature maps in AE models degrades the details of input images, thus can sabotage the performance of super-resolution. Although U-Net proposed skip connections that merge information from different levels, we claim that the degrading impact of feature resizing operations could hardly be removed by skip connections. By conducting large-scale ablation experiments and comparing the performance between models with and without the bottleneck design on a public CT lung dataset , we have discovered that AE models, including U-Net, have failed to achieve a compatible SISR result ($p<0.05$ by Student's t-test) compared to the baseline model. Our work is the first comparative study investigating the suitability of AE architecture for 3D CT SISR tasks and brings a rationale for researchers to re-think the choice of model architectures especially for 3D CT SISR tasks. The full implementation and trained models can be found at: https://github.com/Roldbach/Autoencoder-3D-CT-SISR
翻译:显著的瓶颈结构使得自编码器(AE)及其变体在各种医学图像分析任务中被广泛应用,例如分割、重建和去噪。尽管在上述任务中 AE 模型的表现令人期待,但是在本文中,我们声称 AE 模型不适用于单张图像超分辨率(SISR)的 3D CT 数据。 我们的假设是,在 AE 模型中用于调整特征映射尺寸的瓶颈架构会破坏输入图像的细节,从而破坏超分辨率的性能。虽然 U-Net 提出了跳跃连接来合并不同级别的信息,但我们声称,特征调整操作的降级影响很难通过跳跃连接消除。通过在公共 CT 肺数据集上进行大规模深入分析实验,并比较具有和不具有瓶颈设计的模型之间的性能,我们发现相比基线模型,包括 U-Net 在内的 AE 模型未能实现相容的 SISR 结果(通过学生 t 检验,$p<0.05$)。我们的工作是第一篇关于 AE 架构适用于 3D CT SISR 任务的比较性研究,并为研究人员重新考虑模型架构选择,特别是针对 3D CT SISR 任务提供了基础。完整的实现和训练模型可以在以下网址找到:https://github.com/Roldbach/Autoencoder-3D-CT-SISR