ADS_UNet：一种用于组织病理学图像分割的嵌套UNet
ADS_UNet: A Nested UNet for Histopathology Image Segmentation
AI总结：
本文提出ADS_UNet，一种逐阶段累加的训练算法，通过在较浅层引入资源高效的深度监督并结合性能加权的子UNet，提升了组织病理学图像分割性能，同时大幅降低了GPU消耗和训练时间。
摘要：
UNet模型由排列为收缩编码器和上采样解码器映射的全卷积网络（FCN）层构成。这些编码器和解码器映射的嵌套排列衍生出了UNet模型的扩展，如UNete和UNet++。其他改进包括约束卷积层的输出，使其在端到端训练时能够区分分割标签，这一特性被称为深度监督。尽管这些嵌套UNet模型具有庞大的参数空间，但这降低了它们内部的特征多样性。此外，对于纹理分割，多尺度下的像素相关性有助于分类任务；因此，对较浅层进行显式的深度监督可能会提升性能。本文提出ADS_UNet，这是一种逐阶段累加的训练算法，在较浅层中引入了资源高效的深度监督，并采用性能加权的子UNet组合来构建分割模型。我们在三个组织病理学数据集上提供了实证证据，以支持所提出的ADS_UNet能够减少构成特征之间的相关性，并在提升性能的同时提高资源效率。我们证明，ADS_UNet在CRAG和BCSS数据集上分别比最先进的基于Transformer的模型高出1.08和0.6个百分点，然而其所需的GPU消耗和训练时间分别仅为Transformer的37%和34%。
英文摘要：
The UNet model consists of fully convolutional network (FCN) layers arranged as contracting encoder and upsampling decoder maps. Nested arrangements of these encoder and decoder maps give rise to extensions of the UNet model, such as UNete and UNet++. Other refinements include constraining the outputs of the convolutional layers to discriminate between segment labels when trained end to end, a property called deep supervision. This reduces feature diversity in these nested UNet models despite their large parameter space. Furthermore, for texture segmentation, pixel correlations at multiple scales contribute to the classification task; hence, explicit deep supervision of shallower layers is likely to enhance performance. In this paper, we propose ADS UNet, a stage-wise additive training algorithm that incorporates resource-efficient deep supervision in shallower layers and takes performance-weighted combinations of the sub-UNets to create the segmentation model. We provide empirical evidence on three histopathology datasets to support the claim that the proposed ADS UNet reduces correlations between constituent features and improves performance while being more resource efficient. We demonstrate that ADS_UNet outperforms state-of-the-art Transformer-based models by 1.08 and 0.6 points on CRAG and BCSS datasets, and yet requires only 37% of GPU consumption and 34% of training time as that required by Transformers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
