Medical images offer a non-invasive method to diagnose different diseases, but using them manually produces unreliable results. Modern deep learning architectures and techniques are computed and data-intensive, making them difficult to use for relatively smaller datasets of medical images. Transfer learning has been used as a remedy for the problem mentioned above. However, the domain difference between the datasets used for pre-training (e.g., ImageNet) and the target datasets, like medical images, negatively impacts the transfer learning results. Recently, many researchers have used additional pre-training called domain-adaptive pre-training (DAPT) using the data from the target domain (e.g., medical images) before using the model on the target tasks to achieve superior performance. This study proposes a variant of DAPT by performing it on a subset of the architecture. It has achieved state-of-the-art performance for brain tumor grading on the BraTS 2019 while being computationally efficient.

中文翻译：

---

使用多步预训练进行脑肿瘤分级分类

医学图像提供了一种非侵入性方法来诊断不同的疾病，但手动使用它们会产生不可靠的结果。现代深度学习架构和技术是计算密集型和数据密集型的，这使得它们很难用于相对较小的医学图像数据集。迁移学习已被用来解决上述问题。然而，用于预训练的数据集（例如 ImageNet）和目标数据集（如医学图像）之间的域差异会对迁移学习结果产生负面影响。最近，许多研究人员在将模型用于目标任务之前，使用来自目标域（例如医学图像）的数据进行称为域自适应预训练（DAPT）的额外预训练，以实现卓越的性能。本研究通过在架构的子集上执行 DAPT 提出了一种变体。它在 BraTS 2019 上实现了最先进的脑肿瘤分级性能，同时计算效率高。