Annu Int Conf IEEE Eng Med Biol Soc. 2022 Jul;2022:3059-3062. doi: 10.1109/EMBC48229.2022.9871687.
Transfer learning from ImageNet pretrained weights is widely used when training Deep Learning models on a Histopathology dataset. However, the visual features of the two domains are different. Rather than ImageNet pretrained weights, pre-training on a Histopathology dataset may provide better initialization. To prove this hypothesis, we train two commonly used Deep Learning model architectures - ResNet and DenseNet on a complex Histopathology classification dataset, and compare transfer learning performance with ImageNet pretrained weights. Based on the fine-tuning on three histopathology datasets including two different stains (H&E and IHC), we show that the domain specific pretrained weights are better suited for transfer learning. This is reflected by higher performance, lower training time as well as better feature reuse. Clinical Relevance - The paper establishes merit of using Histopathology domain specific pretrained weights rather than ImageNet pretrained weights.
在病理数据集上训练深度学习模型时，广泛采用从 ImageNet 预训练权重进行迁移学习。然而，两个领域的视觉特征不同。与其使用 ImageNet 预训练权重，不如在病理数据集上进行预训练，从而为模型提供更好的初始化。为了验证这一假设，我们在一个复杂的病理分类数据集上训练了两种常用的深度学习模型架构——ResNet 和 DenseNet，并将迁移学习性能与 ImageNet 预训练权重进行了比较。基于对包括两种不同染色（H&E 和 IHC）的三个病理数据集的微调，我们表明特定于领域的预训练权重更适合迁移学习。这体现在更高的性能、更短的训练时间以及更好的特征重用上。临床相关性——本文证明了使用病理领域特定预训练权重而非 ImageNet 预训练权重的优势。
