论文标题
自我监督的视觉变形金刚学习组织病理学的视觉概念
Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology
论文作者
论文摘要
组织表型是学习癌症病理学肿瘤免疫微环境中组织病理生物标志物的客观特征的基本任务。然而，全曲线成像（WSI）是一个复杂的计算机视觉，其中：1）WSI具有巨大的图像分辨率，并且在数据策划中排除了大规模像素级的努力，而2）形态学表型的多样性会导致在组织标记中的际和内部和内部观察者的可变性。为了解决这些局限性，目前提出了使用验证的图像编码器（从成像网的转移学习，自学预读的转移学习），从而从病理学中提取形态学特征，但尚未得到广泛验证。在这项工作中，我们通过培训各种自我监督模型，对各种弱监督和补丁级的任务进行验证，以搜索病理学的良好表现。我们的主要发现是发现，使用基于恐龙的知识蒸馏的视觉变压器能够在组织学图像中学习数据效率和可解释的特征，其中不同的注意力头脑学习不同的形态表型。我们在以下网址进行评估代码和预估计的权重：https：//github.com/richarizardd/selfs-supervised-vit-path。
Tissue phenotyping is a fundamental task in learning objective characterizations of histopathologic biomarkers within the tumor-immune microenvironment in cancer pathology. However, whole-slide imaging (WSI) is a complex computer vision in which: 1) WSIs have enormous image resolutions with precludes large-scale pixel-level efforts in data curation, and 2) diversity of morphological phenotypes results in inter- and intra-observer variability in tissue labeling. To address these limitations, current efforts have proposed using pretrained image encoders (transfer learning from ImageNet, self-supervised pretraining) in extracting morphological features from pathology, but have not been extensively validated. In this work, we conduct a search for good representations in pathology by training a variety of self-supervised models with validation on a variety of weakly-supervised and patch-level tasks. Our key finding is in discovering that Vision Transformers using DINO-based knowledge distillation are able to learn data-efficient and interpretable features in histology images wherein the different attention heads learn distinct morphological phenotypes. We make evaluation code and pretrained weights publicly-available at: https://github.com/Richarizardd/Self-Supervised-ViT-Path.
