TriDeNT：用于组织病理学中特权知识蒸馏的三重深度网络训练
TriDeNT: Triple Deep Network Training for Privileged Knowledge Distillation in Histopathology
AI总结：
TriDeNT提出一种自监督方法，利用推理时不可用的特权数据（如IHC染色、空间转录组学和专家标注）进行知识蒸馏，在下游任务中显著优于现有方法，最高提升101%。
摘要：
计算病理学模型很少利用在推理时不可用的数据。这意味着大多数模型无法从高度信息化的数据中学习，例如额外的免疫组织化学（IHC）染色和空间转录组学。我们提出TriDeNT，一种新颖的自监督方法，用于利用推理时不可用的特权数据来提升性能。我们展示了该方法在一系列不同配对数据上的有效性，包括免疫组织化学、空间转录组学和专家细胞核标注。在所有设置中，TriDeNT在下游任务中均优于其他最先进方法，观察到最高达101%的改进。此外，我们提供了这些模型所学特征的定性和定量测量，以及它们与基线的差异。TriDeNT提供了一种在训练期间从稀缺或昂贵数据中蒸馏知识的新方法，从而为常规输入创建显著更好的模型。
英文摘要：
Computational pathology models rarely utilise data that will not be available for inference. This means most models cannot learn from highly informative data such as additional immunohistochemical (IHC) stains and spatial transcriptomics. We present TriDeNT, a novel self-supervised method for utilising privileged data that is not available during inference to improve performance. We demonstrate the efficacy of this method for a range of different paired data including immunohistochemistry, spatial transcriptomics and expert nuclei annotations. In all settings, TriDeNT outperforms other state-of-the-art methods in downstream tasks, with observed improvements of up to 101%. Furthermore, we provide qualitative and quantitative measurements of the features learned by these models and how they differ from baselines. TriDeNT offers a novel method to distil knowledge from scarce or costly data during training, to create significantly better models for routine inputs.
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。
