The gold standard for diagnosing lymph node metastasis of papillary thyroid carcinoma is to analyze the whole slide histopathological images (WSIs). Due to the large size of WSIs, recent computer-aided diagnosis approaches adopt the multi-instance learning (MIL) strategy and the key part is how to effectively aggregate the information of different instances (patches). In this paper, a novel transformer-guided framework is proposed to predict lymph node metastasis from WSIs, where we incorporate the transformer mechanism to improve the accuracy from three different aspects. First, we propose an effective transformer-based module for discriminative patch feature extraction, including a lightweight feature extractor with a pruned transformer (Tiny-ViT) and a clustering-based instance selection scheme. Next, we propose a new Transformer-MIL module to capture the relationship of different discriminative patches with sparse distribution on WSIs and better nonlinearly aggregate patch-level features into the slide-level prediction. Considering that the slide-level annotation is relatively limited to training a robust Transformer-MIL, we utilize the pathological relationship between the primary tumor and its lymph node metastasis and develop an effective attention-based mutual knowledge distillation (AMKD) paradigm. Experimental results on our collected WSI dataset demonstrate the efficiency of the proposed Transformer-MIL and attention-based knowledge distillation. Our method outperforms the state-of-the-art methods by over 2.72% in AUC (area under the curve).

中文翻译：

---

使用 Transformer 引导的多实例学习和知识转移从整个幻灯片图像预测淋巴结转移

诊断甲状腺乳头状癌淋巴结转移的金标准是分析整个载玻片的组织病理学图像（WSI）。由于 WSI 的规模很大，最近的计算机辅助诊断方法采用多实例学习 (MIL) 策略，关键部分是如何有效地聚合不同实例（补丁）的信息。在本文中，提出了一种新的变压器引导框架来预测 WSI 的淋巴结转移，其中我们结合了变压器机制以从三个不同方面提高准确性。首先，我们提出了一个有效的基于转换器的模块用于判别补丁特征提取，包括一个带有修剪转换器（Tiny-ViT）的轻量级特征提取器和一个基于聚类的实例选择方案。下一个，我们提出了一个新的 Transformer-MIL 模块来捕获 WSI 上具有稀疏分布的不同判别补丁之间的关系，并更好地将补丁级特征非线性地聚合到幻灯片级预测中。考虑到幻灯片级注释相对仅限于训练健壮的 Transformer-MIL，我们利用原发肿瘤与其淋巴结转移之间的病理关系，开发了一种有效的基于注意力的相互知识蒸馏 (AMKD) 范式。我们收集的 WSI 数据集的实验结果证明了所提出的 Transformer-MIL 和基于注意力的知识蒸馏的效率。我们的方法在 AUC（曲线下面积）方面优于最先进的方法超过 2.72%。