In digital pathology, whole slide images (WSI) are crucial for cancer prognostication and treatment planning. WSI classification is generally addressed using multiple instance learning (MIL), alleviating the challenge of processing billions of pixels and curating rich annotations. Though recent MIL approaches leverage variants of the attention mechanism to learn better representations, they scarcely study the properties of the data distribution itself i.e., different staining and acquisition protocols resulting in intra-patch and inter-slide variations. In this work, we first introduce a distribution re-calibration strategy to shift the feature distribution of a WSI bag (instances) using the statistics of the max-instance (critical) feature. Second, we enforce class (bag) separation via a metric loss assuming that positive bags exhibit larger magnitudes than negatives. We also introduce a generative process leveraging Vector Quantization (VQ) for improved instance discrimination i.e., VQ helps model bag latent factors for improved classification. To model spatial and context information, a position encoding module (PEM) is employed with transformer-based pooling by multi-head self-attention (PMSA). Evaluation of popular WSI benchmark datasets reveals our approach improves over state-of-the-art MIL methods. Further, we validate the general applicability of our method on classic MIL benchmark tasks and for point cloud classification with limited points https://github.com/PhilipChicco/FRMIL.

中文翻译：

---

FR-MIL：基于分布重新校准的多实例学习，使用 Transformer 进行整个幻灯片图像分类。


在数字病理学中，全幻灯片图像 (WSI) 对于癌症预测和治疗计划至关重要。 WSI 分类通常使用多实例学习 (MIL) 来解决，从而减轻了处理数十亿像素和管理丰富注释的挑战。尽管最近的 MIL 方法利用注意力机制的变体来学习更好的表示，但它们很少研究数据分布本身的属性，即不同的染色和采集协议导致补丁内和幻灯片间的变化。在这项工作中，我们首先引入一种分布重新校准策略，使用最大实例（关键）特征的统计数据来改变 WSI 包（实例）的特征分布。其次，我们通过度量损失强制进行类（袋）分离，假设正袋表现出比负袋更大的量级。我们还引入了利用矢量量化 (VQ) 来改进实例辨别的生成过程，即 VQ 有助于对包潜在因子进行建模以改进分类。为了对空间和上下文信息进行建模，位置编码模块（PEM）与多头自注意力（PMSA）基于变压器的池化结合使用。对流行的 WSI 基准数据集的评估表明，我们的方法比最先进的 MIL 方法有所改进。此外，我们验证了我们的方法在经典 MIL 基准任务和有限点点云分类上的普遍适用性 https://github.com/PhilipChicco/FRMIL。