通过聚类激活揭示病理模型全局行为，提升可解释性。
Explaining Digital Pathology Models via Clustering Activations
- 用聚类分析模型激活特征，揭示整体判别模式。
- 在前列腺癌检测任务中验证了方法的有效性。
- 适合希望理解模型决策依据的临床研究者。
我们提出一种基于聚类的数字病理模型可解释性技术，针对卷积神经网络构建。与常用基于显著图的方法（如遮挡、GradCAM、相关性传播）不同，这些方法仅关注单张切片中对预测贡献最大的区域，本方法展现模型的全局行为，同时提供更细粒度的信息。结果聚类可可视化，不仅有助于理解模型，还能增强对其运行的信任，促进其在临床实践中的快速采纳。我们在现有前列腺癌检测模型上评估了该技术的性能，证明了其有效性。
原文摘要 · Abstract (English)
We present a clustering-based explainability technique for digital pathology models based on convolutional neural networks. Unlike commonly used methods based on saliency maps, such as occlusion, GradCAM, or relevance propagation, which highlight regions that contribute the most to the prediction for a single slide, our method shows the global behaviour of the model under consideration, while also providing more fine-grained information. The result clusters can be visualised not only to understand the model, but also to increase confidence in its operation, leading to faster adoption in clinical practice. We also evaluate the performance of our technique on an existing model for detecting prostate cancer, demonstrating its usefulness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。