让手术阶段识别模型变得可解释，通过神经元与概念关联
SurgX: Neuron-Concept Association for Explainable Surgical Phase Recognition
- 用代表性视频序列找出关键神经元，建立手术概念集
- 成功关联神经元与手术概念，揭示模型决策依据
- 适合需要可信医疗AI的医生和算法开发者
手术阶段识别在手术流程分析中至关重要，支持手术监控、技能评估和流程优化等应用。尽管深度学习模型取得显著进展，但其决策过程仍不透明，难以理解与调试。为此，本文提出SurgX，一种基于概念的可解释性框架，通过将神经元与相关手术概念关联，提升模型可解释性。我们设计了选取代表性示例序列的方法，构建适配手术视频数据集的概念集合，完成神经元与概念的映射，并识别对预测至关重要的神经元。在两个手术阶段识别模型上进行了大量实验，验证了方法的有效性并分析了预测解释。结果表明，该方法能有效揭示模型决策逻辑。代码已开源：https://github.com/ailab-kyunghee/SurgX
原文摘要 · Abstract (English)
Surgical phase recognition plays a crucial role in surgical workflow analysis, enabling various applications such as surgical monitoring, skill assessment, and workflow optimization. Despite significant advancements in deep learning-based surgical phase recognition, these models remain inherently opaque, making it difficult to understand how they make decisions. This lack of interpretability hinders trust and makes it challenging to debug the model. To address this challenge, we propose SurgX, a novel concept-based explanation framework that enhances the interpretability of surgical phase recognition models by associating neurons with relevant concepts. In this paper, we introduce the process of selecting representative example sequences for neurons, constructing a concept set tailored to the surgical video dataset, associating neurons with concepts and identifying neurons crucial for predictions. Through extensive experiments on two surgical phase recognition models, we validate our method and analyze the explanation for prediction. This highlights the potential of our method in explaining surgical phase recognition. The code is available at https://github.com/ailab-kyunghee/SurgX
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。