提出可解释的自动CT窗宽设置模块，提升深度学习分割效果
Interpretable Auto Window Setting for Deep-Learning-Based CT Analysis
- 基于CT物理原理设计Tanh启发的可插拔模块
- 在多个数据集上使难分割目标的Dice提升10%~200%
- 兼顾医生理解与模型性能，适合临床部署
无论是在CT技术普及初期还是当前阶段，窗宽设置始终是CT分析不可或缺的环节。尽管已有研究探索了多窗宽融合对神经网络的增强作用，但缺乏领域无关且直观可解释的自动窗宽设置方法。本文提出一种源自Tanh激活函数的即插即用模块，兼容主流深度学习架构。基于CT物理原理，坚持可解释性原则，确保模块在医疗应用中的可靠性。其领域无关设计使自适应机制的决策偏好能从临床直观角度观察，不仅便于神经网络专家理解，也更易获得临床医生信任。在多个开源数据集上验证有效，对难分割目标的Dice评分提升达10%~200%。
原文摘要 · Abstract (English)
Whether during the early days of popularization or in the present, the window setting in Computed Tomography (CT) has always been an indispensable part of the CT analysis process. Although research has investigated the capabilities of CT multi-window fusion in enhancing neural networks, there remains a paucity of domain-invariant, intuitively interpretable methodologies for Auto Window Setting. In this work, we propose an plug-and-play module originate from Tanh activation function, which is compatible with mainstream deep learning architectures. Starting from the physical principles of CT, we adhere to the principle of interpretability to ensure the module's reliability for medical implementations. The domain-invariant design facilitates observation of the preference decisions rendered by the adaptive mechanism from a clinically intuitive perspective. This enables the proposed method to be understood not only by experts in neural networks but also garners higher trust from clinicians. We confirm the effectiveness of the proposed method in multiple open-source datasets, yielding 10%~200% Dice improvements on hard segment targets.
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。