Interpretable Auto Window Setting for Deep-Learning-Based CT Analysis
This work addresses the need for interpretable auto window setting in CT analysis for medical practitioners, offering a domain-invariant solution that enhances trust and usability, though it is incremental as it builds on existing deep learning architectures.
The paper tackles the lack of domain-invariant and interpretable methods for automatic window setting in CT analysis by proposing a plug-and-play module based on the Tanh activation function, resulting in Dice improvements of 10% to 200% on hard segmentation targets across multiple datasets.
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.