Deep Neural Networks (DNNs) have shown remarkable success in various computer vision tasks. However, their black-box nature often leads to difficulty in interpreting their decisions, creating an unfilled need for methods to explain the decisions, and ultimately forming a barrier to their wide acceptance especially in biomedical applications. This work introduces a novel method, Pixel-wise Channel Isolation Mixing (PCIM), to calculate pixel attribution maps, highlighting the image parts most crucial for a classification decision but without the need to extract internal network states or gradients. Unlike existing methods, PCIM treats each pixel as a distinct input channel and trains a blending layer to mix these pixels, reflecting specific classifications. This unique approach allows the generation of pixel attribution maps for each image, but agnostic to the choice of the underlying classification network. Benchmark testing on three application relevant, diverse high content Imaging datasets show state-of-the-art performance, particularly for model fidelity and localization ability in both, fluorescence and bright field High Content Imaging. PCIM contributes as a unique and effective method for creating pixel-level attribution maps from arbitrary DNNs, enabling interpretability and trust.

翻译：深度神经网络（DNN）在各种计算机视觉任务中展现出卓越性能。然而，其黑盒特性常导致决策难以解释，这催生了对决策解释方法的需求，并最终阻碍了其广泛应用，尤其在生物医学领域。本文提出了一种新方法——像素级通道隔离混合（PCIM），用于计算像素归因图，以突出对分类决策最关键的区域，且无需提取网络内部状态或梯度。与现有方法不同，PCIM将每个像素视为独立的输入通道，并训练一个混合层来融合这些像素以反映特定分类。这一独特方法可为每幅图像生成像素归因图，且与底层分类网络的选择无关。在三个应用相关、多样化的高内涵成像数据集上的基准测试表明，该方法在模型保真度和定位能力方面（尤其在荧光和明场高内涵成像中）均达到最先进水平。PCIM作为一种独特而有效的方法，能够从任意DNN生成像素级归因图，从而增强模型的可解释性与可信度。