医学影像中的反事实解释：探索 SPN 引导的潜空间操控
Counterfactual Explanations in Medical Imaging: Exploring SPN-Guided Latent Space Manipulation
AI总结：
本文提出用 SPN 建模半监督 VAE 潜空间并引导反事实优化，使医学影像反事实同时贴近原数据与目标类别分布，且在 cheXpert 上验证其效果。
摘要：
人工智能正越来越多地被应用于各个领域，以自动化对人类生活产生重大影响的决策过程。在医学图像分析中，深度学习模型已展现出卓越性能。然而，其内在复杂性使其成为黑箱系统，引发了对可靠性和可解释性的担忧。反事实解释通过呈现可改变模型分类结果的假设性“如果……会怎样”情景，为决策过程提供可理解的洞察。通过检查输入变化，反事实解释可给出影响决策过程的模式。尽管具有潜力，生成既符合相似性约束、又能提供人类可解释说明的合理反事实仍是一项挑战。本文通过一种模型特定的优化方法研究该挑战。尽管变分自编码器（VAE）等深度生成模型具有强大生成能力，求和-乘积网络（SPN）等概率模型能够高效表示复杂联合概率分布。通过使用 SPN 对半监督 VAE 的潜空间似然进行建模，我们利用其双重角色：既作为潜空间描述符，又作为给定判别任务的分类器。该形式化使得能够优化潜空间反事实，使其既接近原始数据分布，又与目标类别分布保持一致。我们在 cheXpert 数据集上进行实验评估。为评估整合 SPN 的有效性，将我们的 SPN 引导潜空间操控与神经网络基线进行比较。此外，还分析了潜变量正则化与反事实质量之间的权衡。
英文摘要：
Artificial intelligence is increasingly leveraged across various domains to automate decision-making processes that significantly impact human lives. In medical image analysis, deep learning models have demonstrated remarkable performance. However, their inherent complexity makes them black box systems, raising concerns about reliability and interpretability. Counterfactual explanations provide comprehensible insights into decision processes by presenting hypothetical "what-if" scenarios that alter model classifications. By examining input alterations, counterfactual explanations provide patterns that influence the decision-making process. Despite their potential, generating plausible counterfactuals that adhere to similarity constraints providing human-interpretable explanations remains a challenge. In this paper, we investigate this challenge by a model-specific optimization approach. While deep generative models such as variational autoencoders (VAEs) exhibit significant generative power, probabilistic models like sum-product networks (SPNs) efficiently represent complex joint probability distributions. By modeling the likelihood of a semi-supervised VAE's latent space with an SPN, we leverage its dual role as both a latent space descriptor and a classifier for a given discrimination task. This formulation enables the optimization of latent space counterfactuals that are both close to the original data distribution and aligned with the target class distribution. We conduct experimental evaluation on the cheXpert dataset. To evaluate the effectiveness of the integration of SPNs, our SPN-guided latent space manipulation is compared against a neural network baseline. Additionally, the trade-off between latent variable regularization and counterfactual quality is analyzed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
