Zhou Siqiong, Islam Upala J, Pfeiffer Nicholaus, Banerjee Imon, Patel Bhavika K, Iquebal Ashif S
School of Computing and Augmented Intelligence, Arizona State University.
Department of Radiology, Mayo Clinic.
IEEE Trans Autom Sci Eng. 2024 Jul;21(3):2264-2275. doi: 10.1109/tase.2023.3333788. Epub 2023 Nov 23.
Imaging phenotypes extracted via radiomics of magnetic resonance imaging have shown great potential in predicting the treatment response in breast cancer patients after administering neoadjuvant systemic therapy (NST). Understanding the causal relationships between the treatment response and Imaging phenotypes, Clinical information, and Molecular (ICM) features are critical in guiding treatment strategies and management plans. Counterfactual explanations provide an interpretable approach to generating causal inference. However, existing approaches are either computationally prohibitive for high dimensional problems, generate unrealistic counterfactuals, or confound the effects of causal features by changing multiple features simultaneously. This paper proposes a new method called Sparse CounteRGAN (SCGAN) for generating counterfactual instances to reveal causal relationships between ICM features and the treatment response after NST. The generative approach learns the distribution of the original instances and, therefore, ensures that the new instances are realistic. We propose dropout training of the discriminator to promote sparsity and introduce a diversity term in the loss function to maximize the distances among generated counterfactuals. We evaluate the proposed method on two publicly available datasets, followed by the breast cancer dataset, and compare their performance with existing methods in the literature. Results show that SCGAN generates sparse and diverse counterfactual instances that also achieve plausibility and feasibility, making it a valuable tool for understanding the causal relationships between ICM features and treatment response.
通过磁共振成像的放射组学提取的影像表型在预测新辅助全身治疗（NST）后乳腺癌患者的治疗反应方面显示出巨大潜力。了解治疗反应与影像表型、临床信息和分子（ICM）特征之间的因果关系对于指导治疗策略和管理计划至关重要。反事实解释为生成因果推断提供了一种可解释的方法。然而，现有方法要么在计算上对于高维问题来说代价过高，要么生成不现实的反事实，要么通过同时改变多个特征来混淆因果特征的影响。本文提出了一种名为稀疏对抗生成网络（SCGAN）的新方法，用于生成反事实实例，以揭示NST后ICM特征与治疗反应之间的因果关系。生成方法学习原始实例的分布，因此确保新实例是现实的。我们提出对判别器进行随机失活训练以促进稀疏性，并在损失函数中引入一个多样性项，以使生成的反事实之间的距离最大化。我们在两个公开可用的数据集上评估了所提出的方法，随后在乳腺癌数据集上进行评估，并将其性能与文献中的现有方法进行比较。结果表明，SCGAN生成了稀疏且多样的反事实实例，这些实例也具有合理性和可行性，使其成为理解ICM特征与治疗反应之间因果关系的有价值工具。
