用反事实解释3D CT影像分类模型，让医生看得懂结果
Explaining 3D Computed Tomography Classifiers with Counterfactuals
- 用切片自编码器+梯度屏蔽，降低3DCT解释的内存开销
- 在两种临床预测与肺部分割任务中生成可读反事实样本
- 适合需要解释3D医学影像模型的临床研究者
反事实解释能提升医学影像深度学习模型的可解释性，但将该方法应用于3D CT扫描面临体数据复杂性和资源消耗的挑战。本文将2D场景下的潜在空间转移反事实生成方法扩展至3D CT影像分类模型。针对3D分类器训练样本少、内存需求高的问题，提出基于切片的自编码器结构，并仅对特定切片块允许梯度传播，其余部分阻断梯度。该方法利用在单个CT切片上预训练的2D编码器，通过组合切片保持三维上下文信息。我们在两个临床表型预测和肺部分割模型上验证了该方法的有效性，结果表明该方法在高分辨率3D医学影像中兼具内存效率与可解释性。
原文摘要 · Abstract (English)
Counterfactual explanations enhance the interpretability of deep learning models in medical imaging, yet adapting them to 3D CT scans poses challenges due to volumetric complexity and resource demands. We extend the Latent Shift counterfactual generation method from 2D applications to explain 3D computed tomography (CT) scans classifiers. We address the challenges associated with 3D classifiers, such as limited training samples and high memory demands, by implementing a slice-based autoencoder and gradient blocking except for specific chunks of slices. This method leverages a 2D encoder trained on CT slices, which are subsequently combined to maintain 3D context. We demonstrate this technique on two models for clinical phenotype prediction and lung segmentation. Our approach is both memory-efficient and effective for generating interpretable counterfactuals in high-resolution 3D medical imaging.
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。