用生成干预方法审计肺癌风险模型，发现其存在误判隐患
Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions
- 通过3D扩散建模系统性修改解剖特征，分离特定结构对风险评分的因果影响
- 验证发现模型对临床无关伪影敏感，且存在径向偏差等致命缺陷
- 首个对Sybil模型的干预式审计，适合医疗AI安全评估者参考
肺癌仍是癌症死亡主因，推动了自动化筛查工具的发展以减轻放射科医生负担。前沿代表是Sybil模型，仅凭计算机断层扫描（CT）即可高精度预测未来风险。然而，尽管经过广泛临床验证，现有评估仍依赖观察性指标。这种相关性方法忽视了模型的真实推理机制，亟需转向因果验证以确保临床部署前的稳健决策。我们提出S(H)NAP框架，一种无需依赖模型的审计方法，通过专家放射科医生验证的生成干预归因实现。利用真实3D扩散桥接建模，系统性修改解剖特征，从而隔离特定对象对风险评分的因果贡献。首次对Sybil进行干预审计，结果显示：尽管模型常表现出类似专家的行为，能区分恶性与良性肺结节，但存在严重缺陷，包括对临床无关伪影的高度敏感性及明显的径向偏差。
原文摘要 · Abstract (English)
Lung cancer remains the leading cause of cancer mortality, driving the development of automated screening tools to alleviate radiologist workload. Standing at the frontier of this effort is Sybil, a deep learning model capable of predicting future risk solely from computed tomography (CT) with high precision. However, despite extensive clinical validation, current assessments rely purely on observational metrics. This correlation-based approach overlooks the model's actual reasoning mechanism, necessitating a shift to causal verification to ensure robust decision-making before clinical deployment. We propose S(H)NAP, a model-agnostic auditing framework that constructs generative interventional attributions validated by expert radiologists. By leveraging realistic 3D diffusion bridge modeling to systematically modify anatomical features, our approach isolates object-specific causal contributions to the risk score. Providing the first interventional audit of Sybil, we demonstrate that while the model often exhibits behavior akin to an expert radiologist, differentiating malignant pulmonary nodules from benign ones, it suffers from critical failure modes, including dangerous sensitivity to clinically unjustified artifacts and a distinct radial bias.
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。