Plausible but Unimplantable: A Trustworthiness Audit of Shape Completion Foundation Models for Cranial Defect Reconstruction
作者: Marek Wodzinski, Kamil Kwarciak, Daria Hemmerling, Mateusz Daniol
分类: cs.CV
发布日期: 2026-10-21
备注: ACCV 2026 TrustFMI accepted
💡 一句话要点
审计颅骨缺损重建的形状补全基础模型的可信度
🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 颅骨重建 形状补全 基础模型 医疗影像 个性化医疗 模型审计 临床应用
📋 核心要点
- 现有的颅骨缺损重建方法依赖手动CAD绘制，效率低且成本高。
- 论文审计了三种形状补全基础模型，评估其在颅骨缺损重建中的应用效果。
- 实验结果显示，所有模型均未能提供可植入的解决方案，且效果不如简单返回患者自身骨骼。
📝 摘要（中文）
对于失去部分颅骨的患者，需要精确适配缺损的植入物，而目前仍由专家手动在CAD中绘制，导致每个案例处理缓慢且成本高昂。本文审计了三种公开发布的预训练形状补全模型，应用于239个颅骨缺损案例。结果显示，所有模型的输出均无法在不干扰患者剩余骨骼的情况下实现植入，且在210个雕刻缺损中，均未能超越简单返回患者自身骨骼的效果。这表明现有的形状补全基础模型在临床实践中不可用，亟需针对可信的基础模型进行深入研究。
🔬 方法详解
问题定义：本文旨在解决颅骨缺损重建中植入物设计的效率和准确性问题。现有方法依赖手动绘制，导致处理时间长且成本高昂。
核心思路：通过审计预训练的形状补全模型，探索其在颅骨缺损重建中的应用潜力，期望减少手动设计的需求。
技术框架：研究采用零-shot方法对239个颅骨缺损进行评估，比较模型输出与患者自身骨骼的适配性，分析模型在不干扰剩余骨骼的情况下的植入能力。
关键创新：论文的创新在于首次系统审计了形状补全基础模型在临床应用中的可信度，揭示了当前模型在实际应用中的局限性。
关键设计：实验中对模型输出进行了严格的比较，重点关注输出材料是否能够在不干扰患者剩余骨骼的情况下进行植入，且未能找到有效的植入方案。
🖼️ 关键图片
📊 实验亮点
实验结果显示，在210个雕刻缺损案例中，所有模型均未能超越简单返回患者自身骨骼的效果。在29个真实案例中，仅有一个模型的表现略优于随机猜测，且没有任何模型的输出能够实现植入，显示出当前模型的局限性。
🎯 应用场景
该研究的潜在应用领域包括医疗影像处理、个性化医疗和颅骨重建手术。通过改进形状补全模型的可信度，未来可实现更高效的颅骨缺损重建，降低手术成本，提高患者的生活质量。
📄 摘要（原文）
A patient who has lost part of the skull vault needs an implant that fits the defect exactly, and such implants are still drawn by hand in CAD by specialists, which makes each case slow and expensive. The task can be considered as a shape completion problem, so pretrained completion models, and now the first shape completion foundation models, look like a way to remove that manual step. We audited three publicly released pretrained shape completion models, two of them foundation models, applied zero-shot to 239 cranial defects, some carved from public skull datasets and some real post-craniectomy cases. Each output was compared with simply returning the patient's own remaining bone, and tested for whether the predicted material could be placed without intersecting the bone that is still there. On the 210 carved defects none of the three improved on doing nothing, and on the 29 real cases only one did so beyond chance. Yet not one output, from any model in any configuration, was implantable: none managed both to stay clear of the bone the patient still has and to place more material than doing nothing, where a task-specific volumetric model, trained for this task and selected on these cases, was implantable on all but one. The output that most convincingly resembles a skull is no more placeable than the rest, and at these point densities implant thickness cannot be read off the emitted points at all, which is a property of the output representation rather than of any one model. On this evidence the shape completion foundation models we could obtain cannot be trusted and, used as released, are not usable in clinical practice. Substantial research towards trustworthy foundation models for shape completion is still needed.