发表机构
Politecnico di Milano（米兰理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述提出以条件为中心的分类法，沿外部知识类型、知识集成范式、生成架构三个维度组织条件3D CT生成研究，系统化现有方法并指出未来研究方向。
AI 中文摘要
由外部知识引导的可控生成是现代生成式深度学习应用的关键需求，可实现对语义内容、结构属性和变异性有明确约束的样本合成。在3D计算机断层扫描（CT）领域，这种控制对临床应用至关重要，包括数据增强、隐私保护数据共享以及特定解剖或病理场景的模拟。尽管条件3D CT生成的研究发展迅速，但现有方法的多样性使得系统比较变得困难，并掩盖了基本的设计选择。在本综述中，我们提出了一种以条件为中心的分类法，该分类法沿三个正交维度对文献进行组织：外部知识的类型（K）、知识集成范式（I）和生成架构（A）。这种分解定义了一个显式的设计空间（K×I×A），为先前的工作提供了统一的视角。使用该框架，我们对现有方法进行系统化，确定主导趋势和重复出现的设计模式，并强调设计空间中未充分探索的区域，这些区域指向未来研究的有前景方向。
英文摘要
Controllable generation guided by external knowledge is a key requirement in modern generative deep learning applications, enabling the synthesis of samples with explicit constraints on semantic content, structural properties, and variability. In 3D Computed Tomography (CT), such control is essential for clinical applications, including data augmentation, privacy-preserving data sharing, and the simulation of specific anatomical or pathological scenarios. While research on conditional 3D CT generation has expanded rapidly, the diversity of existing approaches makes systematic comparison difficult and obscures fundamental design choices. In this survey, we propose a conditioning-centric taxonomy that organizes the literature along three orthogonal dimensions: the type of external knowledge (K), the knowledge integration paradigm (I), and the generative architecture (A). This factorization defines an explicit design space (K x I x A) that provides a unified perspective on prior work. Using this framework, we systematize existing methods, identify dominant trends and recurring design patterns, and highlight underexplored regions of the design space that point toward promising directions for future research.
CommentsAccepted to IJCAI-ECAI 2026, Survey Track
