Cross-Source Supervision for Bone Infection Segmentation in Dual-Modality PET-CT

用于双模态 PET-CT 骨感染分割的跨源监督方法

Abstract: Early and accurate diagnosis and lesion localization of bone infections are crucial for clinical treatment. PET-CT integrates anatomical information from CT with metabolic information from PET, making it an important imaging modality for diagnosing bone infections. However, accurate lesion segmentation remains challenging due to indistinct lesion boundaries and inconsistencies in annotations generated by different experts or automated systems.

摘要： 骨感染的早期准确诊断和病灶定位对于临床治疗至关重要。PET-CT 将 CT 的解剖信息与 PET 的代谢信息相结合，使其成为诊断骨感染的重要成像模态。然而，由于病灶边界模糊以及不同专家或自动化系统生成的标注存在不一致性，准确的病灶分割仍然具有挑战性。

In this work, we investigate multimodal segmentation of bone infections under annotation discrepancy. We develop a bimodal end-to-end segmentation framework that integrates PET metabolic signals and CT bone-window anatomy through an early-fusion multimodal approach. To mitigate performance inflation caused by inter-slice correlation in small datasets, this study discards traditional two-dimensional evaluation methods and implements a rigorous patient-level 3D volumetric evaluation and cross-validation.

在这项工作中，我们研究了在标注差异存在的情况下，骨感染的多模态分割问题。我们开发了一个双模态端到端分割框架，通过早期融合的多模态方法整合了 PET 代谢信号和 CT 骨窗解剖结构。为了减轻小数据集中切片间相关性导致的性能虚高，本研究摒弃了传统的二维评估方法，实施了严格的患者级 3D 体积评估和交叉验证。

Furthermore, instead of forcing a singular consensus, we propose a decoupled dual-source learning framework where parallel models are trained on independent expert annotations driven by high-sensitivity and high-specificity clinical intents. Experimental results objectively report performance variations at the patient level (Mean + SD and Mean - SD), demonstrating the effectiveness of multimodal PET-CT fusion.

此外，我们没有强求单一的共识，而是提出了一种解耦的双源学习框架，其中并行模型在由高灵敏度和高特异性临床意图驱动的独立专家标注上进行训练。实验结果客观地报告了患者层面的性能差异（均值 + 标准差和均值 - 标准差），证明了多模态 PET-CT 融合的有效性。

The cross-evaluation matrix quantitatively reveals how models successfully internalize distinct expert diagnostic philosophies, providing a robust, diversity-preserving paradigm for clinical AI deployment in bone infection segmentation.

交叉评估矩阵定量地揭示了模型如何成功内化不同的专家诊断理念，为骨感染分割中的临床 AI 部署提供了一种稳健且保留多样性的范式。