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

TL;DR

This paper presents a multimodal PET-CT segmentation framework for bone infections that leverages dual-source annotations and rigorous patient-level evaluation to improve accuracy and robustness in clinical AI applications.

Contribution

It introduces a dual-source learning approach with independent expert annotations and a patient-level 3D evaluation method for more reliable bone infection segmentation.

Findings

Multimodal PET-CT fusion improves segmentation performance.

Decoupled dual-source training captures diverse expert diagnostic philosophies.

Patient-level 3D evaluation provides more robust performance assessment.

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. 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 representation.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. 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. 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.