A Data-Centric Framework for Intraoperative Fluorescence Lifetime Imaging for Glioma Surgical Guidance

2026-04-28

AI Summary

This study addresses the clinical challenge of precisely delineating infiltrative glioma margins during surgery, which limits maximal tumor resection while preserving functional brain regions. The work introduces, for the first time, a data-centric artificial intelligence strategy into intraoperative fluorescence lifetime imaging (FLIm) analysis, systematically enhancing data quality and model robustness through confidence learning, iterative label refinement, and selective relabeling. By integrating a multi-class FLIm classification model with SHAP-based interpretability, the approach achieves 96% accuracy in discriminating three levels of tumor cell density. Furthermore, it uncovers distinct optical signatures associated with varying degrees of tumor infiltration and elucidates biological and acquisition-related factors underlying low-confidence predictions.

Abstract

Accurate intraoperative assessment of glioma infiltration is essential for maximizing tumor resection while preserving functional brain tissue. Fluorescence lifetime imaging (FLIm) offers real-time, label-free biochemical contrast, but its clinical utility is challenged by biological heterogeneity, class imbalance, and variability in histopathological labeling. We present a data-centric AI (DC-AI) framework that integrates confident learning (CL), class refinement, and targeted label evaluation to develop a robust multi-class FLIm classifier for glioblastoma (GBM) resection margins. FLIm data were collected from 192 tissue margins across 31 newly diagnosed IDH-wildtype GBM patients and initially labeled into seven tumor cellularity classes by an expert neuropathologist. CL was applied to quantify FLIm point-level confidence, identify label inconsistencies, and guide iterative class merging into a three-class scheme ("low", "moderate", "high"). The resulting high-fidelity dataset enabled training a model that achieved 96% accuracy in the three-class task. SHAP analysis revealed class-specific FLIm feature importance, highlighting distinct optical signatures across the infiltration spectrum. Targeted FLIm analysis further identified biological (e.g., gray matter composition) and acquisition-related (e.g., blood contamination) contributors to low-confidence predictions. Blinded re-evaluation of margins flagged by CL demonstrated intra-pathologist variability, underscoring the value of selective relabeling rather than exhaustive review. Together, these findings demonstrate that a DC-AI framework can systematically improve data reliability, enhance model robustness, and refine biological interpretation of FLIm signals, supporting the development of clinically actionable optical tools for real-time glioma margin assessment.

Problem

• glioma
• fluorescence lifetime imaging
• surgical guidance
• label inconsistency
• data reliability

Innovation

• data-centric AI
• fluorescence lifetime imaging
• confident learning
• glioma surgical guidance
• label refinement