EvidenceMoE: A Physics-Guided Mixture-of-Experts with Evidential Critics for Advancing Fluorescence Light Detection and Ranging in Scattering Media

2025-05-23

AI Summary

In scattering media, fluorescence LiDAR (FLiDAR) signals suffer from severe coupling between photon time-of-flight (encoding target depth) and intrinsic fluorophore lifetime—hindering simultaneous, accurate estimation of both quantities. To address this, we propose a physics-guided Mixture-of-Experts (MoE) model that uniquely embeds the radiative transfer equation as a structural prior within the MoE architecture. We further introduce an Explainable Dirichlet Critic (EDC), leveraging evidential deep learning to quantify expert output reliability and enable adaptive, uncertainty-aware weighting. The method integrates physics-informed neural networks, differentiable gating, evidential uncertainty modeling, and Monte Carlo simulation–driven training. Evaluated on tissue-level FLiDAR synthetic data, our approach achieves an NRMSE of 0.030 for depth estimation and 0.074 for fluorescence lifetime estimation—substantially outperforming state-of-the-art methods. This work establishes a novel, high-accuracy, and interpretable paradigm for noninvasive depth-resolved detection of cancerous cells.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Fluorescence LiDAR (FLiDAR), a Light Detection and Ranging (LiDAR) technology employed for distance and depth estimation across medical, automotive, and other fields, encounters significant computational challenges in scattering media. The complex nature of the acquired FLiDAR signal, particularly in such environments, makes isolating photon time-of-flight (related to target depth) and intrinsic fluorescence lifetime exceptionally difficult, thus limiting the effectiveness of current analytical and computational methodologies. To overcome this limitation, we present a Physics-Guided Mixture-of-Experts (MoE) framework tailored for specialized modeling of diverse temporal components. In contrast to the conventional MoE approaches our expert models are informed by underlying physics, such as the radiative transport equation governing photon propagation in scattering media. Central to our approach is EvidenceMoE, which integrates Evidence-Based Dirichlet Critics (EDCs). These critic models assess the reliability of each expert's output by providing per-expert quality scores and corrective feedback. A Decider Network then leverages this information to fuse expert predictions into a robust final estimate adaptively. We validate our method using realistically simulated Fluorescence LiDAR (FLiDAR) data for non-invasive cancer cell depth detection generated from photon transport models in tissue. Our framework demonstrates strong performance, achieving a normalized root mean squared error (NRMSE) of 0.030 for depth estimation and 0.074 for fluorescence lifetime.

Problem

• Improving FLiDAR depth and lifetime estimation in scattering media
• Addressing computational challenges in isolating photon time-of-flight
• Enhancing accuracy of fluorescence signal analysis in complex environments

Innovation

• Physics-Guided Mixture-of-Experts for FLiDAR
• Evidence-Based Dirichlet Critics for reliability
• Decider Network adaptively fuses expert predictions