$μ$NeuFMT: Optical-Property-Adaptive Fluorescence Molecular Tomography via Implicit Neural Representation
This work addresses the problem of unreliable FMT reconstruction for medical imaging applications, such as fluorescence-guided surgery, by introducing a new paradigm that is robust to inaccurate optical properties, though it is incremental in combining implicit neural representation with physical modeling.
The paper tackles the challenge of reconstructing accurate 3D fluorescence distributions in Fluorescence Molecular Tomography (FMT) by proposing $μ$NeuFMT, a self-supervised framework that jointly optimizes fluorescence and optical properties, eliminating the need for precise prior knowledge. It demonstrates robust recovery with initial errors ranging from 0.5× to 2× of ground truth and outperforms conventional and supervised deep learning methods in diverse scenarios.
Fluorescence Molecular Tomography (FMT) is a promising technique for non-invasive 3D visualization of fluorescent probes, but its reconstruction remains challenging due to the inherent ill-posedness and reliance on inaccurate or often-unknown tissue optical properties. While deep learning methods have shown promise, their supervised nature limits generalization beyond training data. To address these problems, we propose $μ$NeuFMT, a self-supervised FMT reconstruction framework that integrates implicit neural-based scene representation with explicit physical modeling of photon propagation. Its key innovation lies in jointly optimize both the fluorescence distribution and the optical properties ($μ$) during reconstruction, eliminating the need for precise prior knowledge of tissue optics or pre-conditioned training data. We demonstrate that $μ$NeuFMT robustly recovers accurate fluorophore distributions and optical coefficients even with severely erroneous initial values (0.5$\times$ to 2$\times$ of ground truth). Extensive numerical, phantom, and in vivo validations show that $μ$NeuFMT outperforms conventional and supervised deep learning approaches across diverse heterogeneous scenarios. Our work establishes a new paradigm for robust and accurate FMT reconstruction, paving the way for more reliable molecular imaging in complex clinically related scenarios, such as fluorescence guided surgery.