Learning to simulate realistic human diffuse reflectance spectra.

Significance: Hyperspectral imaging is a noninvasive, cost-effective modality with transformative clinical potential. Its adoption is limited by the lack of accurate and efficient methods that relate spectra to tissue parameters, essential for both AI training and validation of imaging methods, as gold standard Monte Carlo (MC) simulations remain prohibitively computationally expensive. Aim: We aim to develop a scalable and accurate method for generating realistic tissue reflectance spectra in support of AI development and validation in biomedical imaging. Approach: We trained a general-purpose neural surrogate model on Results: The surrogate model achieved accuracy matching MC simulations with 5-10 million photons while delivering inference five orders of magnitude faster. Across 140 million human tissue spectra, it improved spectral recall by 13-48 percentage points over existing surrogate models. Scaling analyses revealed a power law relationship between training dataset size and test error, enabling the prediction of training data requirements for target accuracy. Our porcine study suggests that the synthetic data generated with the surrogate model is suitable for recovering organ-specific Conclusion: Neural surrogate models can achieve MC-level accuracy and