A cone-beam photon-counting CT dataset for spectral image reconstruction and deep learning

Photon-counting CT has gained significant attention in recent years; however, publicly available datasets for spectral reconstruction and deep learning training remain limited. Consequently, many image process algorithms and deep learning models are developed and validated using simulated rather than real spectral CT data. To address this gap, we present a cone-beam photon-counting CT (PCCT) dataset acquired using a custom-built micro-PCCT system and 15 walnut samples. Each walnut was scanned from four bed positions under dual energy thresholds (15 keV and 30 keV), resulting in a total of 172,800 raw projection images with a resolution of 2063 × 505 pixels. The dataset provides full access to raw multi-energy projections, system parameters, calibration tables, calibration phantom raw projection data and reconstruction code, enabling comprehensive spectral CT studies including spectral CT reconstruction, material decomposition, artifact correction, and deep learning-based methods. It addresses the scarcity of real PCCT datasets for developing and validating data-driven approaches and aims to foster fair and reproducible comparisons across spectral CT image process algorithms.