Federated learning-based virtual dual-energy CT generation from single-energy CT for gout detection

Yufang Dong, Min Liu, Jiajun Feng, Yuezhe Yang, Yong Dai, Zhe Jin

Abstract:

**Objective**: This study aims to develop and validate OneGout, a federated learning (FL)-based framework for early and
accurate gout diagnosis to address the limitations of current diagnostic methods, speci cally the invasiveness of joint
aspiration and the accessibility, cost, and radiation exposure associated with advanced imaging techniques like dual-energy
computed tomography (DECT).

**Methods**: We introduce OneGout, which pioneers a deep learning-based method for generating virtual DECT images.
This approach offers a low-cost and low-radiation alternative for gout diagnosis. Furthermore, OneGout integrates fed-
erated learning (OneGout-FL) to enable collaborative model training across multiple medical institutions while ensuring
patient data privacy is preserved.

**Results**: Experiments demonstrate that our method successfully generates high-quality virtual DECT images. The frame-
work based on U-Net achieves a PSNR of 22.44 dB and an SSIM of 0.92 for the generation of 140 kV from 80 kV images. It
also shows strong diagnostic performance, with an IoU of 46.66 and a Dice score of 63.20, indicating promising accuracy
comparable to diagnoses made with real DECT scans.

**Conclusion**: OneGout presents an ef cient, scalable, and privacy-preserving diagnostic solution for gout, particularly
bene cial for resource-limited medical institutions. This framework has the potential to signi cantly enhance global
gout management by providing a more accessible and safer diagnostic alternative.