Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Projection Guided Personalized Federated Learning for Low Dose CT Denoising

Anas Zafar, Muhammad Waqas, Amgad Muneer, Rukhmini Bandyopadhyay, Jia Wu

Abstract

Low-dose CT (LDCT) reduces radiation exposure but introduces protocol-dependent noise and artifacts that vary across institutions. While federated learning enables collaborative training without centralizing patient data, existing methods personalize in image space, making it difficult to separate scanner noise from patient anatomy. We propose ProFed (Projection Guided Personalized Federated Learning), a framework that complements the image space approach by performing dual-level personalization in the projection space, where noise originates during CT measurements before reconstruction combines protocol and anatomy effects. ProFed introduces: (i) anatomy-aware and protocol-aware networks that personalize CT reconstruction to patient and scanner-specific features, (ii) multi-constraint projection losses that enforce consistency with CT measurements, and (iii) uncertainty-guided selective aggregation that weights clients by prediction confidence. Extensive experiments on the Mayo Clinic 2016 dataset demonstrate that ProFed achieves 42.56 dB PSNR with CNN backbones and 44.83 dB with Transformers, outperforming 11 federated learning baselines, including the physics-informed SCAN-PhysFed by +1.42 dB.

Projection Guided Personalized Federated Learning for Low Dose CT Denoising

Abstract

Low-dose CT (LDCT) reduces radiation exposure but introduces protocol-dependent noise and artifacts that vary across institutions. While federated learning enables collaborative training without centralizing patient data, existing methods personalize in image space, making it difficult to separate scanner noise from patient anatomy. We propose ProFed (Projection Guided Personalized Federated Learning), a framework that complements the image space approach by performing dual-level personalization in the projection space, where noise originates during CT measurements before reconstruction combines protocol and anatomy effects. ProFed introduces: (i) anatomy-aware and protocol-aware networks that personalize CT reconstruction to patient and scanner-specific features, (ii) multi-constraint projection losses that enforce consistency with CT measurements, and (iii) uncertainty-guided selective aggregation that weights clients by prediction confidence. Extensive experiments on the Mayo Clinic 2016 dataset demonstrate that ProFed achieves 42.56 dB PSNR with CNN backbones and 44.83 dB with Transformers, outperforming 11 federated learning baselines, including the physics-informed SCAN-PhysFed by +1.42 dB.
Paper Structure (21 sections, 24 equations, 3 figures, 6 tables, 1 algorithm)

This paper contains 21 sections, 24 equations, 3 figures, 6 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. Problem Formulation
  5. Dual Adaptation with Projection Consistency
  6. Architecture Overview
  7. Anatomy Aware Adaptation
  8. Protocol-Aware Adaptation with LoRA
  9. Gated Feature Modulation
  10. Differentiable Projection Operators
  11. Multi-Constraint Projection Consistency
  12. Uncertainty Guided Federated Aggregation
  13. Training Objectives
  14. Experimentation and Results
  15. Datasets
  16. ...and 6 more sections

Figures (3)

  • Figure 1: ProFed framework: Architectural overview for projection-guided personalized federated learning.
  • Figure 2: Qualitative results of six selected comparison methods and our method across different clients using the classical convolutional-based LDCT imaging network. Rows one to five represent Clients #2, #3, #5, #6, and #7, respectively
  • Figure 3: Qualitative comparison of methods across different clients using the Transformer-based reconstruction network. Rows 1-5 show results for Clients #2, #3, #5, #6, and #7, respectively.