# Energy-Efficient Federated Learning via Adaptive Encoder Freezing for MRI-to-CT Conversion: A Green AI-Guided Research

arXiv: https://arxiv.org/abs/2512.03054 · HTML: https://mlsanity.com/paper/2512.03054/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 52 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [Artificial Intelligence: the global landscape of ethics guidelines](https://mlsanity.com/paper/1906.11668/) (2019)
- [Layer-wised Model Aggregation for Personalized Federated Learning](https://mlsanity.com/paper/2205.03993/) (2022)
- [Trustworthy AI: A Computational Perspective](https://mlsanity.com/paper/2107.06641/) (2021)
- [SynthRAD2023 Grand Challenge dataset: generating synthetic CT for radiotherapy](https://mlsanity.com/paper/2303.16320/) (2023)
- [Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directions](https://mlsanity.com/paper/2208.03392/) (2022)
- [Hype, Sustainability, and the Price of the Bigger-is-Better Paradigm in AI](https://mlsanity.com/paper/2409.14160/) (2024)
- [How to estimate carbon footprint when training deep learning models? A guide and review](https://mlsanity.com/paper/2306.08323/) (2023)
- [Deep learning-based synthetic-CT generation in radiotherapy and PET: a review](https://mlsanity.com/paper/2102.02734/) (2021)
- [FedMed-GAN: Federated Domain Translation on Unsupervised Cross-Modality Brain Image Synthesis](https://mlsanity.com/paper/2201.08953/) (2022)
- [Efficient and Private Federated Learning with Partially Trainable Networks](https://mlsanity.com/paper/2110.03450/) (2021)
- [HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networks](https://mlsanity.com/paper/2204.06760/) (2022)
- [Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations](https://mlsanity.com/paper/2405.09839/) (2024)
- [Green Federated Learning: A new era of Green Aware AI](https://mlsanity.com/paper/2409.12626/) (2024)
- [Heterogeneity-Aware Memory Efficient Federated Learning via Progressive Layer Freezing](https://mlsanity.com/paper/2408.09101/) (2024)
- [FedSynthCT-Brain: A Federated Learning Framework for Multi-Institutional Brain MRI-to-CT Synthesis](https://mlsanity.com/paper/2412.06690/) (2024)
- [A Privacy-Preserving Federated Learning Framework for Generalizable CBCT to Synthetic CT Translation in Head and Neck](https://mlsanity.com/paper/2506.08654/) (2025)

## Abstract (arXiv)

Federated Learning (FL) holds the potential to advance equality in health by enabling diverse institutions to collaboratively train deep learning (DL) models, even with limited data. However, the significant resource requirements of FL often exclude centres with limited computational infrastructure, further widening existing healthcare disparities. To address this issue, we propose a Green AI-oriented adaptive layer-freezing strategy designed to reduce energy consumption and computational load while maintaining model performance. We tested our approach using different federated architectures for Magnetic Resonance Imaging (MRI)-to-Computed Tomography (CT) conversion. The proposed adaptive strategy optimises the federated training by selectively freezing the encoder weights based on the monitored relative difference of the encoder weights from round to round. A patience-based mechanism ensures that freezing only occurs when updates remain consistently minimal. The energy consumption and CO2eq emissions of the federation were tracked using the CodeCarbon library. Compared to equivalent non-frozen counterparts, our approach reduced training time, total energy consumption and CO2eq emissions by up to 23%. At the same time, the MRI-to-CT conversion performance was maintained, with only small variations in the Mean Absolute Error (MAE). Notably, for three out of the five evaluated architectures, no statistically significant differences were observed, while two architectures exhibited statistically significant improvements. Our work aligns with a research paradigm that promotes DL-based frameworks meeting clinical requirements while ensuring climatic, social, and economic sustainability. It lays the groundwork for novel FL evaluation frameworks, advancing privacy, equity and, more broadly, justice in AI-driven healthcare.