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

A new framework named Time Attenuated Representation Disentanglement (TARDis) has been proposed to address the challenges of tumor segmentation and classification in multi-modal imaging, particularly in cases where complete multi-phase series in Computed Tomography (CT) are unfeasible due to missing modalities. TARDis redefines these missing phases as points on a continuous Time-Attenuation Curve, effectively disentangling static anatomical features from dynamic perfusion data.

A new study introduces multi-frequency Federated Learning (FL) for Human Activity Recognition (HAR) using head-worn sensors like earbuds and smart glasses. This approach addresses privacy concerns associated with centralized data collection by enabling decentralized model training across devices with varying sampling frequencies.

A new framework called SAFLe has been introduced to address the challenges of high communication overhead and performance collapse in Federated Learning (FL). This framework achieves scalable non-linear expressivity while maintaining the single-round benefits of Analytic FL, significantly outperforming previous models like DeepAFL in accuracy across various benchmarks.

A new study proposes an asynchronous design for Federated Learning (FL) that incorporates periodic aggregation to address the straggler issue in wireless networks. This approach emphasizes the importance of scheduling policies that consider channel quality and data representation, aiming to enhance the convergence performance of distributed machine learning models.

The introduction of ContourDiff, a novel framework for unpaired medical image translation, aims to enhance the accuracy of translating images between modalities like Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). This framework utilizes Spatially Coherent Guided Diffusion (SCGD) to maintain anatomical fidelity, which is crucial for clinical applications such as segmentation models.

Recent advancements in Magnetic Resonance Imaging (MRI) reconstruction have been made with the introduction of flow ODEs, which demonstrate that unrolled networks function as discrete implementations of conditional probability flow ODEs. This connection enhances the understanding of how intermediate states evolve during image reconstruction, addressing issues of instability in previous methods.