Medical Physics,
AI and Neurotechnology

Reconstructing audio from brain activity remains challenging. Existing brain-to-audio pipelines typically map neural responses to predefined stimulus representations before synthesis. While recent work in the visual domain has explored direct conditioning on brain activity, this approach has not yet been extended to audio diffusion models. We introduce MAAS (Multi-Area Auditory Synthesis), an end-to-end framework that conditions a pretrained audio diffusion transformer on ROI-wise fMRI responses without first supervising a decoder to predict an external stimulus representation. MAAS uses region-specific projections and learned brain tokens to condition Stable Audio through a dedicated cross-attention pathway. On a 7T fMRI dataset, we demonstrate consistent improvements over baselines, including two-stage fMRI-to-latent conditioning, across both acoustic and semantic evaluation metrics. In addition, we introduce a fidelity metric grounded in a computational model of auditory neural processing, which allows us to quantify the contribution of individual auditory cortical regions to reconstructed audio representations.

Prompt-gamma (PG) imaging is a promising approach for in vivo verification in proton therapy, but existing methods are primarily limited to reconstructing the PG emission profile, which provides only indirect information on proton transport. In this work, we introduce Prompt-Gamma Time Imaging (PGTI), an iterative reconstruction method based on the PG Timing (PGT) technique that jointly estimates the PG emission distribution and the proton velocity profile from Time-Of-Flight (TOF) measurements acquired with multiple detector modules. Unlike the PG distribution, the proton velocity is directly related to the stopping power and therefore provides access to both the tissue composition traversed by the beam and a first-order estimation of the delivered dose. The method was validated using experimental data acquired with the eight-module TIARA prototype previously developed by our collaboration. The anthropomorphic RANDO head phantom was irradiated with 100 MeV protons in two anatomical configurations representative of treatment planning and delivery, providing the first demonstration of PGTI under realistic conditions. In this example, the reconstructed material sequence agreed with the reference CT; despite ten bins presenting a misclassified material, the reconstructed proton range only differed from the expected value by approximately 1 mm. These results validate both the proposed PGTI framework and the use of the TIARA detector system in a pseudo-clinical environment, extending PG imaging beyond conventional range verification.

Music is a universal phenomenon that influences human experiences across cultures. We investigate whether music can be decoded from human brain activity measured with fMRI, by modeling mappings between neural data and latent representations of musical stimuli. Our approach integrates functional and anatomical alignment techniques to facilitate cross-subject decoding. Starting from the GTZan fMRI dataset, where five participants listened to 540 musical tracks from 10 genres, we used the CLAP model to extract latent representations of the musical stimuli and developed voxel-wise encoding models to identify brain regions responsive to these stimuli, by applying a threshold to the correlation between predicted and actual brain activity. Our decoding pipeline, primarily retrieval-based, employs a linear map to project back brain activity to the corresponding CLAP features. This enables us to retrieve the musical stimuli most similar to those that originated the fMRI data. Our results demonstrate state-of-the-art identification accuracy, outperforming existing approaches.