Medical Physics,
AI and Neurotechnology

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.

RATIONALE AND OBJECTIVES: Automated semantic classification of radiology reports can enhance clinical workflows and research, but often relies on language- and task-specific models, limiting scalability. This study aims to evaluate and improve the 0-shot baseline performance of open-weight large language models (LLMs) in the semantic classification of free-text magnetic resonance imaging (MRI) reports.

MATERIALS AND METHODS: A corpus of 1385 reports from a single neuroradiology center was used to assess four LLMs (GPT-OSS-20B, Magistral-Small-2509, Gemma-4-31B, Qwen3.5-35B-A3B) of comparable scale (∼20-35B parameters). The brain MRI reports were labeled as Pathological or Non-Pathological, with the Pathological ones further classified into five diagnostic categories (Neoformation, Vascular, Inflammation/Infection, Neurodegenerative, Other). The LLMs were evaluated using zero- and few-shot prompting with majority-vote aggregation. Quantized Low-Rank Adaptation (QLoRA) fine-tuning was then applied to the best-performing model across multiple configurations. Performance was assessed using Macro F1, Micro F1, Precision, Recall, and Exact Match Accuracy.

RESULTS: The binary classification task achieved a Macro F1 score of 0.84 on the best-performing Qwen3.5-35B-A3B model, while multilabel classification reached 0.81. Majority voting (MV) outperformed individual-set predictions. QLoRA fine-tuning yielded a Macro F1 score of 0.83 on the multilabel task; the improvement over the 0-shot baseline was statistically supported for Macro F1, Micro F1, Macro Precision, and Exact Match, whose bootstrap 95% confidence intervals excluded zero, but not for Macro Recall. Fine-tuning and few-shot prompting strategies are complementary, with neither consistently outperforming the other. Error analysis showed that the models struggled with borderline annotation cases and often missed secondary labels.

CONCLUSION: Open-weight LLMs demonstrate strong capability for neuroradiology report classification without extensive task-specific training. Fine-tuning further improves performance, supporting integration into scalable semantic radiology data pipelines. However, the present evidence comes from a single Italian center without external validation, and the fine-tuning gain was estimated on a small held-out test set, for which the Macro F1 improvement, though statistically significant, has a confidence interval with a lower bound close to zero. In this light, the approach is best positioned as an internal indexing and semantic-retrieval tool, supporting faster report retrieval, structured cohort identification, internal audit, and scalable phenotyping for neuroradiology research and data warehousing, as well as efficient active-learning strategies, with broader generalizability requiring additional external multicentre validation before clinical deployment.