Matteo Ferrante

Matteo Ciferri, Tommaso Boccato, Michal Olak et al.

Understanding how speech foundation models relate to human cortical activity is a key challenge for computational neuroscience. Here, we investigate how internal representations from Whisper predict intracranial ECoG responses during naturalistic speech perception. We introduce a time-resolved neural encoder that combines speech embeddings with a recurrent temporal model and soft attention, allowing us to examine layer-wise brain alignment. Intermediate Whisper layers provide the strongest correspondence with neural activity, supporting a hierarchical match between model representations and cortical speech processing. Comparisons with baselines show that high-resolution ECoG responses benefit from temporally structured modelling beyond linear mappings from the same speech representations. In addition, attention maps reveal temporally local alignment between speech embeddings and neural responses, while a phonemic interpretability analysis identifies anatomically coherent phoneme-category organization among encoding-informative electrodes. Together, these results suggest that speech foundation models offer a useful framework for studying time-resolved cortical speech representations.

Matteo Ferrante, Tommaso Boccato, Nicola Toschi

Brain decoding is a field of computational neuroscience that uses measurable brain activity to infer mental states or internal representations of perceptual inputs. Therefore, we propose a novel approach to brain decoding that also relies on semantic and contextual similarity. We employ an fMRI dataset of natural image vision and create a deep learning decoding pipeline inspired by the existence of both bottom-up and top-down processes in human vision. We train a linear brain-to-feature model to map fMRI activity features to visual stimuli features, assuming that the brain projects visual information onto a space that is homeomorphic to the latent space represented by the last convolutional layer of a pretrained convolutional neural network, which typically collects a variety of semantic features that summarize and highlight similarities and differences between concepts. These features are then categorized in the latent space using a nearest-neighbor strategy, and the results are used to condition a generative latent diffusion model to create novel images. From fMRI data only, we produce reconstructions of visual stimuli that match the original content very well on a semantic level, surpassing the state of the art in previous literature. We evaluate our work and obtain good results using a quantitative semantic metric (the Wu-Palmer similarity metric over the WordNet lexicon, which had an average value of 0.57) and perform a human evaluation experiment that resulted in correct evaluation, according to the multiplicity of human criteria in evaluating image similarity, in over 80% of the test set.

Tommaso Boccato, Matteo Ferrante, Andrea Duggento et al.

In this study, we explore the impact of network topology on the approximation capabilities of artificial neural networks (ANNs), with a particular focus on complex topologies. We propose a novel methodology for constructing complex ANNs based on various topologies, including Barabási-Albert, Erdős-Rényi, Watts-Strogatz, and multilayer perceptrons (MLPs). The constructed networks are evaluated on synthetic datasets generated from manifold learning generators, with varying levels of task difficulty and noise, and on real-world datasets from the UCI suite. Our findings reveal that complex topologies lead to superior performance in high-difficulty regimes compared to traditional MLPs. This performance advantage is attributed to the ability of complex networks to exploit the compositionality of the underlying target function. However, this benefit comes at the cost of increased forward-pass computation time and reduced robustness to graph damage. Additionally, we investigate the relationship between various topological attributes and model performance. Our analysis shows that no single attribute can account for the observed performance differences, suggesting that the influence of network topology on approximation capabilities may be more intricate than a simple correlation with individual topological attributes. Our study sheds light on the potential of complex topologies for enhancing the performance of ANNs and provides a foundation for future research exploring the interplay between multiple topological attributes and their impact on model performance.

Matteo Ferrante, Tommaso Boccato, Simeon Spasov et al.

In medicine, curated image datasets often employ discrete labels to describe what is known to be a continuous spectrum of healthy to pathological conditions, such as e.g. the Alzheimer's Disease Continuum or other areas where the image plays a pivotal point in diagnosis. We propose an architecture for image stratification based on a conditional variational autoencoder. Our framework, VAESim, leverages a continuous latent space to represent the continuum of disorders and finds clusters during training, which can then be used for image/patient stratification. The core of the method learns a set of prototypical vectors, each associated with a cluster. First, we perform a soft assignment of each data sample to the clusters. Then, we reconstruct the sample based on a similarity measure between the sample embedding and the prototypical vectors of the clusters. To update the prototypical embeddings, we use an exponential moving average of the most similar representations between actual prototypes and samples in the batch size. We test our approach on the MNIST-handwritten digit dataset and on a medical benchmark dataset called PneumoniaMNIST. We demonstrate that our method outperforms baselines in terms of kNN accuracy measured on a classification task against a standard VAE (up to 15% improvement in performance) in both datasets, and also performs at par with classification models trained in a fully supervised way. We also demonstrate how our model outperforms current, end-to-end models for unsupervised stratification.

Matteo Ferrante, Lisa Rinaldi, Francesca Botta et al.

Lesion segmentation is a crucial step of the radiomic workflow. Manual segmentation requires long execution time and is prone to variability, impairing the realisation of radiomic studies and their robustness. In this study, a deep-learning automatic segmentation method was applied on computed tomography images of non-small-cell lung cancer patients. The use of manual vs automatic segmentation in the performance of survival radiomic models was assessed, as well. METHODS A total of 899 NSCLC patients were included (2 proprietary: A and B, 1 public datasets: C). Automatic segmentation of lung lesions was performed by training a previously developed architecture, the nnU-Net, including 2D, 3D and cascade approaches. The quality of automatic segmentation was evaluated with DICE coefficient, considering manual contours as reference. The impact of automatic segmentation on the performance of a radiomic model for patient survival was explored by extracting radiomic hand-crafted and deep-learning features from manual and automatic contours of dataset A, and feeding different machine learning algorithms to classify survival above/below median. Models' accuracies were assessed and compared. RESULTS The best agreement between automatic and manual contours with DICE=0.78 +(0.12) was achieved by averaging predictions from 2D and 3D models, and applying a post-processing technique to extract the maximum connected component. No statistical differences were observed in the performances of survival models when using manual or automatic contours, hand-crafted, or deep features. The best classifier showed an accuracy between 0.65 and 0.78. CONCLUSION The promising role of nnU-Net for automatic segmentation of lung lesions was confirmed, dramatically reducing the time-consuming physicians' workload without impairing the accuracy of survival predictive models based on radiomics.

Matteo Ferrante, Tommaso Boccato, Simeon Spasov et al.

The lack of large labeled medical imaging datasets, along with significant inter-individual variability compared to clinically established disease classes, poses significant challenges in exploiting medical imaging information in a precision medicine paradigm, where in principle dense patient-specific data can be employed to formulate individual predictions and/or stratify patients into finer-grained groups which may follow more homogeneous trajectories and therefore empower clinical trials. In order to efficiently explore the effective degrees of freedom underlying variability in medical images in an unsupervised manner, in this work we propose an unsupervised autoencoder framework which is augmented with a contrastive loss to encourage high separability in the latent space. The model is validated on (medical) benchmark datasets. As cluster labels are assigned to each example according to cluster assignments, we compare performance with a supervised transfer learning baseline. Our method achieves similar performance to the supervised architecture, indicating that separation in the latent space reproduces expert medical observer-assigned labels. The proposed method could be beneficial for patient stratification, exploring new subdivisions of larger classes or pathological continua or, due to its sampling abilities in a variation setting, data augmentation in medical image processing.

Matteo Ferrante, Tommaso Boccato, Nicola Toschi

The willingness to trust predictions formulated by automatic algorithms is key in a vast number of domains. However, a vast number of deep architectures are only able to formulate predictions without an associated uncertainty. In this paper, we propose a method to convert a standard neural network into a Bayesian neural network and estimate the variability of predictions by sampling different networks similar to the original one at each forward pass. We couple our methods with a tunable rejection-based approach that employs only the fraction of the dataset that the model is able to classify with an uncertainty below a user-set threshold. We test our model in a large cohort of brain images from Alzheimer's Disease patients, where we tackle discrimination of patients from healthy controls based on morphometric images only. We demonstrate how combining the estimated uncertainty with a rejection-based approach increases classification accuracy from 0.86 to 0.95 while retaining 75% of the test set. In addition, the model can select cases to be recommended for manual evaluation based on excessive uncertainty. We believe that being able to estimate the uncertainty of a prediction, along with tools that can modulate the behavior of the network to a degree of confidence that the user is informed about (and comfortable with) can represent a crucial step in the direction of user compliance and easier integration of deep learning tools into everyday tasks currently performed by human operators.

Matteo Ferrante, Tommaso Boccato, Nicola Toschi

Previous brain decoding research primarily involves single-subject studies, reconstructing stimuli via fMRI activity from the same subject. Our study aims to introduce a generalization technique for cross-subject brain decoding, facilitated by exploring data alignment methods. We utilized the NSD dataset, a comprehensive 7T fMRI vision experiment involving multiple subjects exposed to 9841 images, 982 of which were viewed by all. Our approach involved training a decoding model on one subject, aligning others' data to this space, and testing the decoding on the second subject. We compared ridge regression, hyper alignment, and anatomical alignment techniques for fMRI data alignment. We established that cross-subject brain decoding is feasible, even using around 10% of the total data, or 982 common images, with comparable performance to single-subject decoding. Ridge regression was the best method for functional alignment. Through subject alignment, we achieved superior brain decoding and a potential 90% reduction in scan time. This could pave the way for more efficient experiments and further advancements in the field, typically requiring an exorbitant 20-hour scan time per subject.

Matteo Ferrante, Tommaso Boccato, Stefano Bargione et al.

Decoding visual representations from human brain activity has emerged as a thriving research domain, particularly in the context of brain-computer interfaces. Our study presents an innovative method that employs to classify and reconstruct images from the ImageNet dataset using electroencephalography (EEG) data from subjects that had viewed the images themselves (i.e. "brain decoding"). We analyzed EEG recordings from 6 participants, each exposed to 50 images spanning 40 unique semantic categories. These EEG readings were converted into spectrograms, which were then used to train a convolutional neural network (CNN), integrated with a knowledge distillation procedure based on a pre-trained Contrastive Language-Image Pre-Training (CLIP)-based image classification teacher network. This strategy allowed our model to attain a top-5 accuracy of 80%, significantly outperforming a standard CNN and various RNN-based benchmarks. Additionally, we incorporated an image reconstruction mechanism based on pre-trained latent diffusion models, which allowed us to generate an estimate of the images which had elicited EEG activity. Therefore, our architecture not only decodes images from neural activity but also offers a credible image reconstruction from EEG only, paving the way for e.g. swift, individualized feedback experiments. Our research represents a significant step forward in connecting neural signals with visual cognition.

Fabrizio Spera, Tommaso Boccato, Michal Olak et al.

Recent progress in visual brain decoding from fMRI has been enabled by large-scale datasets such as the Natural Scenes Dataset (NSD) and powerful diffusion-based generative models. While current pipelines are primarily optimized for perception, their performance under mental-imagery remains less well understood. In this work, we study how a state-of-the-art (SOTA) perception decoder (DynaDiff) can be adapted to reconstruct imagined content from the Imagery-NSD benchmark. We propose a latent functional alignment approach that maps imagery-evoked activity into the pretrained model's conditioning space, while keeping the remaining components frozen. To mitigate the limited amount of matched imagery-perception supervision, we further introduce a retrieval-based augmentation strategy that selects semantically related NSD perception trials. Across four subjects, latent functional alignment consistently improves high-level semantic reconstruction metrics relative to the frozen pretrained baseline and a voxel-space ridge alignment baseline, and enables above-chance decoding from multiple cortical regions. These results suggest that semantic structure learned from perception can be leveraged to stabilize and improve visual imagery decoding under out-of-distribution conditions.

Matteo Ciferri, Matteo Ferrante, Nicola Toschi

Understanding how neural activity gives rise to perception is a central challenge in neuroscience. We address the problem of decoding visual information from high-density intracortical recordings in primates, using the THINGS Ventral Stream Spiking Dataset. We systematically evaluate the effects of model architecture, training objectives, and data scaling on decoding performance. Results show that decoding accuracy is mainly driven by modeling temporal dynamics in neural signals, rather than architectural complexity. A simple model combining temporal attention with a shallow MLP achieves up to 70% top-1 image retrieval accuracy, outperforming linear baselines as well as recurrent and convolutional approaches. Scaling analyses reveal predictable diminishing returns with increasing input dimensionality and dataset size. Building on these findings, we design a modular generative decoding pipeline that combines low-resolution latent reconstruction with semantically conditioned diffusion, generating plausible images from 200 ms of brain activity. This framework provides principles for brain-computer interfaces and semantic neural decoding.

Michal Olak, Tommaso Boccato, Matteo Ferrante

Speech brain--computer interfaces require decoders that translate intracortical activity into linguistic output while remaining robust to limited data and day-to-day variability. While prior high-performing systems have largely relied on framewise phoneme decoding combined with downstream language models, it remains unclear what contextual sequence-to-sequence decoding contributes to sublexical neural readout, robustness, and interpretability. We evaluated a multitask Transformer-based sequence-to-sequence model for attempted speech decoding from area 6v intracortical recordings. The model jointly predicts phoneme sequences, word sequences, and auxiliary acoustic features. To address day-to-day nonstationarity, we introduced the Neural Hammer Scalpel (NHS) calibration module, which combines global alignment with feature-wise modulation. We further analyzed held-out-day generalization and attention patterns in the encoder and decoders. On the Willett et al. dataset, the proposed model achieved a state-of-the-art phoneme error rate of 14.3%. Word decoding reached 25.6% WER with direct decoding and 19.4% WER with candidate generation and rescoring. NHS substantially improved both phoneme and word decoding relative to linear or no day-specific transform, while held-out-day experiments showed increasing degradation on unseen days with temporal distance. Attention visualizations revealed recurring temporal chunking in encoder representations and distinct use of these segments by phoneme and word decoders. These results indicate that contextual sequence-to-sequence modeling can improve the fidelity of neural-to-phoneme readout from intracortical speech signals and suggest that attention-based analyses can generate useful hypotheses about how neural speech evidence is segmented and accumulated over time.

Tommaso Boccato, Michal Olak, Matteo Ferrante

Decoding continuous speech from intracortical recordings is a central challenge for brain-computer interfaces (BCIs), with transformative potential for individuals with conditions that impair their ability to speak. While recent microelectrode array (MEA) decoders achieve impressive accuracy, their performance is fundamentally limited by the small size of existing datasets, they remain brittle to session-to-session variability, and their ability to generalize across participants remains unexplored. We introduce BrainWhisperer, a neural speech decoder that integrates high-resolution MEA recordings with a large pretrained automatic speech recognition (ASR) model. Building on interpretability findings showing that Whisper's encoder learns phoneme-selective representations with localized attention, we train a customized version of Whisper, modified to process neural features, using a hybrid objective that combines CTC loss on phonemes--predicted from the third encoder layer--and cross-entropy loss on word tokens. We introduce domain-informed modifications including windowed self-attention to capture articulatory continuity, hierarchical month/day-specific low-rank projections to address non-stationarity, and subject-specific embedders enabling cross-subject training. Evaluated on a publicly available MEA dataset (Card et al.), BrainWhisperer matches or outperforms prior state-of-the-art decoders. Critically, cross-dataset training improves performance even on individual datasets without fine-tuning, demonstrating unprecedented generalization. The model supports dual decoding paths: a high-accuracy phoneme-based path with external language model rescoring, and a fast direct text generation path enabling sub-100ms inference with minimal hardware requirements.

Matteo Ferrante, Tommaso Boccato, Grigorii Rashkov et al.

This paper presents a novel approach towards creating a foundational model for aligning neural data and visual stimuli across multimodal representationsof brain activity by leveraging contrastive learning. We used electroencephalography (EEG), magnetoencephalography (MEG), and functional magnetic resonance imaging (fMRI) data. Our framework's capabilities are demonstrated through three key experiments: decoding visual information from neural data, encoding images into neural representations, and converting between neural modalities. The results highlight the model's ability to accurately capture semantic information across different brain imaging techniques, illustrating its potential in decoding, encoding, and modality conversion tasks.

Matteo Ferrante, Alessandra Carosi, Rolando Maria D Angelillo et al.

Radiotherapy is a crucial cancer treatment that demands precise planning to balance tumor eradication and preservation of healthy tissue. Traditional treatment planning (TP) is iterative, time-consuming, and reliant on human expertise, which can potentially introduce variability and inefficiency. We propose a novel framework to transform a large multimodal foundation model (MLM) into an action model for TP using a few-shot reinforcement learning (RL) approach. Our method leverages the MLM's extensive pre-existing knowledge of physics, radiation, and anatomy, enhancing it through a few-shot learning process. This allows the model to iteratively improve treatment plans using a Monte Carlo simulator. Our results demonstrate that this method outperforms conventional RL-based approaches in both quality and efficiency, achieving higher reward scores and more optimal dose distributions in simulations on prostate cancer data. This proof-of-concept suggests a promising direction for integrating advanced AI models into clinical workflows, potentially enhancing the speed, quality, and standardization of radiotherapy treatment planning.

Matteo Ciferri, Matteo Ferrante, Nicola Toschi

Understanding the neural mechanisms behind auditory and linguistic processing is key to advancing cognitive neuroscience. In this study, we use Magnetoencephalography (MEG) data to analyze brain responses to spoken language stimuli. We develop two distinct encoding models: an audio-to-MEG encoder, which uses time-frequency decompositions (TFD) and wav2vec2 latent space representations, and a text-to-MEG encoder, which leverages CLIP and GPT-2 embeddings. Both models successfully predict neural activity, demonstrating significant correlations between estimated and observed MEG signals. However, the text-to-MEG model outperforms the audio-based model, achieving higher Pearson Correlation (PC) score. Spatially, we identify that auditory-based embeddings (TFD and wav2vec2) predominantly activate lateral temporal regions, which are responsible for primary auditory processing and the integration of auditory signals. In contrast, textual embeddings (CLIP and GPT-2) primarily engage the frontal cortex, particularly Broca's area, which is associated with higher-order language processing, including semantic integration and language production, especially in the 8-30 Hz frequency range. The strong involvement of these regions suggests that auditory stimuli are processed through more direct sensory pathways, while linguistic information is encoded via networks that integrate meaning and cognitive control. Our results reveal distinct neural pathways for auditory and linguistic information processing, with higher encoding accuracy for text representations in the frontal regions. These insights refine our understanding of the brain's functional architecture in processing auditory and textual information, offering quantitative advancements in the modelling of neural responses to complex language stimuli.

Matteo Ferrante, Matteo Ciferri, Nicola Toschi

Music is a universal phenomenon that profoundly influences human experiences across cultures. This study investigates whether music can be decoded from human brain activity measured with functional MRI (fMRI) during its perception. Leveraging recent advancements in extensive datasets and pre-trained computational models, we construct mappings between neural data and latent representations of musical stimuli. Our approach integrates functional and anatomical alignment techniques to facilitate cross-subject decoding, addressing the challenges posed by the low temporal resolution and signal-to-noise ratio (SNR) in fMRI data. Starting from the GTZan fMRI dataset, where five participants listened to 540 musical stimuli from 10 different genres while their brain activity was recorded, we used the CLAP (Contrastive Language-Audio Pretraining) 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 association between predicted and actual brain activity, we identified specific regions of interest (ROIs) which can be interpreted as key players in music processing. Our decoding pipeline, primarily retrieval-based, employs a linear map to project brain activity to the corresponding CLAP features. This enables us to predict and retrieve the musical stimuli most similar to those that originated the fMRI data. Our results demonstrate state-of-the-art identification accuracy, with our methods significantly outperforming existing approaches. Our findings suggest that neural-based music retrieval systems could enable personalized recommendations and therapeutic applications. Future work could use higher temporal resolution neuroimaging and generative models to improve decoding accuracy and explore the neural underpinnings of music perception and emotion.

Matteo Ferrante, Furkan Ozcelik, Tommaso Boccato et al.

Every day, the human brain processes an immense volume of visual information, relying on intricate neural mechanisms to perceive and interpret these stimuli. Recent breakthroughs in functional magnetic resonance imaging (fMRI) have enabled scientists to extract visual information from human brain activity patterns. In this study, we present an innovative method for decoding brain activity into meaningful images and captions, with a specific focus on brain captioning due to its enhanced flexibility as compared to brain decoding into images. Our approach takes advantage of cutting-edge image captioning models and incorporates a unique image reconstruction pipeline that utilizes latent diffusion models and depth estimation. We utilized the Natural Scenes Dataset, a comprehensive fMRI dataset from eight subjects who viewed images from the COCO dataset. We employed the Generative Image-to-text Transformer (GIT) as our backbone for captioning and propose a new image reconstruction pipeline based on latent diffusion models. The method involves training regularized linear regression models between brain activity and extracted features. Additionally, we incorporated depth maps from the ControlNet model to further guide the reconstruction process. We evaluate our methods using quantitative metrics for both generated captions and images. Our brain captioning approach outperforms existing methods, while our image reconstruction pipeline generates plausible images with improved spatial relationships. In conclusion, we demonstrate significant progress in brain decoding, showcasing the enormous potential of integrating vision and language to better understand human cognition. Our approach provides a flexible platform for future research, with potential applications in various fields, including neural art, style transfer, and portable devices.