arXiv subjects

Marco Lorenzi

Publications and source records attributed to Marco Lorenzi.

At least 19 recordsLinked to original sources

arXiv2026

Discovering Subtypes of Neurodegenerative Progression with a Scalable Connectome-Constrained Dynamic Model

Parkinson's disease is clinically and biologically heterogeneous, yet its spatiotemporal progression remains poorly characterized. We present a connectome-constrained disease progression model that jointly estimates subject-specific disease time and data-driven subtypes from longitudinal morphometry. Applied to 85 imaging and clinical biomarkers from the Parkinson's Progressive Markers Initiative (PPMI) cohort, the model recovers four morphologically distinct progression subtypes. We validate the model on a hold-out cross-sectional dataset and benchmark it against SuStaIn under a matched training and validation protocol. Only our method recovers subtypes that correspond significantly to clinical motor subtypes and genetic variants of Parkinson's Disease.

q-bio.QM↗

arXiv2026

SMART: A Flexible, Interpretable, and Scalable Spatio-temporal Brain Atlas from High-Resolution Imaging Data

We introduce SMART, a framework for learning a flexible, interpretable, and scalable spatio-temporal brain atlas from longitudinal high-resolution 3D medical images. Existing approaches to spatio-temporal atlas construction rely on black-box generative models that lack flexibility, limit interpretability, and struggle to scale to high-dimensional data. SMART addresses these challenges by learning a continuous disease-time atlas that decouples global group-wise disease dynamics from their patient-specific anatomical manifestation. Guided by anatomically inspired priors, SMART models interpretable global trajectories of regional progression along a shared disease timeline through region-specific differential equations. Global trajectories are further personalized to individual anatomies via dense diffeomorphic displacements parameterized by a flexible and scalable multi-scale Neural Cellular Automata. Evaluated on five longitudinal MRI datasets in Alzheimer's disease (ADNI-1/GO/2, OASIS-3, AIBL; > 1,300 subjects), SMART produces anatomically meaningful predictions of disease progression and achieves state-of-the-art forecasting accuracy and improved temporal consistency over adversarial and diffusion baselines. Our approach establishes a new paradigm for flexible, interpretable, and scalable modeling of spatio-temporal change in high-dimensional medical image time-series.

cs.CV↗

arXiv2026

MedScribe: Clinically Grounded CT Reporting through Agentic Workflows

Vision-language models (VLMs) have shown potential for automated radiology report generation, yet existing approaches rely on global embedding compression of volumetric data, often leading to hallucinated findings and limited anatomical grounding in 3D CT imaging. We introduce MedScribe, a hypothesis-driven framework that reformulates report generation as an iterative evidence acquisition process rather than a single-pass encoding task. MedScribe models reporting as a sequential decision process in which a large language model dynamically invokes pathology-specific diagnostic tools to extract localized volumetric features. These structured features are used to query a multidimensional retrieval space aligned with pathology-specific textual evidence. By explicitly accumulating quantitative evidence prior to synthesis, the framework enforces fine-grained grounding and reduces unsupported claims. Without task-specific fine-tuning, MedScribe improves clinical accuracy, factual consistency, and interpretability on CT-RATE and RadChestCT compared to state-of-the-art 2D and 3D VLMs, demonstrating the value of hypothesis-driven reasoning for reliable medical image reporting.

cs.CV↗

arXiv2026

Variance-Reduced $(\varepsilon,δ)-$Unlearning using Forget Set Gradients

In machine unlearning, $(\varepsilon,δ)-$unlearning is a popular framework that provides formal guarantees on the effectiveness of the removal of a subset of training data, the forget set, from a trained model. For strongly convex objectives, existing first-order methods achieve $(\varepsilon,δ)-$unlearning, but they only use the forget set to calibrate injected noise, never as a direct optimization signal. In contrast, efficient empirical heuristics often exploit the forget samples (e.g., via gradient ascent) but come with no formal unlearning guarantees. We bridge this gap by presenting the Variance-Reduced Unlearning (VRU) algorithm. To the best of our knowledge, VRU is the first first-order algorithm that directly includes forget set gradients in its update rule, while provably satisfying ($(\varepsilon,δ)-$unlearning. We establish the convergence of VRU and show that incorporating the forget set yields strictly improved rates, i.e. a better dependence on the achieved error compared to existing first-order $(\varepsilon,δ)-$unlearning methods. Moreover, we prove that, in a low-error regime, VRU asymptotically outperforms any first-order method that ignores the forget set.Experiments corroborate our theory, showing consistent gains over both state-of-the-art certified unlearning methods and over empirical baselines that explicitly leverage the forget set.

cs.LG↗

arXiv2026

Fed-ComBat: A Generalized Federated Framework for Batch Effect Harmonization in Collaborative Studies

The use of multi-centric analyses is crucial for obtaining sufficient sample sizes and representative clinical populations in experimental studies. In this setting, data harmonization techniques are typically employed to address systematic biases and ensure the interoperability of the data. State-of-the-art harmonisation approaches are based on the statistical theory of random effect modeling, allowing to account for either linear of non-linear biases and batch effects. However, optimizing these statistical methods generally requires data centralization at some point during the analysis pipeline, therefore introducing the risk of exposing individual patient information while posing significant data governance issues. To overcome this challenge, in this paper we present Fed-ComBat, a federated framework for batch effect harmonization on decentralized data. Fed-ComBat enables the preservation of nonlinear covariate effects without requiring centralization of data and without prior parametric hypothesis on the variables to account for. We demonstrate the effectiveness of Fed-ComBat against a comprehensive panel of existing approaches based on the state-of-the-art ComBat, along with distributed and nonlinear variants. Our experiments are based on extensive simulated data, and on the analysis of multiple cohorts based on 7 neuroimaging studies comprising healthy controls (CI) and subjects with various disorders such as Parkinson's disease (PD), Alzheimer's disease (AD), and autism spectrum disorder (ASD). Our results show that in a federated settings, Fed-ComBat harmonization exhibits comparable results to centralized methods for both linear and nonlinear cases. On real data, harmonized trajectories of the thickness ofthe right hippocampus across lifespan measured on a set of 7 public studies show comparable results between centralized and federated models and are consistent with the literature when using a nonlinear model. The code is publicly available at: https://gitlab.inria.fr/greguig/fedcombat

q-bio.QM↗

arXiv2025

A Technical Policy Blueprint for Trustworthy Decentralized AI

Decentralized AI systems, such as federated learning, can play a critical role in further unlocking AI asset marketplaces (e.g., healthcare data marketplaces) thanks to increased asset privacy protection. Unlocking this big potential necessitates governance mechanisms that are transparent, scalable, and verifiable. However current governance approaches rely on bespoke, infrastructure-specific policies that hinder asset interoperability and trust among systems. We are proposing a Technical Policy Blueprint that encodes governance requirements as policy-as-code objects and separates asset policy verification from asset policy enforcement. In this architecture the Policy Engine verifies evidence (e.g., identities, signatures, payments, trusted-hardware attestations) and issues capability packages. Asset Guardians (e.g. data guardians, model guardians, computation guardians, etc.) enforce access or execution solely based on these capability packages. This core concept of decoupling policy processing from capabilities enables governance to evolve without reconfiguring AI infrastructure, thus creating an approach that is transparent, auditable, and resilient to change.

cs.CY↗

arXiv2025

Scalable Modeling of Nonlinear Network Dynamics in Neurodegenerative Disease

Mechanistic models of progressive neurodegeneration offer great potential utility for clinical use and novel treatment development. Toward this end, several connectome-informed models of neuroimaging biomarkers have been proposed. However, these models typically do not scale well beyond a small number of biomarkers due to heterogeneity in individual disease trajectories and a large number of parameters. To address this, we introduce the Connectome-based Monotonic Inference of Neurodegenerative Dynamics (COMIND). The model combines concepts from diffusion and logistic models with structural brain connectivity. This guarantees monotonic disease trajectories while maintaining a limited number of parameters to improve scalability. We evaluate our model on simulated data as well as on the Parkinson's Progressive Markers Initiative (PPMI) data. Our model generalizes to anatomical imaging representations from a standard brain atlas without the need to reduce biomarker number.

q-bio.QM↗

arXiv2025

When to Forget? Complexity Trade-offs in Machine Unlearning

Machine Unlearning (MU) aims at removing the influence of specific data points from a trained model, striving to achieve this at a fraction of the cost of full model retraining. In this paper, we analyze the efficiency of unlearning methods and establish the first upper and lower bounds on minimax computation times for this problem, characterizing the performance of the most efficient algorithm against the most difficult objective function. Specifically, for strongly convex objective functions and under the assumption that the forget data is inaccessible to the unlearning method, we provide a phase diagram for the unlearning complexity ratio -- a novel metric that compares the computational cost of the best unlearning method to full model retraining. The phase diagram reveals three distinct regimes: one where unlearning at a reduced cost is infeasible, another where unlearning is trivial because adding noise suffices, and a third where unlearning achieves significant computational advantages over retraining. These findings highlight the critical role of factors such as data dimensionality, the number of samples to forget, and privacy constraints in determining the practical feasibility of unlearning.

stat.ML↗

arXiv2025

Federated Learning in Distributed Medical Databases: Meta-Analysis of Large-Scale Subcortical Brain Data

At this moment, databanks worldwide contain brain images of previously unimaginable numbers. Combined with developments in data science, these massive data provide the potential to better understand the genetic underpinnings of brain diseases. However, different datasets, which are stored at different institutions, cannot always be shared directly due to privacy and legal concerns, thus limiting the full exploitation of big data in the study of brain disorders. Here we propose a federated learning framework for securely accessing and meta-analyzing any biomedical data without sharing individual information. We illustrate our framework by investigating brain structural relationships across diseases and clinical cohorts. The framework is first tested on synthetic data and then applied to multi-centric, multi-database studies including ADNI, PPMI, MIRIAD and UK Biobank, showing the potential of the approach for further applications in distributed analysis of multi-centric cohorts

stat.ML↗

arXiv2024

Disease Progression Modelling and Stratification for detecting sub-trajectories in the natural history of pathologies: application to Parkinson's Disease trajectory modelling

Modelling the progression of Degenerative Diseases (DD) is essential for detection, prevention, and treatment, yet it remains challenging due to the heterogeneity in disease trajectories among individuals. Factors such as demographics, genetic conditions, and lifestyle contribute to diverse phenotypical manifestations, necessitating patient stratification based on these variations. Recent methods like Subtype and Stage Inference (SuStaIn) have advanced unsupervised stratification of disease trajectories, but they face potential limitations in robustness, interpretability, and temporal granularity. To address these challenges, we introduce Disease Progression Modelling and Stratification (DP-MoSt), a novel probabilistic method that optimises clusters of continuous trajectories over a long-term disease time-axis while estimating the confidence of trajectory sub-types for each biomarker. We validate DP-MoSt using both synthetic and real-world data from the Parkinson's Progression Markers Initiative (PPMI). Our results demonstrate that DP-MoSt effectively identifies both sub-trajectories and subpopulations, and is a promising alternative to current state-of-the-art models.

math.OC↗

arXiv2024

A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications

Federated learning (FL) has gained wide popularity as a collaborative learning paradigm allowing collaborative Artificial Intelligence (AI) in sensitive healthcare applications. Nevertheless, the practical implementation of FL presents technical and organizational challenges, as it generally requires complex communication infrastructures. In this context, consensus-based learning (CBL) may represent a promising alternative for collaborative learning, allowing the combination of local knowledge into a federated decision system, while potentially reducing deployment overhead. Nevertheless, a comprehensive assessment of the viability of consensus-based learning as a cost-effective and sustainable alternative to federated learning has not yet been conducted. In this work we propose an extensive benchmark of the accuracy, cost-effectiveness, and sustainability of a panel of FL and CBL methods in a wide range of collaborative medical data analysis scenarios. The benchmark includes 7 different medical datasets, encompassing 3 machine learning tasks, 8 different data modalities, and multi-centric settings involving 3 to 23 clients. Our results reveal that CBL is a cost-effective and more sustainable alternative to FL. When compared across the panel of medical datasets in the considered benchmark, CBL methods provide equivalent accuracy to the one achieved by FL. Nonetheless, CBL significantly reduces training time and communication cost (resp. 15 fold and 131 fold decrease) (p-value < 0.05). This study opens a novel perspective on the deployment of collaborative AI in real-world applications, whereas the adoption of cost-effective methods is instrumental to achieve sustainability and democratization of AI by alleviating the need for extensive computational resources.

cs.LG↗

arXiv2024

Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications

Deploying federated learning (FL) in real-world scenarios, particularly in healthcare, poses challenges in communication and security. In particular, with respect to the federated aggregation procedure, researchers have been focusing on the study of secure aggregation (SA) schemes to provide privacy guarantees over the model's parameters transmitted by the clients. Nevertheless, the practical availability of SA in currently available FL frameworks is currently limited, due to computational and communication bottlenecks. To fill this gap, this study explores the implementation of SA within the open-source Fed-BioMed framework. We implement and compare two SA protocols, Joye-Libert (JL) and Low Overhead Masking (LOM), by providing extensive benchmarks in a panel of healthcare data analysis problems. Our theoretical and experimental evaluations on four datasets demonstrate that SA protocols effectively protect privacy while maintaining task accuracy. Computational overhead during training is less than 1% on a CPU and less than 50% on a GPU for large models, with protection phases taking less than 10 seconds. Incorporating SA into Fed-BioMed impacts task accuracy by no more than 2% compared to non-SA scenarios. Overall this study demonstrates the feasibility of SA in real-world healthcare applications and contributes in reducing the gap towards the adoption of privacy-preserving technologies in sensitive applications.

cs.CR↗

arXiv2024

Privacy Preserving Image Registration

Image registration is a key task in medical imaging applications, allowing to represent medical images in a common spatial reference frame. Current approaches to image registration are generally based on the assumption that the content of the images is usually accessible in clear form, from which the spatial transformation is subsequently estimated. This common assumption may not be met in practical applications, since the sensitive nature of medical images may ultimately require their analysis under privacy constraints, preventing to openly share the image content.In this work, we formulate the problem of image registration under a privacy preserving regime, where images are assumed to be confidential and cannot be disclosed in clear. We derive our privacy preserving image registration framework by extending classical registration paradigms to account for advanced cryptographic tools, such as secure multi-party computation and homomorphic encryption, that enable the execution of operations without leaking the underlying data. To overcome the problem of performance and scalability of cryptographic tools in high dimensions, we propose several techniques to optimize the image registration operations by using gradient approximations, and by revisiting the use of homomorphic encryption trough packing, to allow the efficient encryption and multiplication of large matrices. We demonstrate our privacy preserving framework in linear and non-linear registration problems, evaluating its accuracy and scalability with respect to standard, non-private counterparts. Our results show that privacy preserving image registration is feasible and can be adopted in sensitive medical imaging applications.

cs.CV↗

arXiv2024

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization

Machine Unlearning (MU) is an increasingly important topic in machine learning safety, aiming at removing the contribution of a given data point from a training procedure. Federated Unlearning (FU) consists in extending MU to unlearn a given client's contribution from a federated training routine. While several FU methods have been proposed, we currently lack a general approach providing formal unlearning guarantees to the FedAvg routine, while ensuring scalability and generalization beyond the convex assumption on the clients' loss functions. We aim at filling this gap by proposing SIFU (Sequential Informed Federated Unlearning), a new FU method applying to both convex and non-convex optimization regimes. SIFU naturally applies to FedAvg without additional computational cost for the clients and provides formal guarantees on the quality of the unlearning task. We provide a theoretical analysis of the unlearning properties of SIFU, and practically demonstrate its effectiveness as compared to a panel of unlearning methods from the state-of-the-art.

cs.LG↗

arXiv2023

Benchmarking Collaborative Learning Methods Cost-Effectiveness for Prostate Segmentation

Healthcare data is often split into medium/small-sized collections across multiple hospitals and access to it is encumbered by privacy regulations. This brings difficulties to use them for the development of machine learning and deep learning models, which are known to be data-hungry. One way to overcome this limitation is to use collaborative learning (CL) methods, which allow hospitals to work collaboratively to solve a task, without the need to explicitly share local data. In this paper, we address a prostate segmentation problem from MRI in a collaborative scenario by comparing two different approaches: federated learning (FL) and consensus-based methods (CBM). To the best of our knowledge, this is the first work in which CBM, such as label fusion techniques, are used to solve a problem of collaborative learning. In this setting, CBM combine predictions from locally trained models to obtain a federated strong learner with ideally improved robustness and predictive variance properties. Our experiments show that, in the considered practical scenario, CBMs provide equal or better results than FL, while being highly cost-effective. Our results demonstrate that the consensus paradigm may represent a valid alternative to FL for typical training tasks in medical imaging.

cs.LG↗

arXiv2023

Tackling the dimensions in imaging genetics with CLUB-PLS

A major challenge in imaging genetics and similar fields is to link high-dimensional data in one domain, e.g., genetic data, to high dimensional data in a second domain, e.g., brain imaging data. The standard approach in the area are mass univariate analyses across genetic factors and imaging phenotypes. That entails executing one genome-wide association study (GWAS) for each pre-defined imaging measure. Although this approach has been tremendously successful, one shortcoming is that phenotypes must be pre-defined. Consequently, effects that are not confined to pre-selected regions of interest or that reflect larger brain-wide patterns can easily be missed. In this work we introduce a Partial Least Squares (PLS)-based framework, which we term Cluster-Bootstrap PLS (CLUB-PLS), that can work with large input dimensions in both domains as well as with large sample sizes. One key factor of the framework is to use cluster bootstrap to provide robust statistics for single input features in both domains. We applied CLUB-PLS to investigating the genetic basis of surface area and cortical thickness in a sample of 33,000 subjects from the UK Biobank. We found 107 genome-wide significant locus-phenotype pairs that are linked to 386 different genes. We found that a vast majority of these loci could be technically validated at a high rate: using classic GWAS or Genome-Wide Inferred Statistics (GWIS) we found that 85 locus-phenotype pairs exceeded the genome-wide suggestive (P<1e-05) threshold.

q-bio.GN↗

arXiv2023

Faster Training of Diffusion Models and Improved Density Estimation via Parallel Score Matching

In Diffusion Probabilistic Models (DPMs), the task of modeling the score evolution via a single time-dependent neural network necessitates extended training periods and may potentially impede modeling flexibility and capacity. To counteract these challenges, we propose leveraging the independence of learning tasks at different time points inherent to DPMs. More specifically, we partition the learning task by utilizing independent networks, each dedicated to learning the evolution of scores within a specific time sub-interval. Further, inspired by residual flows, we extend this strategy to its logical conclusion by employing separate networks to independently model the score at each individual time point. As empirically demonstrated on synthetic and image datasets, our approach not only significantly accelerates the training process by introducing an additional layer of parallelization atop data parallelization, but it also enhances density estimation performance when compared to the conventional training methodology for DPMs.

cs.LG↗

arXiv2023

Enhanced Distribution Modelling via Augmented Architectures For Neural ODE Flows

While the neural ODE formulation of normalizing flows such as in FFJORD enables us to calculate the determinants of free form Jacobians in O(D) time, the flexibility of the transformation underlying neural ODEs has been shown to be suboptimal. In this paper, we present AFFJORD, a neural ODE-based normalizing flow which enhances the representation power of FFJORD by defining the neural ODE through special augmented transformation dynamics which preserve the topology of the space. Furthermore, we derive the Jacobian determinant of the general augmented form by generalizing the chain rule in the continuous sense into the Cable Rule, which expresses the forward sensitivity of ODEs with respect to their initial conditions. The cable rule gives an explicit expression for the Jacobian of a neural ODE transformation, and provides an elegant proof of the instantaneous change of variable. Our experimental results on density estimation in synthetic and high dimensional data, such as MNIST, CIFAR-10 and CelebA 32x32, show that AFFJORD outperforms the baseline FFJORD through the improved flexibility of the underlying vector field.

cs.LG↗