Marco Lorenzi
YOU?
Author Swipe
View article: Knowledge-based semantic enrichment of medical imaging data for automatic phenotyping and pattern discovery in metastatic lung cancer
Knowledge-based semantic enrichment of medical imaging data for automatic phenotyping and pattern discovery in metastatic lung cancer Open
IntroductionThe emergence of AI models for the analysis of 18FDG PET/CT images has opened the way for automatic quantification of clinically-relevant parameters in metastatic cancer patients such as e.g. the number, metabolic volume, and d…
View article: Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications
Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications Open
View article: Introduction to trustworthy AI for medical imaging
Introduction to trustworthy AI for medical imaging Open
View article: Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applications
Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applications Open
View article: Disease Progression Modelling and Stratification for detecting sub-trajectories in the natural history of pathologies: application to Parkinson's Disease trajectory modelling
Disease Progression Modelling and Stratification for detecting sub-trajectories in the natural history of pathologies: application to Parkinson's Disease trajectory modelling Open
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, gen…
View article: A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications
A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications Open
Background. Federated learning (FL) has gained wide popularity as a collaborative learning paradigm enabling collaborative AI in sensitive healthcare applications. Nevertheless, the practical implementation of FL presents technical and org…
View article: A data-driven model of disability progression in progressive multiple sclerosis
A data-driven model of disability progression in progressive multiple sclerosis Open
This study applies the Gaussian process progression model, a Bayesian data-driven disease progression model, to analyse the evolution of primary progressive multiple sclerosis. Utilizing data from 1521 primary progressive multiple sclerosi…
View article: Volumetric Study of the Hippocampus in Early-onset Schizophrenia: Correlations with Age of Onset
Volumetric Study of the Hippocampus in Early-onset Schizophrenia: Correlations with Age of Onset Open
View article: Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications
Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications Open
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 th…
View article: Let Them Drop: Scalable and Efficient Federated Learning Solutions Agnostic to Stragglers
Let Them Drop: Scalable and Efficient Federated Learning Solutions Agnostic to Stragglers Open
International audience
View article: Buffalo: A Practical Secure Aggregation Protocol for Buffered Asynchronous Federated Learning
Buffalo: A Practical Secure Aggregation Protocol for Buffered Asynchronous Federated Learning Open
International audience
View article: A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications
A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications Open
Federated learning (FL) has gained wide popularity as a collaborative learning paradigm enabling trustworthy AI in sensitive healthcare applications. Never-theless, the practical implementation of FL presents technical and organizational c…
View article: Preictal dysfunctions of inhibitory interneurons paradoxically lead to their rebound hyperactivity and to low-voltage-fast onset seizures in Dravet syndrome
Preictal dysfunctions of inhibitory interneurons paradoxically lead to their rebound hyperactivity and to low-voltage-fast onset seizures in Dravet syndrome Open
Epilepsies have numerous specific mechanisms. The understanding of neural dynamics leading to seizures is important for disclosing pathological mechanisms and developing therapeutic approaches. We investigated electrographic activities and…
View article: Privacy preserving image registration
Privacy preserving image registration Open
View article: Federated Multi-centric Image Segmentation with Uneven Label Distribution
Federated Multi-centric Image Segmentation with Uneven Label Distribution Open
View article: Fed-MIWAE: Federated Imputation of Incomplete Data Via Deep Generative Models
Fed-MIWAE: Federated Imputation of Incomplete Data Via Deep Generative Models Open
View article: Benchmarking Collaborative Learning Methods Cost-Effectiveness for Prostate Segmentation
Benchmarking Collaborative Learning Methods Cost-Effectiveness for Prostate Segmentation Open
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 learn…
View article: Tackling the dimensions in imaging genetics with CLUB-PLS
Tackling the dimensions in imaging genetics with CLUB-PLS Open
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 …
View article: On Tail Decay Rate Estimation of Loss Function Distributions
On Tail Decay Rate Estimation of Loss Function Distributions Open
The study of loss function distributions is critical to characterize a model's behaviour on a given machine learning problem. For example, while the quality of a model is commonly determined by the average loss assessed on a testing set, t…
View article: Faster Training of Diffusion Models and Improved Density Estimation via Parallel Score Matching
Faster Training of Diffusion Models and Improved Density Estimation via Parallel Score Matching Open
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 counterac…
View article: Enhanced Distribution Modelling via Augmented Architectures For Neural ODE Flows
Enhanced Distribution Modelling via Augmented Architectures For Neural ODE Flows Open
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 subopti…
View article: Fed-ComBat: A Generalized Federated Framework for Batch Effect Harmonization in Collaborative Studies
Fed-ComBat: A Generalized Federated Framework for Batch Effect Harmonization in Collaborative Studies Open
In neuroimaging research, the utilization of multi-centric analyses is crucial for obtaining sufficient sample sizes and representative clinical populations. Data harmonization techniques are typically part of the pipeline in multi-centric…
View article: Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applications
Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applications Open
The real-world implementation of federated learning is complex and requires research and development actions at the crossroad between different domains ranging from data science, to software programming, networking, and security. While tod…
View article: First pilot case-control interventional study using autologous extracellular vesicles to treat chronic venous ulcers unresponsive to conventional treatments
First pilot case-control interventional study using autologous extracellular vesicles to treat chronic venous ulcers unresponsive to conventional treatments Open
Current therapeutic approaches for chronic venous ulcers (CVUs) still require evidence of effectiveness. Diverse sources of extracellular vesicles (EVs) have been proposed for tissue regeneration, however the lack of potency tests, to pred…
View article: A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates
A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates Open
Code is available https://github.com/Accenture/Labs-Federated-Learning/tree/asynchronous_FL
View article: MC-RVAE: Multi-channel recurrent variational autoencoder for multimodal Alzheimer’s disease progression modelling
MC-RVAE: Multi-channel recurrent variational autoencoder for multimodal Alzheimer’s disease progression modelling Open
View article: Sequential Informed Federated Unlearning: Efficient and Provable Client Unlearning in Federated Optimization
Sequential Informed Federated Unlearning: Efficient and Provable Client Unlearning in Federated Optimization Open
The aim of Machine Unlearning (MU) is to provide theoretical guarantees on the removal of the contribution of a given data point from a training procedure. Federated Unlearning (FU) consists in extending MU to unlearn a given client's cont…
View article: Integration of Multimodal Data
Integration of Multimodal Data Open
This chapter focuses on the joint modeling of heterogeneous information, such as imaging, clinical, and biological data. This kind of problem requires to generalize classical uni- and multivariate association models to account for complex …
View article: Validation of Federated Unlearning on Collaborative Prostate Segmentation
Validation of Federated Unlearning on Collaborative Prostate Segmentation Open
View article: Convalescent or standard plasma versus standard of care in the treatment of COVID-19 patients with respiratory impairment: short and long-term effects. A three-arm randomized controlled clinical trial
Convalescent or standard plasma versus standard of care in the treatment of COVID-19 patients with respiratory impairment: short and long-term effects. A three-arm randomized controlled clinical trial Open
Background The efficacy of early treatment with convalescent plasma in patients with COVID-19 is debated. Nothing is known about the potential effect of other plasma components other than anti-SARS-CoV-2 antibodies. Methods To determine wh…