Marco Lorenzi

lorenzi-photoMy activity concerns the development and study of computational and statistical methods for the analysis of biomedical data and brain images. I’m also interested in statistical analysis in clinical trials of disease modifying drugs. I’m currently editorial board member of Nature Scientific Report (Neurology Panel), and I worked as statistical consultant for the European clinical project Pharmacog. I was awarded in 2015 with the second ex-aequo prize for the ERCIM Cor Baayen Award.


For an up-to-date list of my publications, please take a look to my Google Scholar page.



Selected research topics

  • Imaging Genetics

One of my main research axis consists in studying the relationship between brain phenotypes quantified by neuroimaging (such as atrophy, or connectivity) and individual’s genetic profile. This challenging research field requires the development of efficient and powerful statistical models for studying multivariate patterns of associations between imaging and genetics data. The circle plot on the left shows the genetic locations significantly associated to the brain cortical thickness shown on the right hand side.


pls_example_20161110_v2 Alzheimer's Brain and Genetics


  • Gaussian Processes for temporal analysis of clinical data

I’m interested in the study of learning algorithms for modeling and predicting longitudinal changes in imaging, clinical and biological data. We can think of time series of patients’ data as measurements from an underlying disease progression trajectory spanning several years (left figure, top). Yet, when we observe the patients during a clinical trial, the disease time information is unknown (left figure bottom). This fascinating research topic aims at reconstructing the natural history of a pathology from individual time series of clinical data (right figure).














  • Statistical learning of multimodal image variation

I’ve been working in the analysis of the joint variation between multimodal brain imaging modalities, such as the brain atrophy measured in magnetic resonance images (MRIs), and the hypometabolism quantified by FDG-PET radiotracers. The video shows that the non-local correlation between atrophy and hypomethabolism in Alzheimer’s patients is identified by localised subcortical temporal atrophy and ventricular enlargement, a pattern mostly associated with the hypometabolism of the temporal/parietal cortex.



  • Non-linear image registration

I’m interested in the development and study of non-linear registration algorithms to reliably detect morphological changes. The figure below shows the parameters of the diffeomorphic transformation of longitudinal brain atrophy in Alzheimer’s disease (left), and the associated spatio-temporal model of brain changes (right). We note that the registration model accurately describes the global brain atrophy, as well as the ventricular expansion and hippocampal atrophy.