Lemuel Puglisi

Find me either in Catania (DMI, UniCT)

or in Messina (MIFT, UniME)

PhD student at University of Catania and Imaging Research Scientist at Queen Square Analytics.

Short bio. I graduated cum laude with a Bachelor’s degree in Computer Science from the University of Catania in July 2021, and I have completed my Master’s degree in Computer Science, specializing in data science, also with a cum laude distinction from the same institution in April 2023. I started my internship at Queen Square Analytics in September 2022 and have joined the QSA team as an imaging research scientist since March 2023. From August 2023, I have started my PhD at University of Catania on data-driven neurodegenerative disease progression modeling under the supervision of Prof. Daniele Ravì. In February 2025, I joined the MANIFOLD lab at UCL as a visiting researcher, under the supervision of Prof. James Cole.

My research interests center around the application of artificial intelligence (AI) to medical imaging with a focus on the study of neurodegenerative diseases, particularly Multiple Sclerosis and Alzheimer’s disease.

news

Jan 1, 2026	Our Brain paper on MS subtyping has attracted Global Attention (click post).
Nov 8, 2025	DeepSSIM has been accepted to WACV’26!
Nov 8, 2025	CoCoLIT has been accepted to AAAI’26! (17% A.R.)
Sep 26, 2025	BrLP achieved the runner-up position at the MedIA Best Paper Award (@ MICCAI’25)
Aug 1, 2025	BrLP has been accepted for publication in Medical Image Analysis!

selected publications

2026

CoCoLIT: ControlNet-Conditioned Latent Image Translation for MRI to Amyloid PET Synthesis

Alec Sargood^†, Lemuel Puglisi^†, James H Cole, and 3 more authors

In AAAI, 2026

^† Joint first authorship (<17% acceptance rate over 20k+ papers)
Abs PDF Code

Synthesizing amyloid PET scans from the more widely available and accessible structural MRI modality offers a promising, cost-effective approach for large-scale Alzheimer’s Disease (AD) screening. This is motivated by evidence that, while MRI does not directly detect amyloid pathology, it may nonetheless encode information correlated with amyloid deposition that can be uncovered through advanced modeling. However, the high dimensionality and structural complexity of 3D neuroimaging data pose significant challenges for existing MRI-to-PET translation methods. Modeling the cross-modality relationship in a lower-dimensional latent space can simplify the learning task and enable more effective translation. As such, we present CoCoLIT (ControlNet-Conditioned Latent Image Translation), a diffusion-based latent generative framework that incorporates three main innovations: (1) a novel Weighted Image Space Loss (WISL) that improves latent representation learning and synthesis quality; (2) a theoretical and empirical analysis of Latent Average Stabilization (LAS), an existing technique used in similar generative models to enhance inference consistency; and (3) the introduction of ControlNet-based conditioning for MRI-to-PET translation. We evaluate CoCoLIT’s performance on publicly available datasets and find that our model significantly outperforms state-of-the-art methods on both image-based and amyloid-related metrics. Notably, in amyloid-positivity classification, CoCoLIT outperforms the second-best method with improvements of +10.5% on the internal dataset and +23.7% on the external dataset.

2025

Combined magnetic resonance imaging and serum analysis reveals distinct multiple sclerosis types

Charles Willard^†, Lemuel Puglisi^†, Daniele Ravi, and 7 more authors

In Brain, 2025

^† Joint first authorship; 🌟 Featured in The Guardian.
Abs PDF

Multiple sclerosis (MS) is a highly heterogeneous disease in its clinical manifestation and progression. Predicting individual disease courses is key for aligning treatments with underlying pathobiology. We developed an unsupervised machine learning model integrating MRI-derived measures with serum neurofilament light chain (sNfL) levels to identify biologically informed MS subtypes and stages. Using a training cohort of patients with relapsing–remitting and secondary progressive MS (n = 189), with validation on a newly diagnosed population (n = 445), we discovered two distinct subtypes defined by the timing of sNfL elevation and MRI abnormalities (early- and late-sNfL types). In comparison to MRI-only models, incorporating sNfL with MRI improved correlations of data-derived stages with the Expanded Disability Status Scale in the training (Spearman’s ρ = 0.420 versus MRI-only ρ = 0.231, P = 0.001) and external test sets (ρ = 0.163 for MRI–sNfL, versus ρ = 0.067 for MRI-only). The early-sNfL subtype showed elevated sNfL, corpus callosum injury and early lesion accrual, reflecting more active inflammation and neurodegeneration, whereas the late-sNfL group showed early volume loss in the cortical and deep grey matter volumes, with later sNfL elevation. Cross-sectional subtyping predicted longitudinal radiological activity: the early-sNfL group showed a 144% increased risk of new lesion formation (hazard ratio = 2.44, 95% confidence interval 1.38–4.30, P < 0.005) compared with the late-sNfL group. Baseline subtyping, over time, predicted treatment effect on new lesion formation on the external test set (faster lesion accrual in early-sNfL compared with late-sNfL, P = 0.01), in addition to treatment effects on brain atrophy (early sNfL average percentage brain volume change: −0.41, late-sNfL = −0.31, P = 0.04). Integration of sNfL provides an improved framework in comparison to MRI-only subtyping of MS to stage disease progression and inform prognosis. Our model predicted treatment responsiveness in early, more active disease states. This approach offers a powerful alternative to conventional clinical phenotypes and supports future efforts to refine prognostication and guide personalized therapy in MS.
Brain Latent Progression: Individual-based Spatiotemporal Disease Progression on 3D Brain MRIs via Latent Diffusion

Lemuel Puglisi, Daniel C Alexander, and Daniele Ravì

In Medical Image Analysis, 2025

Impact Factor = 11.8; 🌟 Runner-up @ Best MedIA Paper Award
Abs PDF Code

The growing availability of longitudinal Magnetic Resonance Imaging (MRI) datasets has facilitated Artificial Intelligence (AI)-driven modeling of disease progression, making it possible to predict future medical scans for individual patients. However, despite significant advancements in AI, current methods continue to face challenges including achieving patient-specific individualization, ensuring spatiotemporal consistency, efficiently utilizing longitudinal data, and managing the substantial memory demands of 3D scans. To address these challenges, we propose Brain Latent Progression (BrLP), a novel spatiotemporal model designed to predict individual-level disease progression in 3D brain MRIs. The key contributions in BrLP are fourfold: (i) it operates in a small latent space, mitigating the computational challenges posed by high-dimensional imaging data; (ii) it explicitly integrates subject metadata to enhance the individualization of predictions; (iii) it incorporates prior knowledge of disease dynamics through an auxiliary model, facilitating the integration of longitudinal data; and (iv) it introduces the Latent Average Stabilization (LAS) algorithm, which (a) enforces spatiotemporal consistency in the predicted progression at inference time and (b) allows us to derive a measure of the uncertainty for the prediction at the global and voxel level. We train and evaluate BrLP on 11,730 T1-weighted (T1w) brain MRIs from 2,805 subjects and validate its generalizability on an external test set comprising 2,257 MRIs from 962 subjects. Our experiments compare BrLP-generated MRI scans with real follow-up MRIs, demonstrating state-of-the-art accuracy compared to existing methods. The code is publicly available at: https://github.com/LemuelPuglisi/BrLP.

2024

SynthBA: Reliable Brain Age Estimation Across Multiple MRI Sequences and Resolutions

Lemuel Puglisi, Alessia Rondinella, Linda De Meo, and 3 more authors

In IEEE Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, 2024

Abs PDF Code

Brain age is a critical measure that reflects the biological ageing process of the brain. The gap between brain age and chronological age, referred to as brain PAD (Predicted Age Difference), has been utilized to investigate neurodegenerative conditions. Brain age can be predicted using MRIs and machine learning techniques. However, existing methods are often sensitive to acquisition-related variabilities, such as differences in acquisition protocols, scanners, MRI sequences, and resolutions, significantly limiting their application in highly heterogeneous clinical settings. In this study, we introduce Synthetic Brain Age (SynthBA), a robust deep-learning model designed for predicting brain age. SynthBA utilizes an advanced domain randomization technique, ensuring effective operation across a wide array of acquisition-related variabilities. To assess the effectiveness and robustness of SynthBA, we evaluate its predictive capabilities on internal and external datasets, encompassing various MRI sequences and resolutions, and compare it with state-of-the-art techniques. Additionally, we calculate the brain PAD in a large cohort of subjects with Alzheimer’s Disease (AD), demonstrating a significant correlation with AD-related measures of cognitive dysfunction. SynthBA holds the potential to facilitate the broader adoption of brain age prediction in clinical settings, where re-training or fine-tuning is often unfeasible. The SynthBA source code and pre-trained models are publicly available at https://github.com/LemuelPuglisi/SynthBA.
Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledge

Lemuel Puglisi, Daniel C Alexander, and Daniele Ravì

In International Conference on Medical Image Computing and Computer Assisted Intervention, 2024

🌟 Oral, Best Paper Award Candidate (top <1%)
Abs PDF Code demo

In this work, we introduce Brain Latent Progression (BrLP), a novel spatiotemporal disease progression model based on latent diffusion. BrLP is designed to predict the evolution of diseases at the individual level on 3D brain MRIs. Existing deep generative models developed for this task are primarily data-driven and face challenges in learning disease progressions. BrLP addresses these challenges by incorporating prior knowledge from disease models to enhance the accuracy of predictions. To implement this, we propose to integrate an auxiliary model that infers volumetric changes in various brain regions. Additionally, we introduce Latent Average Stabilization (LAS), a novel technique to improve spatiotemporal consistency of the predicted progression. BrLP is trained and evaluated on a large dataset comprising 11,730 T1-weighted brain MRIs from 2,805 subjects, collected from three publicly available, longitudinal Alzheimer’s Disease (AD) studies. In our experiments, we compare the MRI scans generated by BrLP with the actual follow-up MRIs available from the subjects, in both cross-sectional and longitudinal settings. BrLP demonstrates significant improvements over existing methods, with an increase of 22% in volumetric accuracy across AD-related brain regions and 43% in image similarity to the ground-truth scans. The ability of BrLP to generate conditioned 3D scans at the subject level, along with the novelty of integrating prior knowledge to enhance accuracy, represents a significant advancement in disease progression modeling, opening new avenues for precision medicine. The code of BrLP is available at the following link: https://github.com/LemuelPuglisi/BrLP.

2023

DeepBrainPrint: A Novel Contrastive Framework for Brain MRI Re-Identification

Lemuel Puglisi, Arman Eshaghi, Geoff Parker, and 3 more authors

In Medical Imaging with Deep Learning, 2023

Abs PDF Code Poster

Recent advances in MRI have led to the creation of large datasets. With the increase in data volume, it has become difficult to locate previous scans of the same patient within these datasets (a process known as re-identification). To address this issue, we propose an AI-powered medical imaging retrieval framework called DeepBrainPrint, which is designed to retrieve brain MRI scans of the same patient. Our framework is a semi-self-supervised contrastive deep learning approach with three main innovations. First, we use a combination of self-supervised and supervised paradigms to create an effective brain fingerprint from MRI scans that can be used for real-time image retrieval. Second, we use a special weighting function to guide the training and improve model convergence. Third, we introduce new imaging transformations to improve retrieval robustness in the presence of intensity variations (i.e. different scan contrasts), and to account for age and disease progression in patients. We tested DeepBrainPrint on a large dataset of T1-weighted brain MRIs from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and on a synthetic dataset designed to evaluate retrieval performance with different image modalities. Our results show that DeepBrainPrint outperforms previous methods, including simple similarity metrics and more advanced contrastive deep learning frameworks.