Spatio-Temporal Conditional Diffusion Models for Forecasting Future Multiple Sclerosis Lesion Masks Conditioned on Treatments

(LMID Workshop, MICCAI 2025) Image-based personalized medicine has the potential to transform healthcare, particularly for diseases that exhibit heterogeneous progression such as Multiple Sclerosis (MS). In this work, we introduce the first treatment-aware spatio-temporal diffusion model that is able to generate future masks demonstrating lesion evolution in MS. Our voxel-space approach incorporates multi-modal patient data, including MRI and treatment information, to forecast new and enlarging T2 (NET2) lesion masks at a future time point. Extensive experiments on a multi-centre dataset of 2131 patient 3D MRIs from randomized clinical trials for relapsing-remitting MS demonstrate that our generative model is able to accurately predict NET2 lesion masks for patients across six different treatments. Moreover, we demonstrate our model has the potential for real-world clinical applications through downstream tasks such as future lesion count and location estimation, binary lesion activity classification, and generating counterfactual future NET2 masks for several treatments with different efficacies. This work highlights the potential of causal, image-based generative models as powerful tools for advancing data-driven prognostics in MS.

Conditional Diffusion Models are Medical Image Classifiers that Provide Explainability and Uncertainty for Free

(MIDL 2025) Discriminative classifiers have become a foundational tool in deep learning for medical imaging, excelling at learning separable features of complex data distributions. However, these models often need careful design, augmentation, and training techniques to ensure safe and reliable deployment. Recently, diffusion models have become synonymous with generative modeling in 2D. These models showcase robustness across a range of tasks including natural image classification, where classification is performed by comparing reconstruction errors across images generated for each possible conditioning input. This work presents the first exploration of the potential of class conditional diffusion models for 2D medical image classification. First, we develop a novel majority voting scheme shown to improve the performance of medical diffusion classifiers. Next, extensive experiments on the CheXpert and ISIC Melanoma skin cancer datasets demonstrate that foundation and trained-from-scratch diffusion models achieve competitive performance against SOTA discriminative classifiers without the need for explicit supervision. In addition, we show that diffusion classifiers are intrinsically explainable, and can be used to quantify the uncertainty of their predictions, increasing their trustworthiness and reliability in safety-critical, clinical contexts.

Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality

(ICLR 2025) The Fréchet Video Distance (FVD) is a widely adopted metric for evaluating video generation distribution quality. However, its effectiveness relies on critical assumptions. Our analysis reveals three significant limitations: (1) the non-Gaussianity of the Inflated 3D Convnet (I3D) feature space; (2) the insensitivity of I3D features to temporal distortions; (3) the impractical sample sizes required for reliable estimation. These findings undermine FVD's reliability and show that FVD falls short as a standalone metric for video generation evaluation. After extensive analysis of a wide range of metrics and backbone architectures, we propose JEDi, the JEPA Embedding Distance, based on features derived from a Joint Embedding Predictive Architecture, measured using Maximum Mean Discrepancy with polynomial kernel. Our experiments on multiple open-source datasets show clear evidence that it is a superior alternative to the widely used FVD metric, requiring only 16% of the samples to reach its steady value, while increasing alignment with human evaluation by 34%, on average.

Electrochemical Analysis of High Capacity Li-Ion Pouch Cell for Automotive Applications

(SAE WCX Digital Summit 2021) Major original equipment manufacturers (OEMs) have already marketed electric vehicles in large scale but apart from business strategies and policies, the real engineering problems must be addressed. Lithium-ion batteries are a promising technology for energy storage; however, their low energy density and complex electro-chemical nature, compared to fossil fuels, presents additional challenges. Their complex nature and strong temperature dependence during operation must be studied with additional accuracy, capable to predict their behavior. In this research, a pseudo two dimensional (P2D) electro-chemical model, for a recent high capacity NMC pouch cell for automotive applications is developed. The electrochemical model with its temperature dependent parameters is validated at high, low, and reference temperature within 10°C to 50°C temperature range. For each temperature various discharge C-rates to accurately replicate the battery cell operational conditions. The overall goodness of the model is proven with limited RMS errors in all the cases. Low temperatures and high C-rates are discovered to limit sensibly the battery performances. The complete analysis provides valuable design considerations for the battery thermal management system (BTMS) to enhance performance, cycle life and safety of future electrified vehicle energy storage systems.