José Luis Ambite

This paper generates synthetic diffusion MRI scalar maps from T1-weighted images using RevGAN, showing they retain microstructural features and perform well in downstream tasks.

This study evaluates 2D and 3D diffusion models for generating synthetic DTI maps, finding 3D models perform better in downstream tasks like sex and dementia classification.

This study compares explainable AI models for Alzheimer's disease classification using MRI scans, evaluating interpretability methods and generalization across different populations.

This paper evaluates transfer learning methods for Alzheimer's disease classification using brain MRI, finding that contrastive learning improves performance, especially with limited data.

This paper proposes a 3D CNN for classifying Alzheimer's and Parkinson's disease using T1-weighted MRI, achieving higher ROC-AUC than random forest on multiple datasets.

The paper evaluates clustering algorithms for IBD mapping, finding that Markov Clustering outperforms others in statistical power and efficiency.

The paper introduces iLASH, an algorithm for fast and accurate detection of identity-by-descent tracts in large genomic datasets, achieving significant speed improvements over existing methods.

This study links genomic data with EHRs to identify health outcomes enriched in sub-populations, revealing both known and novel associations.

This paper introduces NERO, a biomedical named-entity ontology with an annotated corpus, and demonstrates its utility through text embedding for discovering associations.