Important Notice for Prospective Lab Members

Kidney Cancer Diagnosis and Prognosis Using Vision Language Models: Developing multimodal AI systems to improve kidney cancer diagnosis, subtype classification, and outcome prediction. Collaboration: AdventHealth

Multimodal AI for Vocal Fold Pathology Detection and Classification: Developing multimodal deep learning models that integrate stroboscopic video, and clinical data to detect, classify, and track vocal fold pathologies. Collaboration: Weill Cornell Medicine

Automated Cardiac Imaging Interpretation for CHD: Building a multimodal AI system that analyzes cardiovascular imaging and generates structured and narrative reports modeled after expert cardiologists. Collaboration: West Virginia University Medicine Children's Hospital

Transformer Guided Implicit Neural Diffeomorphic Registration for Brain MRI: Developing a next-generation neuroimaging registration framework. Collaboration: Orlando Health

Longitudinal AI for Early Breast Cancer Detection and Tumor Evolution Modeling: Developing a multimodal deep learning framework that leverages longitudinal mammography to identify early imaging patterns associated with breast cancer before tumors become clinically visible. This work aims to support earlier detection and improve personalized screening strategies. Collaboration: UCF IAI Faculty

AI-Driven MRI Scanner Usage and Reliability Analysis: Developing data-driven methods to analyze MRI scanner usage patterns, protocol characteristics, and system performance using operational log data, with the goal of improving reliability, safety, and efficiency of clinical imaging systems. Collaboration: Nemours Children’s Health

Lung OncoVision: Multimodal AI for Early Lung Cancer Detection: Developing a foundation-model-enabled multimodal system that integrates radiology imaging, pathology representations, and clinical features to improve early lung cancer detection and malignancy-risk prediction. Collaboration: UCF IAI Faculty

Diagnostic Certainty in Multimodal Medical AI: Developing AI methods to study how diagnostic confidence evolves as information from multiple medical imaging modalities is integrated, with the goal of improving reliability and trustworthiness of clinical AI systems. Collaboration: UCF IAI Faculty