Mission
The research mission of the Pulmonary Imaging and Computer Vision (PICV) Lab is to develop innovative artificial intelligence (AI) techniques for multimodal medical image processing to characterize physiological structure-function relationships. Specifically we specialize in studying pulmonary diseases using computed tomography (CT), dual-energy CT (DECT), photon-counting CT, and hyper-polarized gas magnetic resonance imaging (HG-MRI).
News
2024 College of Engineering Research Open House
Thursday, April 25, 2024
Fantastic work by all the students that presented at the 2024 College of Engineering Research Open House.
Paper accepted to TMI
Wednesday, February 21, 2024
Faizyab's manuscript "LungViT: Ensembling Cascade of Texture Sensitive Hierarchical Vision Transformers for Cross-Volume Chest CT Image-to-Image Translation" was accepted for publication in IEEE Transactions on Medical Imaging. This work proposes LungViT – a generative adversarial learning approach using hierarchical vision transformers for translating inspiratory CT intensities to corresponding expiratory CT intensities.
Paper accepted to MICCAI MLMI workshop
Sunday, August 20, 2023
Faizyab's paper "Bridging the Task Barriers: Online Knowledge Distillation Across Tasks for Semi-Supervised Mediastinal Segmentation in CT" was accepted to the MICCAI MLMI workshop. This work uses semi-supervised learning with knowledge distillation to perform mediastinal segmentation in non-contrast CT images.