Greg Holste

Greg Holste

Ph.D. Candidate
ECE Department, UT Austin

About Me

I am a Ph.D. candidate in Electrical Engineering at The University of Texas at Austin advised by Atlas Wang. As part of the Visual Informatics @ UT Austin (VITA) group, I develop deep learning and computer vision techniques to solve clinical decision-making and medical image analysis problems. My research is funded by the NSF Graduate Research Fellowship Program (GRFP). [CV]

Previously, I have worked with the Medical Imaging and Data Integration (MIDI) Lab at Michigan State University under Adam Alessio on multimodal learning for breast cancer prediction and pediatric rib fracture detection.

Interests

  • Medical image analysis
  • Computer-aided diagnosis
  • Multimodal learning
  • Self-supervised learning
  • Long-tailed learning

Education

  • Ph.D. in Electrical Engineering, 2021-present

    The University of Texas at Austin

  • M.S.E. in Electrical Engineering, 2021-2024

    The University of Texas at Austin

  • B.A. in Mathematics, 2016-2020

    Kenyon College

News

Recent Publications

Quickly discover relevant content by filtering publications.

Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling

npj Digital Medicine
Automated eye disease prognosis by survival analysis from longitudinal medical imaging.
PDF Code Source Document
Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling

Efficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning

Communications Medicine
EchoCLR, a label-efficient self-supervised learning method for echocardiography.
PDF Code Poster Source Document
Efficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning

Artificial intelligence-guided detection of under-recognized cardiomyopathies on point-of-care cardiac ultrasound: a multi-center study

medRxiv preprint
Automated cardiomyopathy detection in point-of-care ultrasonography (POCUS).
PDF Source Document
Artificial intelligence-guided detection of under-recognized cardiomyopathies on point-of-care cardiac ultrasound: a multi-center study

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge

Medical Image Analysis
Overview of the CXR-LT challenge on long-tailed, multi-label disease classification from chest X-ray.
PDF Dataset Project Source Document
Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge

High sensitivity methods for automated rib fracture detection in pediatric radiographs

Scientific Reports
Ensemble methods for automated pediatric rib fracture detection on chest X-ray.
PDF Source Document
High sensitivity methods for automated rib fracture detection in pediatric radiographs
See all publications

Contact

  • gholste@utexas.edu