About Me
I am a Ph.D. student 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 use and develop computer vision techniques to solve clinical problems. [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 Computer Vision
- Automated Diagnosis
- Multimodal Learning
- Self-Supervised Learning
- Imbalanced Learning
Education
Ph.D. in Electrical Engineering, 2021-present
The University of Texas at Austin
B.A. in Mathematics, 2016-2020
Kenyon College
News
- [Jan. 2023] Paper accepted to ISBI 2023 on multimodal fusion of histopathology imaging and clinical data from my internship with Artera!
- [Oct. 2022] Paper accepted to IEEE Transactions on Medical Imaging on weakly supervised localization in chest X-rays! [Link] [arXiv]
- [Aug. 2022] Preprint out on automated detection of severe aortic stenosis [Paper]
- [Jul. 2022] Paper accepted to DALI 2022 (MICCAI 2022 workshop) and abstract accepted to RSNA 2022 on long-tailed learning for chest X-rays
- [Jun. 2022] Paper accepted to IMLH 2022 (ICML 2022 workshop) on self-supervised learning of echocardiogram videos [Paper] [Code] [Poster]
- [May 2022] Started my internship with the AI team at Artera
- [Oct. 2021] One paper accepted to SPIE Medical Imaging 2022 on pediatric rib fracture detection
- [Aug. 2021] Started my Ph.D. at UT Austin with Atlas Wang!
- [Aug. 2021] One paper accepted to CVAMD 2021 (ICCV 2021 workshop) on multimodal learning
Recent Publications
Quickly discover relevant content by filtering publications.
Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays
IEEE Transactions on Medical Imaging
A Transformer for weakly supervised disease localization that uses a novel feedback loop between (local) radiomics features and (global) chest X-ray features.
A Transformer for weakly supervised disease localization that uses a novel feedback loop between (local) radiomics features and (global) chest X-ray features.
Automated detection of severe aortic stenosis using single-view echocardiography: A self-supervised ensemble learning approach
medRxiv Preprint
Accurate detection of severe aortic stenosis based on self-supervised and ensemble learning of single-view echocardiograms.
Accurate detection of severe aortic stenosis based on self-supervised and ensemble learning of single-view echocardiograms.
Self-Supervised Learning of Echocardiogram Videos Enables Data-Efficient Clinical Diagnosis
arXiv Preprint
Self-supervised learning method for echocardiogram videos drives label-efficient fine-tuning on aortic stenosis classification. Presented at IMLH 2022, an ICML workshop.
Self-supervised learning method for echocardiogram videos drives label-efficient fine-tuning on aortic stenosis classification. Presented at IMLH 2022, an ICML workshop.
Contact
- gholste@utexas.edu