M. Elizabeth Oates
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
M. Elizabeth Oates has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Caroline Leach
Office of Research, College of Medicine, University of Kentucky, Lexington, KY 40536, USA
1 shared publication - Clifford Seth Parker
Department of Computer Science, Stanley and Karen Pigman College of Engineering, University of Kentucky, Lexington, KY 40506, USA
1 shared publication - Donald P. Frush
Department of Radiology, Duke University Medical Center, Durham, USA
1 shared publication - Evan Damron
Office of Research, College of Medicine, University of Kentucky, Lexington, KY 40536, USA
1 shared publication - Jie Zhang
Department of Radiology University of Kentucky College of Medicine Lexington Kentucky USA
1 shared publication - Lane F. Donnelly
School of Medicine, Department of Radiology, Division of Pediatric Radiology, University of North Carolina at Chapel Hill, Chapel Hill, United States
1 shared publication
Latest Publications
- Open Access
- 16 November 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (11) , 579
Beyond Segmentation: Coronary Artery Calcium Scoring with Frozen Self-Supervised CT Features
Coronary artery calcium (CAC) scoring on computed tomography (CT) acquired for other indications could provide calcium-burden information without a dedicated scoring examination. We investigate direct, segmentation-free Agatston score prediction from frozen CT patch representations using only volume-level supervision for the scoring head. A lightweight additive head maps attention-selected features to non-negative contributions, combines them within slices, and sums slice scores across each volume. In developmental evaluation, applying the nonlinear mapping before aggregation improved linearly weighted by – over a pooled multilayer perceptron across six encoders. Using spatially adaptive label-guided temperature (SALT) features, held-out was on gated CT and on contrast-enhanced coronary CT angiography (CCTA), with separately fitted heads. On external non-gated CT, a head fitted on 165 patients from the same cohort achieved on 40 held-out patients; patient-level five-fold cross-validation over all 205 patients yielded , indicating preliminary local-adaptation performance. Unchanged-head external gated transfer achieved (). Gated intraclass correlation coefficient on was . Study-level CAC scores served as CCTA reference targets; non-contrast images were not model inputs. SALT uses gated calcium masks during pretraining, not downstream scoring. Its highest-attention patch overlapped calcium in of calcium-bearing slices, but localization rankings did not directly track scoring rankings. These results support direct, spatially decomposable CAC prediction from reusable features; broader validation is needed before clinical use.- 16 November 2026
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (11) , 579
Open AccessBeyond Segmentation: Coronary Artery Calcium Scoring with Frozen Self-Supervised CT Features
Coronary artery calcium (CAC) scoring on computed tomography (CT) acquired for other indications could provide calcium-burden information without a dedicated scoring examination. We investigate direct, segmentation-free Agatston score prediction from frozen CT patch representations using only volume-level supervision for the scoring head. A lightweight additive head maps attention-selected features to non-negative contributions, combines them within slices, and sums slice scores across each volume. In developmental evaluation, applying the nonlinear mapping before aggregation improved linearly weighted by – over a pooled multilayer perceptron across six encoders. Using spatially adaptive label-guided temperature (SALT) features, held-out was on gated CT and on contrast-enhanced coronary CT angiography (CCTA), with separately fitted heads. On external non-gated CT, a head fitted on 165 patients from the same cohort achieved on 40 held-out patients; patient-level five-fold cross-validation over all 205 patients yielded , indicating preliminary local-adaptation performance. Unchanged-head external gated transfer achieved (). Gated intraclass correlation coefficient on was . Study-level CAC scores served as CCTA reference targets; non-contrast images were not model inputs. SALT uses gated calcium masks during pretraining, not downstream scoring. Its highest-attention patch overlapped calcium in of calcium-bearing slices, but localization rankings did not directly track scoring rankings. These results support direct, spatially decomposable CAC prediction from reusable features; broader validation is needed before clinical use. - 9 June 2025
- Published by Springer Nature in Pediatric Radiology
- Vol. 55 (8) , 1549-1555
The Journey and Relevant Influences for the 15-month Pathway Addressing the Pediatric Radiology Workforce Shortage
The number of trainees pursuing pediatric radiology as a subspecialty is decreasing. Multiple formal and informal discussions have led to a variety of proposed solutions to address the workforce shortage in pediatric radiology. This article focuses on the proposal, approval, and future considerations of an American Board of Radiology (ABR) 15-month pediatric radiology pathway, which includes both certification for diagnostic radiology and subspecialty certification in pediatric radiology, similar to the existing ABR nuclear radiology pathway. The following discussion includes survey data from pediatric radiology leadership Society of Chiefs of Radiology at Children’s Hospitals (SCORCH) and pediatric radiology fellowship program directors on the creation of such a pathway. The results show agreement from leaders in pediatric radiology that an accelerated pathway to ABR certification would help to alleviate the shortage of pediatric radiologists and that the current diagnostic radiology resident training would be impacted by this pathway. Further discussions including this data and an open forum at the 2024 Radiological Society of North America (RSNA) annual meeting led to the recent approval of the 15-month pediatric radiology pathway by the ABR Board of Governors. The implementation of this pathway will be a potential opportunity in addressing the pediatric radiology workforce shortage to better serve pediatric care.
- 9 June 2025
- Published by Springer Nature in Pediatric Radiology
- Vol. 55 (8) , 1549-1555
The Journey and Relevant Influences for the 15-month Pathway Addressing the Pediatric Radiology Workforce Shortage
The number of trainees pursuing pediatric radiology as a subspecialty is decreasing. Multiple formal and informal discussions have led to a variety of proposed solutions to address the workforce shortage in pediatric radiology. This article focuses on the proposal, approval, and future considerations of an American Board of Radiology (ABR) 15-month pediatric radiology pathway, which includes both certification for diagnostic radiology and subspecialty certification in pediatric radiology, similar to the existing ABR nuclear radiology pathway. The following discussion includes survey data from pediatric radiology leadership Society of Chiefs of Radiology at Children’s Hospitals (SCORCH) and pediatric radiology fellowship program directors on the creation of such a pathway. The results show agreement from leaders in pediatric radiology that an accelerated pathway to ABR certification would help to alleviate the shortage of pediatric radiologists and that the current diagnostic radiology resident training would be impacted by this pathway. Further discussions including this data and an open forum at the 2024 Radiological Society of North America (RSNA) annual meeting led to the recent approval of the 15-month pediatric radiology pathway by the ABR Board of Governors. The implementation of this pathway will be a potential opportunity in addressing the pediatric radiology workforce shortage to better serve pediatric care.