ORION-CMR: On-scanner Reporting with Integrated Foundation Model for End-to-End Cardiac MRI Analysis and Interpretation
Abstract
Cardiovascular magnetic resonance (CMR) provides comprehensive cardiac assessment but remains underutilized because of the complexity of acquisition, post-processing, and interpretation. Existing artificial intelligence (AI) methods address isolated tasks, limiting clinical integration. We present ORION-CMR (On-scanner Reporting with Integrated fOunda-tioN Model), the first clinically evaluated scanner-native end-to-end CMR foundation model. Pretrained on 12,896,733 CMR images from 9,258 studies, ORION-CMR performs sequence classification, ventricular function assessment, late gadolinium enhancement (LGE) detection, binary and multiclass disease classification, and local large language model-based report generation in approximately 90 seconds. The framework. was evaluated on public benchmarks and clinically validated in a multi-vendor cohort of 68 subjects with normal examinations, congenital heart disease, dilated cardiomyopathy, and myocardial infarction. ORION-CMR outperformed supervised baselines and the previously published CMR foundation model (CMR-FM), achieving state-of-the-art performance for LGE classification and scar segmentation. Clinical evaluation achieved an AUC of 0.96 for normal-versus abnormal classification and 0.88 for multiclass disease classification, while generated reports demonstrated 81.4% agreement with expert interpretation. These results demonstrate the feasibility of real-time scanner-native AI-assisted CMR analysis and automated report generation.
Related
- Synthetic diagnostics and integrated modeling: Bridging the gap between measurement and interpretation in magnetic confinement fusion
- Four-scanner virtual-conjugation for large field-of-view, broadband one-, two- and three-photon microscopy
- Comparison of spectral performance of three dual-energy CT scanners equipped with a deep-learning image reconstruction algorithm and one photon counting CT scanner: A phantom study
- Towards Sustainable Magnetic Resonance Imaging: Insights from long-term, high-resolution energy recordings across an entire scanner fleet
- Resampling-based batch reweighting for ComBat harmonization of MRI radiomic features in a multi-scanner glioma cohort
BibTeX
@misc{demirel2026orioncmr,
title = {{ORION-CMR: On-scanner Reporting with Integrated Foundation Model for End-to-End Cardiac MRI Analysis and Interpretation}},
author = {Omer Burak Demirel and Kelly K. Horst and Alessio Perazzolo and Elisa Bruno and Kenan Kaya and Rongzhen Ouyang and Enas Ahmed and Jouke Smink and Spencer L. Waddle and Zainudeen Kallumpurath and Tzu Cheng Chao and Dinghui Wang and Steve G. Langer and Timothy L. Kline and Panagiotis Korfiatis and Jacinta Browne and Ivana Isgum and Tim Leiner},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.23950},
eprint = {2609.23950},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.23950},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - ORION-CMR: On-scanner Reporting with Integrated Foundation Model for End-to-End Cardiac MRI Analysis and Interpretation
AU - Omer Burak Demirel
AU - Kelly K. Horst
AU - Alessio Perazzolo
AU - Elisa Bruno
AU - Kenan Kaya
AU - Rongzhen Ouyang
AU - Enas Ahmed
AU - Jouke Smink
AU - Spencer L. Waddle
AU - Zainudeen Kallumpurath
AU - Tzu Cheng Chao
AU - Dinghui Wang
AU - Steve G. Langer
AU - Timothy L. Kline
AU - Panagiotis Korfiatis
AU - Jacinta Browne
AU - Ivana Isgum
AU - Tim Leiner
PY - 2026
DA - 2026/09/20
PB - arXiv
DO - 10.48550/arxiv.2609.23950
UR - https://arxiv.org/abs/2609.23950
AB - Cardiovascular magnetic resonance (CMR) provides comprehensive cardiac assessment but remains underutilized because of the complexity of acquisition, post-processing, and interpretation. Existing artificial intelligence (AI) methods address isolated tasks, limiting clinical integration. We present ORION-CMR (On-scanner Reporting with Integrated fOunda-tioN Model), the first clinically evaluated scanner-native end-to-end CMR foundation model. Pretrained on 12,896,733 CMR images from 9,258 studies, ORION-CMR performs sequence classification, ventricular function assessment, late gadolinium enhancement (LGE) detection, binary and multiclass disease classification, and local large language model-based report generation in approximately 90 seconds. The framework. was evaluated on public benchmarks and clinically validated in a multi-vendor cohort of 68 subjects with normal examinations, congenital heart disease, dilated cardiomyopathy, and myocardial infarction. ORION-CMR outperformed supervised baselines and the previously published CMR foundation model (CMR-FM), achieving state-of-the-art performance for LGE classification and scar segmentation. Clinical evaluation achieved an AUC of 0.96 for normal-versus abnormal classification and 0.88 for multiclass disease classification, while generated reports demonstrated 81.4% agreement with expert interpretation. These results demonstrate the feasibility of real-time scanner-native AI-assisted CMR analysis and automated report generation.
ER -