HyperCMR: Enhanced Multi-contrast CMR Reconstruction with Eagle Loss

Ruru Xu; Caner Özer; Ilkay Oksuz

doi:10.1007/978-3-031-87756-8_15

HyperCMR: Enhanced Multi-contrast CMR Reconstruction with Eagle Loss

Ruru Xu^*
, Caner Özer
, Ilkay Oksuz

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Accelerating image acquisition for cardiac magnetic resonance imaging (CMRI) is a critical task. CMRxRecon2024 challenge aims to set the state of the art for multi-contrast CMR reconstruction. This paper presents HyperCMR, a novel framework designed to accelerate the reconstruction of multi-contrast cardiac magnetic resonance (CMR) images. HyperCMR enhances the existing PromptMR model by incorporating advanced loss functions, notably the innovative Eagle Loss, which is specifically designed to recover missing high-frequency information in undersampled k-space. Extensive experiments conducted on the CMRxRecon2024 challenge dataset demonstrate that HyperCMR consistently outperforms the baseline across multiple evaluation metrics, achieving superior SSIM and PSNR scores.

Original language	English
Title of host publication	Statistical Atlases and Computational Models of the Heart. Workshop, CMRxRecon and MBAS Challenge Papers. - 15th International Workshop, STACOM 2024, Held in Conjunction with MICCAI 2024, Revised Selected Papers
Editors	Oscar Camara, Esther Puyol-Antón, Maxime Sermesant, Avan Suinesiaputra, Jichao Zhao, Chengyan Wang, Qian Tao, Alistair Young
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	152-163
Number of pages	12
ISBN (Print)	9783031877551
DOIs	https://doi.org/10.1007/978-3-031-87756-8_15
Publication status	Published - 2025
Event	15th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2024, Held in Conjunction with MICCAI 2024 - Marrakesh, Morocco Duration: 10 Oct 2024 → 10 Oct 2024

Publication series

Name	Lecture Notes in Computer Science
Volume	15448 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	15th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2024, Held in Conjunction with MICCAI 2024
Country/Territory	Morocco
City	Marrakesh
Period	10/10/24 → 10/10/24

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Keywords

Cardiac MRI
Deep Learning
Multi-Modality
Reconstruction

Access to Document

10.1007/978-3-031-87756-8_15

Cite this

Xu, R., Özer, C., & Oksuz, I. (2025). HyperCMR: Enhanced Multi-contrast CMR Reconstruction with Eagle Loss. In O. Camara, E. Puyol-Antón, M. Sermesant, A. Suinesiaputra, J. Zhao, C. Wang, Q. Tao, & A. Young (Eds.), Statistical Atlases and Computational Models of the Heart. Workshop, CMRxRecon and MBAS Challenge Papers. - 15th International Workshop, STACOM 2024, Held in Conjunction with MICCAI 2024, Revised Selected Papers (pp. 152-163). (Lecture Notes in Computer Science; Vol. 15448 LNCS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-87756-8_15

Xu, Ruru ; Özer, Caner ; Oksuz, Ilkay. / HyperCMR : Enhanced Multi-contrast CMR Reconstruction with Eagle Loss. Statistical Atlases and Computational Models of the Heart. Workshop, CMRxRecon and MBAS Challenge Papers. - 15th International Workshop, STACOM 2024, Held in Conjunction with MICCAI 2024, Revised Selected Papers. editor / Oscar Camara ; Esther Puyol-Antón ; Maxime Sermesant ; Avan Suinesiaputra ; Jichao Zhao ; Chengyan Wang ; Qian Tao ; Alistair Young. Springer Science and Business Media Deutschland GmbH, 2025. pp. 152-163 (Lecture Notes in Computer Science).

@inproceedings{aee7625e1dd14a80aa311b55234a4b0c,

title = "HyperCMR: Enhanced Multi-contrast CMR Reconstruction with Eagle Loss",

abstract = "Accelerating image acquisition for cardiac magnetic resonance imaging (CMRI) is a critical task. CMRxRecon2024 challenge aims to set the state of the art for multi-contrast CMR reconstruction. This paper presents HyperCMR, a novel framework designed to accelerate the reconstruction of multi-contrast cardiac magnetic resonance (CMR) images. HyperCMR enhances the existing PromptMR model by incorporating advanced loss functions, notably the innovative Eagle Loss, which is specifically designed to recover missing high-frequency information in undersampled k-space. Extensive experiments conducted on the CMRxRecon2024 challenge dataset demonstrate that HyperCMR consistently outperforms the baseline across multiple evaluation metrics, achieving superior SSIM and PSNR scores.",

keywords = "Cardiac MRI, Deep Learning, Multi-Modality, Reconstruction",

author = "Ruru Xu and Caner {\"O}zer and Ilkay Oksuz",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; 15th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2024, Held in Conjunction with MICCAI 2024 ; Conference date: 10-10-2024 Through 10-10-2024",

year = "2025",

doi = "10.1007/978-3-031-87756-8\_15",

language = "English",

isbn = "9783031877551",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "152--163",

editor = "Oscar Camara and Esther Puyol-Ant{\'o}n and Maxime Sermesant and Avan Suinesiaputra and Jichao Zhao and Chengyan Wang and Qian Tao and Alistair Young",

booktitle = "Statistical Atlases and Computational Models of the Heart. Workshop, CMRxRecon and MBAS Challenge Papers. - 15th International Workshop, STACOM 2024, Held in Conjunction with MICCAI 2024, Revised Selected Papers",

address = "Germany",

}

Xu, R, Özer, C & Oksuz, I 2025, HyperCMR: Enhanced Multi-contrast CMR Reconstruction with Eagle Loss. in O Camara, E Puyol-Antón, M Sermesant, A Suinesiaputra, J Zhao, C Wang, Q Tao & A Young (eds), Statistical Atlases and Computational Models of the Heart. Workshop, CMRxRecon and MBAS Challenge Papers. - 15th International Workshop, STACOM 2024, Held in Conjunction with MICCAI 2024, Revised Selected Papers. Lecture Notes in Computer Science, vol. 15448 LNCS, Springer Science and Business Media Deutschland GmbH, pp. 152-163, 15th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, 10/10/24. https://doi.org/10.1007/978-3-031-87756-8_15

HyperCMR: Enhanced Multi-contrast CMR Reconstruction with Eagle Loss. / Xu, Ruru; Özer, Caner ; Oksuz, Ilkay.
Statistical Atlases and Computational Models of the Heart. Workshop, CMRxRecon and MBAS Challenge Papers. - 15th International Workshop, STACOM 2024, Held in Conjunction with MICCAI 2024, Revised Selected Papers. ed. / Oscar Camara; Esther Puyol-Antón; Maxime Sermesant; Avan Suinesiaputra; Jichao Zhao; Chengyan Wang; Qian Tao; Alistair Young. Springer Science and Business Media Deutschland GmbH, 2025. p. 152-163 (Lecture Notes in Computer Science; Vol. 15448 LNCS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - HyperCMR

T2 - 15th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2024, Held in Conjunction with MICCAI 2024

AU - Xu, Ruru

AU - Özer, Caner

AU - Oksuz, Ilkay

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025

Y1 - 2025

N2 - Accelerating image acquisition for cardiac magnetic resonance imaging (CMRI) is a critical task. CMRxRecon2024 challenge aims to set the state of the art for multi-contrast CMR reconstruction. This paper presents HyperCMR, a novel framework designed to accelerate the reconstruction of multi-contrast cardiac magnetic resonance (CMR) images. HyperCMR enhances the existing PromptMR model by incorporating advanced loss functions, notably the innovative Eagle Loss, which is specifically designed to recover missing high-frequency information in undersampled k-space. Extensive experiments conducted on the CMRxRecon2024 challenge dataset demonstrate that HyperCMR consistently outperforms the baseline across multiple evaluation metrics, achieving superior SSIM and PSNR scores.

AB - Accelerating image acquisition for cardiac magnetic resonance imaging (CMRI) is a critical task. CMRxRecon2024 challenge aims to set the state of the art for multi-contrast CMR reconstruction. This paper presents HyperCMR, a novel framework designed to accelerate the reconstruction of multi-contrast cardiac magnetic resonance (CMR) images. HyperCMR enhances the existing PromptMR model by incorporating advanced loss functions, notably the innovative Eagle Loss, which is specifically designed to recover missing high-frequency information in undersampled k-space. Extensive experiments conducted on the CMRxRecon2024 challenge dataset demonstrate that HyperCMR consistently outperforms the baseline across multiple evaluation metrics, achieving superior SSIM and PSNR scores.

KW - Cardiac MRI

KW - Deep Learning

KW - Multi-Modality

KW - Reconstruction

UR - https://www.scopus.com/pages/publications/105004253586

U2 - 10.1007/978-3-031-87756-8_15

DO - 10.1007/978-3-031-87756-8_15

M3 - Conference contribution

AN - SCOPUS:105004253586

SN - 9783031877551

T3 - Lecture Notes in Computer Science

SP - 152

EP - 163

BT - Statistical Atlases and Computational Models of the Heart. Workshop, CMRxRecon and MBAS Challenge Papers. - 15th International Workshop, STACOM 2024, Held in Conjunction with MICCAI 2024, Revised Selected Papers

A2 - Camara, Oscar

A2 - Puyol-Antón, Esther

A2 - Sermesant, Maxime

A2 - Suinesiaputra, Avan

A2 - Zhao, Jichao

A2 - Wang, Chengyan

A2 - Tao, Qian

A2 - Young, Alistair

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 10 October 2024 through 10 October 2024

ER -

Xu R, Özer C , Oksuz I. HyperCMR: Enhanced Multi-contrast CMR Reconstruction with Eagle Loss. In Camara O, Puyol-Antón E, Sermesant M, Suinesiaputra A, Zhao J, Wang C, Tao Q, Young A, editors, Statistical Atlases and Computational Models of the Heart. Workshop, CMRxRecon and MBAS Challenge Papers. - 15th International Workshop, STACOM 2024, Held in Conjunction with MICCAI 2024, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2025. p. 152-163. (Lecture Notes in Computer Science). doi: 10.1007/978-3-031-87756-8_15