Sustainable Ultralightweight U-Net-Based Architecture for Myocardium Segmentation

Filarecki, Jakub; Mockiewicz, Dorota; Giełczyk, Agata; Kuźba-Kryszak, Tamara; Makarewicz, Roman; Lewandowski, Marek; Serafin, Zbigniew

doi:10.3390/jcm14227971

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Sustainable Ultralightweight U-Net-Based Architecture for Myocardium Segmentation

by

Jakub Filarecki

¹

,

Dorota Mockiewicz

¹

,

Agata Giełczyk

^1,*

,

Tamara Kuźba-Kryszak

²,

Roman Makarewicz

³

,

Marek Lewandowski

¹ and

Zbigniew Serafin

¹

Faculty of Telecommunications, Computer Science and Electrical Engineering, Bydgoszcz University of Science and Technology, 85-796 Bydgoszcz, Poland

²

Department of Radiotherapy, Centre of Oncology in Bydgoszcz, 85-796 Bydgoszcz, Poland

³

Department of Oncology and Brachytherapy, Ludwik Rydygier Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University in Torun, 85-067 Bydgoszcz, Poland

^*

Author to whom correspondence should be addressed.

J. Clin. Med. 2025, 14(22), 7971; https://doi.org/10.3390/jcm14227971

Submission received: 7 October 2025 / Revised: 5 November 2025 / Accepted: 7 November 2025 / Published: 10 November 2025

(This article belongs to the Special Issue Applications of Artificial Intelligence and Digital Therapeutics in Clinical Medicine)

Download

Browse Figure

Versions Notes

Abstract

Background: Medical image segmentation is essential for accurate diagnosis and treatment planning. The U-Net architecture is widely regarded as the gold standard, yet its large size and high computational demand pose significant challenges for practical deployment. Methods: Real data (MRI images) from hospital patients were used in this study. We proposed a novel lightweight architecture tailored specifically for myocardium (cardiac muscle) segmentation. Results: We presented results comparable to state-of-the-art methods in terms of IoU and Dice coefficients. Nonetheless, the results achieved are much more favorable from the perspective of AI’s sustainable development. The proposed architecture ensured the following average results: IOU = 0.7889 and Dice = 0.8780 using 263 k parameters and a total of 6.24 G FLOPs. Conclusions: The proposed schema can potentially be used to support radiologists in improving the diagnostic process. The presented approach is efficient and fast. Most promisingly, the reduction in the model’s complexity is significant compared to the state-of-the-art methods.

Keywords: computer vision; Green AI; MRI images; myocardium; segmentation; U-Net

Graphical Abstract

Share and Cite

MDPI and ACS Style

Filarecki, J.; Mockiewicz, D.; Giełczyk, A.; Kuźba-Kryszak, T.; Makarewicz, R.; Lewandowski, M.; Serafin, Z. Sustainable Ultralightweight U-Net-Based Architecture for Myocardium Segmentation. J. Clin. Med. 2025, 14, 7971. https://doi.org/10.3390/jcm14227971

AMA Style

Filarecki J, Mockiewicz D, Giełczyk A, Kuźba-Kryszak T, Makarewicz R, Lewandowski M, Serafin Z. Sustainable Ultralightweight U-Net-Based Architecture for Myocardium Segmentation. Journal of Clinical Medicine. 2025; 14(22):7971. https://doi.org/10.3390/jcm14227971

Chicago/Turabian Style

Filarecki, Jakub, Dorota Mockiewicz, Agata Giełczyk, Tamara Kuźba-Kryszak, Roman Makarewicz, Marek Lewandowski, and Zbigniew Serafin. 2025. "Sustainable Ultralightweight U-Net-Based Architecture for Myocardium Segmentation" Journal of Clinical Medicine 14, no. 22: 7971. https://doi.org/10.3390/jcm14227971

APA Style

Filarecki, J., Mockiewicz, D., Giełczyk, A., Kuźba-Kryszak, T., Makarewicz, R., Lewandowski, M., & Serafin, Z. (2025). Sustainable Ultralightweight U-Net-Based Architecture for Myocardium Segmentation. Journal of Clinical Medicine, 14(22), 7971. https://doi.org/10.3390/jcm14227971

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Sustainable Ultralightweight U-Net-Based Architecture for Myocardium Segmentation

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI