Right Atrium Segmentation (RAS), how cardiac imaging data resources contribute to personalized diagnosis and treatment of atrial fibrillation patients through digital heart twins?

RAS, a data set for atrial structural analysis and mining, focuses on the structural remodeling of the atrium of patients with atrial fibrillation or personalized diagnosis and treatment based on digital twin hearts.
Like

Share this post

Choose a social network to share with, or copy the URL to share elsewhere

This is a representation of how your post may appear on social media. The actual post will vary between social networks

Atrial fibrillation (AF) is a globally significant chronic disease, being the most common cardiac arrhythmia, and is associated with substantial morbidity and mortality. The suboptimal clinical management of AF largely stems from a fundamental lack of understanding of atrial anatomy. Recent advancements, particularly the widespread use of gadolinium-based contrast agents in assessing atrial fibrosis and scarring through late gadolinium-enhanced magnetic resonance imaging (LGE-MRI), have significantly improved the visualization of organ structures and related components5. Clinical investigations utilizing LGE-MRI in AF patients have highlighted that the extent and distribution of atrial fibrosis can reliably predict the success of ablation procedures6. Recent studies using LGE-MRI for atrial assessments have further emphasized the crucial role of atrial structure in comprehending and treating AF. Therefore, a direct analysis of atrial structure is vital for effective AF treatment.

Atrial segmentation is a fundamental process involving the extraction of atrial cavity structures from LGE-MRI images. This process serves as a crucial preliminary step in enabling the objective evaluation and quantitative analysis of atrial structure within the context of AF. While extensive research has been conducted on the automatic and semi-automatic segmentation of the left atrium (LA), given its central role in AF studies, it is equally imperative to conduct comprehensive structural assessments of the right atrium (RA). Despite the relatively limited exploration of the pathological changes occurring in the RA within the context of AF, existing evidence strongly suggests that AF exerts its impact on both atria. Therefore, it is imperative to delve into the intricate relationship between AF and the RA. This connection is primarily attributed to a complex interplay of structural, electrical, and metabolic remodeling processes that transpire within the RA. Consequently, research endeavours dedicated to the segmentation of the RA from LGE-MRI scans are indispensable.

Thus, we introduce the RAS dataset (https://zenodo.org/records/10967867), a valuable resource comprising 50 high-resolution LGE-MRI scans, each with spatial dimensions of either 576 × 576 × 88 or 640 × 640 × 88 pixels. These scans have undergone meticulous pixel-wise manual annotation, performed by four highly trained graduate students and subsequently validated by three experienced advisors. The RAS dataset represents a significant contribution to the field, serving as a valuable resource for researchers engaged in developing and evaluating automatic RA segmentation algorithms. Furthermore, it has the potential to support the creation of image-based personalized models, thereby advancing our understanding and treatment of AF.

Finally, we are delighted to share our work with the scientific community and domain experts in the prestigious journal, Scientific Data. We sincerely hope that this resource can provide valuable research groundwork and further insights for the community.

Reference

  1. Zhu, J., Bai, J., Zhou, Z., Liang, Y., Chen, Z., Chen, X., & Zhang, X. (2024). RAS Dataset: A 3D Cardiac LGE-MRI Dataset for Segmentation of Right Atrial Cavity. Scientific data. https://doi.org/10.1038/s41597-024-03253-9
  2. Zhao, J., Kennelly, J., Nalar, A., Kulathilaka, A., Sharma, R., Bai, J., Li, N., & Fedorov, V. V. (2023). Chamber-specific wall thickness features in human atrial fibrillation. Interface focus, 13(6), 20230044. https://doi.org/10.1098/rsfs.2023.0044
  3. Bai, J., Lo, A., Kennelly, J., Sharma, R., Zhao, N., Trew, M. L., & Zhao, J. (2023). Mechanisms of pulmonary arterial hypertension-induced atrial fibrillation: insights from multi-scale models of the human atria. Interface focus, 13(6), 20230039. https://doi.org/10.1098/rsfs.2023.0039
  4. Bai, J., Zhao, J., Ni, H., & Yin, D. (2023). Editorial: Diagnosis, monitoring, and treatment of heart rhythm: new insights and novel computational methods. Frontiers in physiology, 14, 1272377. https://doi.org/10.3389/fphys.2023.1272377
  5. Bai, J., Lu, Y., Wang, H., & Zhao, J. (2022). How synergy between mechanistic and statistical models is impacting research in atrial fibrillation. Frontiers in physiology, 13, 957604. https://doi.org/10.3389/fphys.2022.957604
  6. Bai, J., Qiu, R., Chen, J., Wang, L., Li, L., Tian, Y., Wang, H., Lu, Y., & Zhao, J. (2023). A Two-stage Method with a Shared 3D U-Net for Left Atrial Segmentation of Late Gadolinium-Enhanced MRI Images. Cardiovascular Innovations and Applications, 8(1). https://doi.org/ 10.15212/CVIA.2023.0039
  7. Chen, Z., Bai, J., & Lu, Y. (2023). Dilated convolution network with edge fusion block and directional feature maps for cardiac MRI segmentation. Frontiers in physiology, 14, 1027076. https://doi.org/10.3389/fphys.2023.1027076

Please sign in or register for FREE

If you are a registered user on Research Communities by Springer Nature, please sign in

Follow the Topic

Medical Imaging
Technology and Engineering > Biological and Physical Engineering > Biomedical Engineering and Bioengineering > Biomedical Devices and Instrumentation > Medical Imaging
Atrial Fibrillation
Life Sciences > Health Sciences > Clinical Medicine > Diseases > Cardiovascular Diseases > Arrhythmias > Atrial Fibrillation
Personalized Medicine
Life Sciences > Biological Sciences > Genetics and Genomics > Medical Genetics > Personalized Medicine
Artificial Intelligence
Mathematics and Computing > Computer Science > Artificial Intelligence
Computational Physics and Simulations
Physical Sciences > Physics and Astronomy > Theoretical, Mathematical and Computational Physics > Computational Physics and Simulations

Related Collections

With collections, you can get published faster and increase your visibility.

Epidemiological data

This Collection presents a series of articles describing epidemiological datasets spanning diverse populations, ecosystems, and disease contexts. Data are presented without hypotheses or significant analyses, and can be derived from population surveys, health registries, electronic health records, field sampling, or other sources.

Publishing Model: Open Access

Deadline: Dec 22, 2024

Metabolomics

This collection presents a series of articles describing metabolomics datasets, covering data from any organism type, collected via any valid metabolomic technique, and for any application.

Publishing Model: Open Access

Deadline: Nov 28, 2024