{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:59:11Z","timestamp":1790312351527,"version":"4.1.0"},"reference-count":37,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Najran University","award":["NU\/GP\/MRC\/14\/3155-1"],"award-info":[{"award-number":["NU\/GP\/MRC\/14\/3155-1"]}],"id":[{"id":"https:\/\/ror.org\/05edw4a90","id-type":"ROR","asserted-by":"crossref"}]},{"award":["NU\/GP\/MRC\/14\/3155-1"],"award-info":[{"award-number":["NU\/GP\/MRC\/14\/3155-1"]}],"id":[{"id":"https:\/\/ror.org\/05edw4a90","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Tomography"],"abstract":"<jats:p>Background: Cardiac MRI analysis typically treats segmentation, biomarker estimation, and disease classification as separate problems, even though clinical biomarkers are themselves derived from segmentation masks and diagnosis depends on both. This paper investigates whether a single jointly trained network can perform all three tasks without sacrificing accuracy on any of them. Methods: I propose CardioSynergyNet, which is a multi-task network with a weight-shared encoder for end-diastolic (ED) and end-systolic (ES) frames. Three modules link the tasks: Cross-Phase Deformation Attention (CPDA) models ED\u2013ES deformation, a Differentiable Biomarker Extraction Layer (DBEL) computes eight clinical biomarkers directly from the soft segmentation mask, and Class-Conditional Prototype Feedback (CCPF) conditions segmentation on the predicted disease class. The model was trained and tested on 150 patients (30 per class across five diagnostic groups), who were split patient-wise into 110\/20\/20 train\/validation\/test, yielding 1489 paired ED\/ES slices. Results: On the test set, the model achieved a mean ED Dice score of 0.905 (computed across all four classes, including background), with the right ventricle being the hardest structure, particularly at ES. Biomarker regression was accurate for area- and mass-based quantities (R &gt; 0.92) but weaker for ratio-based biomarkers such as ejection fraction (R = 0.66). Disease classification reached 76.65% accuracy with most confusions occurring between clinically similar disease pairs. Conclusions: The joint training of segmentation, biomarker extraction, and classification achieves performance competitive with task-specific models while keeping outputs across tasks consistent with one another, supporting cross-task feedback as a viable direction for integrated cardiac MRI analysis.<\/jats:p>","DOI":"10.3390\/tomography12090137","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:12:09Z","timestamp":1789999929000},"page":"137","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CardioSynergyNet: A Closed-Loop Multi-Task Deep Learning Architecture for Cardiac Segmentation and Biomarkers with Diagnosis from Paired ED-ES Cine-MRI"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3354-5018","authenticated-orcid":false,"given":"Saeed","family":"Alqahtani","sequence":"first","affiliation":[{"name":"Radiological Sciences Department, College of Applied Medical Sciences, Najran University, Najran 61441, Saudi Arabia"},{"name":"Health Research Center, Najran University, Najran 61441, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Alnasser, T.N., Abdulaal, L., Maiter, A., Sharkey, M., Dwivedi, K., Salehi, M., Garg, P., Swift, A.J., and Alabed, S. (2024). Advancements in cardiac structures segmentation: A comprehensive systematic review of deep learning in CT imaging. Front. Cardiovasc. Med., 11.","DOI":"10.3389\/fcvm.2024.1323461"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Xu, W., Shi, J., Lin, Y., Liu, C., Xie, W., Liu, H., Huang, S., Zhu, D., Su, L., and Huang, Y. (2023). Deep learning-based image segmentation model using an MRI-based convolutional neural network for physiological evaluation of the heart. Front. Physiol., 14.","DOI":"10.3389\/fphys.2023.1148717"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3754","DOI":"10.1038\/s41598-024-54164-z","article-title":"Assessment of deep learning segmentation for real-time free-breathing cardiac magnetic resonance imaging at rest and under exercise stress","volume":"14","author":"Schilling","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_4","first-page":"100083","article-title":"Deep neural network architectures for cardiac image segmentation","volume":"4","author":"Cabrera","year":"2023","journal-title":"Artif. Intell. Life Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4208231","DOI":"10.1155\/2023\/4208231","article-title":"An overview of deep learning methods for left ventricle segmentation","volume":"2023","author":"Shoaib","year":"2023","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Geroski, T., Filipovi\u0107, N., and Amini, A. (2025). Segmentation of ACDC challenge cardiac MRI dataset across diverse neural network architectures. Proceedings of the Medical Imaging 2025: Clinical and Biomedical Imaging, SPIE. Available online: https:\/\/www.spiedigitallibrary.org\/conference-proceedings-of-spie\/13410\/0000\/Segmentation-of-ACDC-challenge-cardiac-MRI-dataset-across-diverse-neural\/10.1117\/12.3049100.short.","DOI":"10.1117\/12.3049100"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cai, S., Lu, Y., Li, B., Gao, Q., Xu, L., Hu, X., and Zhang, L. (2023). Segmentation of cardiac tissues and organs for CCTA images based on a deep learning model. Front. Phys., 11.","DOI":"10.3389\/fphy.2023.1266500"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102528","DOI":"10.1016\/j.media.2022.102528","article-title":"Cardiac segmentation on late gadolinium enhancement MRI: A benchmark study from multi-sequence cardiac MR segmentation challenge","volume":"81","author":"Zhuang","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"102360","DOI":"10.1016\/j.media.2022.102360","article-title":"Medical image analysis on left atrial LGE MRI for atrial fibrillation studies: A review","volume":"77","author":"Li","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e28539","DOI":"10.1016\/j.heliyon.2024.e28539","article-title":"Usformer: A small network for left atrium segmentation of 3D LGE MRI","volume":"10","author":"Lin","year":"2024","journal-title":"Heliyon"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Wang, Z., Wang, X., Wang, K., Yuan, Y., and Li, Q. (2024). A novel network with enhanced edge information for left atrium segmentation from LGE-MRI. Front. Physiol., 15.","DOI":"10.3389\/fphys.2024.1478347"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102303","DOI":"10.1016\/j.media.2021.102303","article-title":"AtrialJSQnet: A new framework for joint segmentation and quantification of left atrium and scars incorporating spatial and shape information","volume":"76","author":"Li","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"105782","DOI":"10.1016\/j.compbiomed.2022.105782","article-title":"Cardiac segmentation on CT images through shape-aware contour attentions","volume":"147","author":"Park","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1186\/s44348-025-00058-1","article-title":"Deep learning models for segmentation and quantification of left atrial appendage volume using noncontrast cardiac computed tomography","volume":"33","author":"Zhuang","year":"2025","journal-title":"J. Cardiovasc. Imaging"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1109\/TMI.2022.3142321","article-title":"A fully automated multimodal MRI-based multi-task learning for glioma segmentation and IDH genotyping","volume":"41","author":"Cheng","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"102383","DOI":"10.1016\/j.media.2022.102383","article-title":"Atlas-ISTN: Joint segmentation, registration and atlas construction with image-and-spatial transformer networks","volume":"78","author":"Sinclair","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"102682","DOI":"10.1016\/j.media.2022.102682","article-title":"Generative myocardial motion tracking via latent space exploration with biomechanics-informed prior","volume":"83","author":"Qin","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"102811","DOI":"10.1016\/j.media.2023.102811","article-title":"Anatomically constrained and attention-guided deep feature fusion for joint segmentation and deformable medical image registration","volume":"88","author":"Khor","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, W., Hu, X., Wang, W., Cui, X., Li, B., and Li, Y. (2026). UniCarSeg: A Unified Framework for Multi-task Cardiac Image Segmentation, Springer. Available online: https:\/\/link.springer.com\/chapter\/10.1007\/978-3-032-16271-7_16.","DOI":"10.1007\/978-3-032-16271-7_16"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"106496","DOI":"10.1016\/j.compbiomed.2022.106496","article-title":"Multi-task deep learning for medical image computing and analysis: A review","volume":"153","author":"Zhao","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Brahim, K., Arega, T.W., Boucher, A., Bricq, S., Sakly, A., and Meriaudeau, F. (2022). An improved 3D deep learning-based segmentation of left ventricular myocardial diseases from delayed-enhancement MRI with inclusion and classification prior information U-Net (ICPIU-Net). Sensors, 22.","DOI":"10.3390\/s22062084"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.media.2018.10.004","article-title":"Fully convolutional multi-scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers","volume":"51","author":"Khened","year":"2019","journal-title":"Med. Image Anal."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1007\/s40846-023-00794-z","article-title":"Automatic left ventricle segmentation from short-axis MRI images using U-Net with study of the papillary muscles\u2019 removal effect","volume":"43","author":"Baccouch","year":"2023","journal-title":"J. Med. Biol. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"107679","DOI":"10.1016\/j.cmpb.2023.107679","article-title":"Fully automatic initialization and segmentation of left and right ventricles for large-scale cardiac MRI using a deeply supervised network and 3D-ASM","volume":"240","author":"Hu","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Elizar, E., Muharar, R., and Zulkifley, M.A. (2024). DeSPPNet: A multiscale deep learning model for cardiac segmentation. Diagnostics, 14.","DOI":"10.3390\/diagnostics14242820"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kumari, V., Katiyar, A., Bhagawati, M., Maindarkar, M., Gupta, S., Paul, S., Chhabra, T., Boi, A., Tiwari, E., and Rathore, V. (2025). Transformer and attention-based architectures for segmentation of coronary arterial walls in intravascular ultrasound: A narrative review. Diagnostics, 15.","DOI":"10.3390\/diagnostics15070848"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"102685","DOI":"10.1016\/j.media.2022.102685","article-title":"One model is all you need: Multi-task learning enables simultaneous histology image segmentation and classification","volume":"83","author":"Graham","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"102652","DOI":"10.1016\/j.media.2022.102652","article-title":"A semi-supervised multi-task learning framework for cancer classification with weak annotation in whole-slide images","volume":"83","author":"Gao","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Guo, Y., Cai, Y.H., Xu, T., Song, X.Y., Guo, H.X., Dong, M., Ni, D., Li, H., Wang, F., and Xue, W.F. (2025). Echocardiographic video-driven multi-task learning model for coronary artery disease diagnosis and severity grading. Front. Bioeng. Biotechnol., 13.","DOI":"10.3389\/fbioe.2025.1556748"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3642","DOI":"10.1109\/TBME.2025.3574090","article-title":"Deep separable spatiotemporal learning for fast dynamic cardiac MRI","volume":"72","author":"Wang","year":"2025","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"116704","DOI":"10.1016\/j.eswa.2022.116704","article-title":"A cascade approach for automatic segmentation of cardiac structures in short-axis cine-MR images using deep neural networks","volume":"197","author":"Silva","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"e004211","DOI":"10.1136\/openhrt-2026-004211","article-title":"AI-enhanced electrocardiography as a digital biomarker platform in cardiovascular medicine: Clinical applications, validation gaps and future implementation pathways","volume":"13","author":"Venturiello","year":"2026","journal-title":"Open Heart"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Elizar, E., Rizki, F., Muharar, R., Roslidar, R., Afnan, A., and Yunidar, Y. (2025). GAN-Assisted Deep Learning for Automated Cardiac MRI Segmentation: A Comparative Study with SegNet Baselines. Proceedings of the 2025 3rd International Conference on Computer System, Information Technology, and Electrical Engineering (COSITE), IEEE.","DOI":"10.1109\/COSITE68330.2025.11414415"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Xiao, X., Dong, S., Yu, Y., Li, Y., Yang, G., and Qiu, Z. (2023). MAE-TransRNet: An improved transformer-ConvNet architecture with masked autoencoder for cardiac MRI registration. Front. Med., 10.","DOI":"10.3389\/fmed.2023.1114571"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Vesal, S., Maier, A., and Ravikumar, N. (2020). Fully automated 3D cardiac MRI localisation and segmentation using deep neural networks. J. Imaging, 6.","DOI":"10.3390\/jimaging6070065"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"14565","DOI":"10.1038\/s41598-025-97779-6","article-title":"Medical image segmentation by combining feature enhancement Swin Transformer and UperNet","volume":"15","author":"Zhang","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lina, D., Johar, M.G.M., and Alkawaz, M.H. (2026). Application of attention-driven semi-supervised medical image segmentation model in cardiac image segmentation. International Conference on Knowledge Innovation and Invention, Springer. Lecture Notes in Electrical Engineering.","DOI":"10.1007\/978-981-95-2113-5_4"}],"container-title":["Tomography"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2379-139X\/12\/9\/137\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:10:47Z","timestamp":1790309447000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2379-139X\/12\/9\/137"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":37,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["tomography12090137"],"URL":"https:\/\/doi.org\/10.3390\/tomography12090137","relation":{},"ISSN":["2379-139X"],"issn-type":[{"value":"2379-139X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]}}}