AI-Based Multi-View Echocardiographic Image Synthesis using Dynamic Shape Control
Authors: João Freitas, Anca Balinisteanu, Ahmed Youssef, Vitor Hugo Pereira, Jan D'hooge, Sandro Queirós
Organizations: Life and Health Sciences Research Institute, School of Medicine, University of Minho, Braga, Portugal · Department of Cardiovascular Sciences, KU Leuven, Leuven, Belgium · 2Ai - Applied Artificial Intelligence Laboratory, School of Technology, Polytechnic University of Cávado and Ave (UPCA), Barcelos, Portugal · Department of Cardiology and Cardiovascular Surgery, University of Medicine and Pharmacy ”Carol Davila”, Bucharest, Romania · Department of Cardiovascular Medicine, Suez Canal University, Ismailia, Egypt
Although automated methods have improved echocardiographic workflows, progress remains constrained by the need for large, well-annotated datasets. As the development of clinical databases is often limited by ethical and logistical challenges, synthetic data generation has emerged as a promising alternative. However, existing approaches commonly rely on left ventricle shape-based supervision or are tailored to specific cardiac views, limiting the generation of additional standard and unconventional imaging planes and the preservation of multi-view consistency across cardiac chambers. To address these limitations, we propose a novel framework for shape-controlled synthesis of multi-view echocardiographic sequences. First, multi-view cross-sections are extracted from dynamic whole-heart meshes. Ultrasound-like appearance is then introduced through a two-stage AI-based pipeline. In Stage 1, an unpaired GAN-diffusion model translates these cross-sections into realistic echocardiographic frames. As this translation is performed independently at the frame level, Stage 2 employs masked video reconstruction to improve temporal coherence and cardiac motion. Evaluation demonstrated high frame-level realism for both stages, while the integration of Stage 2 substantially improved video-level motion quality and temporal consistency. Overall, the proposed framework enables the generation of realistic multi-view echocardiographic sequences from diverse cardiac models, providing a scalable source of annotated data for dataset augmentation and the development of multi-view cardiac assessment methods.
Figures & tables
Fig. 1: Overview of the proposed framework for synthetic multi-view echocardiographic sequence generation.
Fig. 2: Qualitative and quantitative evaluation of the proposed framework. (A) Representative examples across different echocardiographic views, showing Stage 1 and Stage 2 outputs alongside the corresponding simulated anatomy. (B) Four consecutive frames with magnified regions highlighting improved valve and wall dynamics and reduced temporal artifacts after Stage 2. (C) View-averaged FID, SCL, TWE, and blinded reader-study results on the test set.
School of Biomedical Engineering, The University of British Columbia, Vancouver, BC V6T 1Z4, Canada · École polytechnique fédérale de Lausanne (EPFL), Lausanne, Switzerland · Faculty of Informatics and Data Science, University of Regensburg, 93053 Regensburg, Germany +8
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou, China · Systemes Complexes et Intelligence Artificielle, IMT Mines Ales, Ales, France · School of Artificial Intelligence and Advanced Computing, Xi’an Jiaotong-Liverpool University, Suzhou, China