Leveraging artificial intelligence for enhanced echocardiography: using machine learning for Congenital Heart Disease

dc.contributor.advisorNgoepe, Malebogo
dc.contributor.advisorMishra, Amit
dc.contributor.authorDzonzi, Brenald
dc.date.accessioned2026-11-16T12:57:49Z
dc.date.available2026-11-16T12:57:49Z
dc.date.issued2026
dc.date.updated2026-11-16T12:53:56Z
dc.description.abstractCoarctation of the aorta (CoA) is a congenital cardiovascular defect characterised by a focal narrowing of the descending aorta, resulting in elevated cardiac afterload and often necessitating lifelong haemodynamic surveillance. Although computational fluid dynamics (CFD) enables non-invasive assessment of pressure gradients and flow fields, its reliance on labour-intensive image segmentation, mesh generation, and substantial compute time limits its applicability for rapid parameter studies and routine clinical use, particularly in resource-constrained settings. Neural network surrogates offer a promising alternative by learning input–output mappings from CFD data at a fraction of the inference cost, yet the relative merits of physics informed versus purely data-driven architectures remain insufficiently characterised for patient-specific cardiovascular geometries. This dissertation benchmarks physics-informed neural networks (PINNs) against data-only deep neural networks (DNNs) as mesh-free surrogates for haemodynamic prediction in CoA, with evaluation on a patient-specific geometry from the PROTEA project at the University of Cape Town. A structured benchmark ladder of increasing physical complexity is employed: (i) analytic ordinary and partial differential equations (spring–mass system, two-dimensional Poisson equation) providing exact reference solutions; (ii) canonical laminar flows (planar Poiseuille and three-dimensional pipe flow); (iii) a parametric stenosis series with varying constriction severity; and (iv) a clinically derived CoA geometry with pulsatile inflow. Model families—supervised DNNs with optional random Fourier feature embeddings, physics-only PINNs, hybrid PINNs combining data and residual losses, and a signed-distance-function-augmented variant—are implemented in PyTorch and trained using automatic mixed precision, adaptive loss weighting, and reproducible multi-seed protocols. OpenFOAM supplies the ground-truth CFD datasets and boundary conditions throughout. Results demonstrate that physics constraints confer a substantial advantage under extreme data scarcity (the PINN achieves an 8.5× lower extrapolation error than the DNN at ten labelled points on the Poisson benchmark), but this benefit diminishes as labelled data increase. On the patient-specific CoA geometry, the baseline DNN and Fourier-enhanced DNN satisfy the adopted pressure-drop acceptance criterion (below 1% mean relative error) at both 50% and 100% data fractions, whereas the hybrid PINN exhibits systematic gradient imbalance between its data and physics objectives. Fourier feature embeddings deliver comparable accuracy to the baseline at one to two orders of magnitude lower training cost, representing the most favourable cost–accuracy trade-off observed. All models are validated against CFD rather than in-vivo measurements; clinical deployment would require subsequent catheterisation or four-dimensional flow MRI validation and multi-patient generalisation. This work establishes reproducible technical foundations—encompassing data generation, training, and post-processing pipelines—for neural-network-based haemodynamic surrogates in congenital heart disease, contributing toward the long-term goal of accessible, rapid cardiovascular assessment.
dc.identifier.apacitationDzonzi, B. (2026). <i>Leveraging artificial intelligence for enhanced echocardiography: using machine learning for Congenital Heart Disease</i>. (). University of Cape Town ,Faculty of Engineering and the Built Environment ,Department of Mechanical Engineering. Retrieved from http://hdl.handle.net/11427/43945en_ZA
dc.identifier.chicagocitationDzonzi, Brenald. <i>"Leveraging artificial intelligence for enhanced echocardiography: using machine learning for Congenital Heart Disease."</i> ., University of Cape Town ,Faculty of Engineering and the Built Environment ,Department of Mechanical Engineering, 2026. http://hdl.handle.net/11427/43945en_ZA
dc.identifier.citationDzonzi, B. 2026. Leveraging artificial intelligence for enhanced echocardiography: using machine learning for Congenital Heart Disease. . University of Cape Town ,Faculty of Engineering and the Built Environment ,Department of Mechanical Engineering. http://hdl.handle.net/11427/43945en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Dzonzi, Brenald AB - Coarctation of the aorta (CoA) is a congenital cardiovascular defect characterised by a focal narrowing of the descending aorta, resulting in elevated cardiac afterload and often necessitating lifelong haemodynamic surveillance. Although computational fluid dynamics (CFD) enables non-invasive assessment of pressure gradients and flow fields, its reliance on labour-intensive image segmentation, mesh generation, and substantial compute time limits its applicability for rapid parameter studies and routine clinical use, particularly in resource-constrained settings. Neural network surrogates offer a promising alternative by learning input–output mappings from CFD data at a fraction of the inference cost, yet the relative merits of physics informed versus purely data-driven architectures remain insufficiently characterised for patient-specific cardiovascular geometries. This dissertation benchmarks physics-informed neural networks (PINNs) against data-only deep neural networks (DNNs) as mesh-free surrogates for haemodynamic prediction in CoA, with evaluation on a patient-specific geometry from the PROTEA project at the University of Cape Town. A structured benchmark ladder of increasing physical complexity is employed: (i) analytic ordinary and partial differential equations (spring–mass system, two-dimensional Poisson equation) providing exact reference solutions; (ii) canonical laminar flows (planar Poiseuille and three-dimensional pipe flow); (iii) a parametric stenosis series with varying constriction severity; and (iv) a clinically derived CoA geometry with pulsatile inflow. Model families—supervised DNNs with optional random Fourier feature embeddings, physics-only PINNs, hybrid PINNs combining data and residual losses, and a signed-distance-function-augmented variant—are implemented in PyTorch and trained using automatic mixed precision, adaptive loss weighting, and reproducible multi-seed protocols. OpenFOAM supplies the ground-truth CFD datasets and boundary conditions throughout. Results demonstrate that physics constraints confer a substantial advantage under extreme data scarcity (the PINN achieves an 8.5× lower extrapolation error than the DNN at ten labelled points on the Poisson benchmark), but this benefit diminishes as labelled data increase. On the patient-specific CoA geometry, the baseline DNN and Fourier-enhanced DNN satisfy the adopted pressure-drop acceptance criterion (below 1% mean relative error) at both 50% and 100% data fractions, whereas the hybrid PINN exhibits systematic gradient imbalance between its data and physics objectives. Fourier feature embeddings deliver comparable accuracy to the baseline at one to two orders of magnitude lower training cost, representing the most favourable cost–accuracy trade-off observed. All models are validated against CFD rather than in-vivo measurements; clinical deployment would require subsequent catheterisation or four-dimensional flow MRI validation and multi-patient generalisation. This work establishes reproducible technical foundations—encompassing data generation, training, and post-processing pipelines—for neural-network-based haemodynamic surrogates in congenital heart disease, contributing toward the long-term goal of accessible, rapid cardiovascular assessment. DA - 2026 DB - OpenUCT DP - University of Cape Town KW - Engineering KW - Physics-informed neural networks KW - Computational fluid dynamics KW - Coarctation of the aorta KW - Surrogate modelling KW - Deep learning KW - Haemodynamics KW - Congenital heart disease LK - https://open.uct.ac.za PB - University of Cape Town PY - 2026 T1 - Leveraging artificial intelligence for enhanced echocardiography: using machine learning for Congenital Heart Disease TI - Leveraging artificial intelligence for enhanced echocardiography: using machine learning for Congenital Heart Disease UR - http://hdl.handle.net/11427/43945 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/43945
dc.identifier.vancouvercitationDzonzi B. Leveraging artificial intelligence for enhanced echocardiography: using machine learning for Congenital Heart Disease. []. University of Cape Town ,Faculty of Engineering and the Built Environment ,Department of Mechanical Engineering, 2026 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/43945en_ZA
dc.language.isoen
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Mechanical Engineering
dc.publisher.facultyFaculty of Engineering and the Built Environment
dc.publisher.institutionUniversity of Cape Town
dc.subjectEngineering
dc.subjectPhysics-informed neural networks
dc.subjectComputational fluid dynamics
dc.subjectCoarctation of the aorta
dc.subjectSurrogate modelling
dc.subjectDeep learning
dc.subjectHaemodynamics
dc.subjectCongenital heart disease
dc.titleLeveraging artificial intelligence for enhanced echocardiography: using machine learning for Congenital Heart Disease
dc.typeThesis / Dissertation
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMSc
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_ebe_2026_dzonzi brenald.pdf
Size:
57.57 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections