Cardiac MRI segmentation improved for rare single ventricle defects
SV-Cine: Diagnosis-Conditioned Segmentation of Single Ventricle Physiology via Generative Data Augmentation
Computer Vision and Pattern Recognition
Summary
Single ventricle heart defects are rare and different in each patient, which makes it hard for computers to understand MRI images of their hearts. The authors created a new way to generate more heart images to teach computers, and they built a smarter system that understands the type of heart defect a patient has when analyzing images. Their system did better than previous methods at identifying and measuring parts of the heart in these patients. This helps doctors by providing more accurate information from MRI scans despite limited real patient data.
What this means in practice
- •For clinical imaging teams: Use diagnosis-aware MRI segmentation to improve analysis of single ventricle heart defects in clinical workflows.
- •For medical device developers: Incorporate diagnosis-conditioned segmentation into cardiac imaging products to enhance rare heart defect assessment.$Commercial implications: It enables development of advanced imaging software for congenital heart disease diagnostics, supporting better treatment planning.
Authors
Lila Cunge, Yuehong Liu, Hang Xu, Thomas Coudert, Pierangelo Renella, J Paul Finn, William Hsu, Kim-Lien Nguyen
Abstract
Single Ventricle Physiology (SVP) is a rare subtype of congenital heart disease characterized by the presence of a single functional cardiac ventricle with atypical anatomic configurations that challenge conventional image segmentation approaches. The scarcity of clinical data and the morphological diversity across SVP subtypes make the development of robust segmentation methods particularly difficult. To address these limitations, we propose a cardiac MRI segmentation framework focused on ventricular chambers and myocardium segmentation tailored for SVP. First, we introduce a data augmentation pipeline that generates synthetic 3D cardiac meshes using SDF4CHD and corresponding synthetic cardiac MRI through generative modeling. Second, we introduce SV-Cine, a diagnosis-conditioned adaptation of the foundation model CineMA that incorporates patient-level diagnostic information through Feature-wise Linear Modulation layers, enabling diagnosis-aware feature adaptation during segmentation. We evaluated the framework on an internal cohort with varying SVP subtypes. SV-Cine achieved median Dice scores of 0.89 (IQR: 0.80--0.91) for the left ventricle and 0.72 (IQR: 0.54--0.84) for the right ventricle, outperforming the strongest baseline, nnU-Net, by 0.39 Dice points on right ventricle segmentation. It also yields a median ejection fraction error of 5.55 percentage points (IQR: 3.41--7.69) for the dominant ventricle. Compared with the internal cohort, LV and myocardium segmentation performance was lower for the external cohort; whereas RV Dice scores were comparable for both cohorts. Our findings suggest that a pretrained foundation model can be adapted for highly specialized downstream tasks through usage of diagnosis priors while leveraging anatomic knowledge learned from large-scale MRI datasets during pretraining.