Using Foundation Models as Pseudo-Label Generators for Pre-Clinical 4D Cardiac CT Segmentation
This work addresses the limited segmentation capabilities for pre-clinical porcine cardiac imaging, which is important for cardiac analysis and modeling tasks, but it is incremental as it builds on existing foundation models and self-training methods.
The paper tackled the problem of segmenting pre-clinical 4D cardiac CT images in porcine models, where domain shift from human data complicates direct model transfer, by using foundation models as pseudo-label generators and a self-training approach to iteratively refine labels without manual annotations, resulting in enhanced segmentation accuracy and smoothed temporal inconsistencies across frames.
Cardiac image segmentation is an important step in many cardiac image analysis and modeling tasks such as motion tracking or simulations of cardiac mechanics. While deep learning has greatly advanced segmentation in clinical settings, there is limited work on pre-clinical imaging, notably in porcine models, which are often used due to their anatomical and physiological similarity to humans. However, differences between species create a domain shift that complicates direct model transfer from human to pig data. Recently, foundation models trained on large human datasets have shown promise for robust medical image segmentation; yet their applicability to porcine data remains largely unexplored. In this work, we investigate whether foundation models can generate sufficiently accurate pseudo-labels for pig cardiac CT and propose a simple self-training approach to iteratively refine these labels. Our method requires no manually annotated pig data, relying instead on iterative updates to improve segmentation quality. We demonstrate that this self-training process not only enhances segmentation accuracy but also smooths out temporal inconsistencies across consecutive frames. Although our results are encouraging, there remains room for improvement, for example by incorporating more sophisticated self-training strategies and by exploring additional foundation models and other cardiac imaging technologies.