🤖 AI Summary
Statistical shape models (SSMs) rely heavily on expert manual segmentation, incurring high annotation costs that hinder their clinical and research adoption.
Method: This work presents the first systematic evaluation of semi-supervised segmentation methods for SSM construction, establishing a performance benchmark tailored to morphological modeling. We integrate leading frameworks—including Mean Teacher, Unsupervised Data Augmentation (UDA), and FixMatch—with 3D medical images and an end-to-end SSM fitting pipeline, quantitatively assessing their ability to capture anatomical shape variation patterns.
Contribution/Results: With only 20–40% labeled data, multiple semi-supervised approaches reconstruct SSMs approaching full-supervision baseline accuracy, reducing annotation cost by 60–80%. We propose principled trade-off criteria between annotation efficiency and model fidelity, enabling scalable, low-resource morphological modeling. This establishes a novel paradigm for constructing clinically viable SSMs under data-scarce conditions.
📝 Abstract
Statistical Shape Models (SSMs) excel at identifying population level anatomical variations, which is at the core of various clinical and biomedical applications, including morphology-based diagnostics and surgical planning. However, the effectiveness of SSM is often constrained by the necessity for expert-driven manual segmentation, a process that is both time-intensive and expensive, thereby restricting their broader application and utility. Recent deep learning approaches enable the direct estimation of Statistical Shape Models (SSMs) from unsegmented images. While these models can predict SSMs without segmentation during deployment, they do not address the challenge of acquiring the manual annotations needed for training, particularly in resource-limited settings. Semi-supervised models for anatomy segmentation can mitigate the annotation burden. Yet, despite the abundance of available approaches, there are no established guidelines to inform end-users on their effectiveness for the downstream task of constructing SSMs. In this study, we systematically evaluate the potential of semi-supervised methods as viable alternatives to manual segmentations for building SSMs. We establish a new performance benchmark by employing various semi-supervised methods for anatomy segmentation under low annotation settings, utilizing the predicted segmentations for the task of SSM. Our results indicate that some methods produce noisy segmentation, which is very unfavorable for SSM tasks, while others can capture the correct modes of variations in the population cohort with 60-80% reduction in required manual annotation