On the Viability of Semi-Supervised Segmentation Methods for Statistical Shape Modeling

TL;DR

This paper evaluates semi-supervised segmentation methods for constructing statistical shape models, demonstrating that some approaches can significantly reduce manual annotation needs while maintaining model quality.

Contribution

It provides a systematic benchmark of semi-supervised segmentation techniques for SSM construction, highlighting their potential and limitations in low annotation scenarios.

Findings

Some methods produce noisy segmentations unsuitable for SSM.

Certain approaches capture population variation modes with 60-80% less manual annotation.

Established a new benchmark for semi-supervised SSM construction.

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