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 SSMs is often constrained by the necessity for expert-driven manual segmentation, a time-intensive and expensive process that restricts their broader utility. While deep learning approaches can estimate SSMs directly from unsegmented images, they still require segmentation annotations for SSM training. Although segmentations are unnecessary during deployment, the challenge of acquiring training manual annotations remains. Semi-supervised anatomical segmentation offers a promising solution to the annotation burden by leveraging a small labeled dataset alongside abundant unlabeled images. However, its effectiveness for downstream statistical shape model (SSM) construction remains largely unexplored. In this study, we systematically evaluate semi-supervised methods as alternatives to manual segmentation under low-annotation settings, using their predicted segmentations to construct SSMs and establish a comprehensive performance benchmark. Our findings reveal a clear divide in performance: while certain methods yield noisy segmentations that degrade SSM quality, others accurately capture the population’s modes of variation comparable to those obtained from manual-segmentation SSMs despite a 60-80% reduction in manual annotation requirements. GitHub repository: https://github.com/asmakhans/weaklyssm_shapeMI
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/ShapeMI_009.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=ZIb4veC2oG
BibTex
@InProceedings{KhaAsm_On_MICCAISAT2026,
author = { Khan, Asma AND Kataria, Tushar AND Ukey, Janmesh AND Elhabian, Shireen Y.},
title = { { On the Viability of Semi-Supervised Segmentation Methods for Statistical Shape Modeling } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17259},
month = {pending},
page = {pending}
}
