# Weakly Supervised Bayesian Shape Modeling from Unsegmented Medical Images

arXiv: https://arxiv.org/abs/2405.09697 · HTML: https://mlsanity.com/paper/2405.09697/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 15 May 2024.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [Concrete Dropout](https://mlsanity.com/paper/1705.07832/) (2017)
- [AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?](https://mlsanity.com/paper/2010.14808/) (2020)
- [On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks](https://mlsanity.com/paper/2203.09168/) (2022)
- [Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis](https://mlsanity.com/paper/2203.03311/) (2022)
- [Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignment](https://mlsanity.com/paper/2011.14723/) (2020)
- [DeepSSM: A Deep Learning Framework for Statistical Shape Modeling from Raw Images](https://mlsanity.com/paper/1810.00111/) (2018)
- [DeepSSM: A Blueprint for Image-to-Shape Deep Learning Models](https://mlsanity.com/paper/2110.07152/) (2021)
- [Uncertain-DeepSSM: From Images to Probabilistic Shape Models](https://mlsanity.com/paper/2007.06516/) (2020)
- [From Images to Probabilistic Anatomical Shapes: A Deep Variational Bottleneck Approach](https://mlsanity.com/paper/2205.06862/) (2022)
- [Point2SSM: Learning Morphological Variations of Anatomies from Point Cloud](https://mlsanity.com/paper/2305.14486/) (2023)
- [Mesh2SSM: From Surface Meshes to Statistical Shape Models of Anatomy](https://mlsanity.com/paper/2305.07805/) (2023)
- [Benchmarking off-the-shelf statistical shape modeling tools in clinical applications](https://mlsanity.com/paper/2009.02878/) (2020)
- [Fully Bayesian VIB-DeepSSM](https://mlsanity.com/paper/2305.05797/) (2023)
- [Uncertainty Quantification in CNN-Based Surface Prediction Using Shape Priors](https://mlsanity.com/paper/1807.11272/) (2018)
- [Can point cloud networks learn statistical shape models of anatomies?](https://mlsanity.com/paper/2305.05610/) (2023)
- [On the Necessity and Effectiveness of Learning the Prior of Variational Auto-Encoder](https://mlsanity.com/paper/1905.13452/) (2019)
- [Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentation](https://mlsanity.com/paper/2308.07506/) (2023)
- [SCorP: Statistics-Informed Dense Correspondence Prediction Directly from Unsegmented Medical Images](https://mlsanity.com/paper/2404.17967/) (2024)
- [VIB is Half Bayes](https://mlsanity.com/paper/2011.08711/) (2020)

## Built on by (most cited first, 4 of 4)

- [A Survey of Medical Point Cloud Shape Learning: Registration, Reconstruction and Variation](https://mlsanity.com/paper/2508.03057/) (2025)
- [On the Viability of Semi-Supervised Segmentation Methods for Statistical Shape Modeling](https://mlsanity.com/paper/2407.15260/) (2024)
- [Implicit Shape-Prior for Few-Shot Assisted 3D Segmentation](https://mlsanity.com/paper/2509.08580/) (2025)
- [MorphoFlow: Sparse-Supervised Generative Shape Modeling with Adaptive Latent Relevance](https://mlsanity.com/paper/2604.11636/) (2026)

## Abstract (arXiv)

Anatomical shape analysis plays a pivotal role in clinical research and hypothesis testing, where the relationship between form and function is paramount. Correspondence-based statistical shape modeling (SSM) facilitates population-level morphometrics but requires a cumbersome, potentially bias-inducing construction pipeline. Recent advancements in deep learning have streamlined this process in inference by providing SSM prediction directly from unsegmented medical images. However, the proposed approaches are fully supervised and require utilizing a traditional SSM construction pipeline to create training data, thus inheriting the associated burdens and limitations. To address these challenges, we introduce a weakly supervised deep learning approach to predict SSM from images using point cloud supervision. Specifically, we propose reducing the supervision associated with the state-of-the-art fully Bayesian variational information bottleneck DeepSSM (BVIB-DeepSSM) model. BVIB-DeepSSM is an effective, principled framework for predicting probabilistic anatomical shapes from images with quantification of both aleatoric and epistemic uncertainties. Whereas the original BVIB-DeepSSM method requires strong supervision in the form of ground truth correspondence points, the proposed approach utilizes weak supervision via point cloud surface representations, which are more readily obtainable. Furthermore, the proposed approach learns correspondence in a completely data-driven manner without prior assumptions about the expected variability in shape cohort. Our experiments demonstrate that this approach yields similar accuracy and uncertainty estimation to the fully supervised scenario while substantially enhancing the feasibility of model training for SSM construction.