# ADASSM: Adversarial Data Augmentation in Statistical Shape Models From Images

arXiv: https://arxiv.org/abs/2307.03273 · HTML: https://mlsanity.com/paper/2307.03273/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 6 Jul 2023.

## Builds on (most cited first, 15 of 15)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [C-Mixup: Improving Generalization in Regression](https://mlsanity.com/paper/2210.05775/) (2022)
- [How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization](https://mlsanity.com/paper/2210.06441/) (2022)
- [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)
- [Automatic Data Augmentation for 3D Medical Image Segmentation](https://mlsanity.com/paper/2010.11695/) (2020)
- [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)
- [Fully Bayesian VIB-DeepSSM](https://mlsanity.com/paper/2305.05797/) (2023)
- [Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training](https://mlsanity.com/paper/2103.16493/) (2021)
- [Uncertainty Quantification in CNN-Based Surface Prediction Using Shape Priors](https://mlsanity.com/paper/1807.11272/) (2018)
- [Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions](https://mlsanity.com/paper/2305.11946/) (2023)
- [Deep Learning for End-to-End Atrial Fibrillation Recurrence Estimation](https://mlsanity.com/paper/1810.00475/) (2018)

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

- [StainDiffuser: MultiTask Dual Diffusion Model for Virtual Staining](https://mlsanity.com/paper/2403.11340/) (2024)
- [SCorP: Statistics-Informed Dense Correspondence Prediction Directly from Unsegmented Medical Images](https://mlsanity.com/paper/2404.17967/) (2024)
- [MASSM: An End-to-End Deep Learning Framework for Multi-Anatomy Statistical Shape Modeling Directly From Images](https://mlsanity.com/paper/2403.11008/) (2024)
- [On the Viability of Semi-Supervised Segmentation Methods for Statistical Shape Modeling](https://mlsanity.com/paper/2407.15260/) (2024)

## Abstract (arXiv)

Statistical shape models (SSM) have been well-established as an excellent tool for identifying variations in the morphology of anatomy across the underlying population. Shape models use consistent shape representation across all the samples in a given cohort, which helps to compare shapes and identify the variations that can detect pathologies and help in formulating treatment plans. In medical imaging, computing these shape representations from CT/MRI scans requires time-intensive preprocessing operations, including but not limited to anatomy segmentation annotations, registration, and texture denoising. Deep learning models have demonstrated exceptional capabilities in learning shape representations directly from volumetric images, giving rise to highly effective and efficient Image-to-SSM networks. Nevertheless, these models are data-hungry and due to the limited availability of medical data, deep learning models tend to overfit. Offline data augmentation techniques, that use kernel density estimation based (KDE) methods for generating shape-augmented samples, have successfully aided Image-to-SSM networks in achieving comparable accuracy to traditional SSM methods. However, these augmentation methods focus on shape augmentation, whereas deep learning models exhibit image-based texture bias resulting in sub-optimal models. This paper introduces a novel strategy for on-the-fly data augmentation for the Image-to-SSM framework by leveraging data-dependent noise generation or texture augmentation. The proposed framework is trained as an adversary to the Image-to-SSM network, augmenting diverse and challenging noisy samples. Our approach achieves improved accuracy by encouraging the model to focus on the underlying geometry rather than relying solely on pixel values.