# Semixup: In- and Out-of-Manifold Regularization for Deep Semi-Supervised Knee Osteoarthritis Severity Grading from Plain Radiographs

arXiv: https://arxiv.org/abs/2003.01944 · HTML: https://mlsanity.com/paper/2003.01944/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2020.

## Built on by (most cited first, 8 of 8)

- [CLIMAT: Clinically-Inspired Multi-Agent Transformers for Knee Osteoarthritis Trajectory Forecasting](https://mlsanity.com/paper/2104.03642/) (2021)
- [Multimodal Prototype Alignment for Semi-supervised Pathology Image Segmentation](https://mlsanity.com/paper/2508.19574/) (2025)
- [H-SemiS: Hierarchical Fusion of Semi and Self-Supervised Learning for Knee Osteoarthritis Severity Grading](https://mlsanity.com/paper/2604.23335/) (2026)
- [Improving Image Classification of Knee Radiographs: An Automated Image Labeling Approach](https://mlsanity.com/paper/2309.02681/) (2023)
- [Identity-Consistent Diffusion Network for Grading Knee Osteoarthritis Progression in Radiographic Imaging](https://mlsanity.com/paper/2407.21381/) (2024)
- [Toward Cost-efficient Adaptive Clinical Trials in Knee Osteoarthritis with Reinforcement Learning](https://mlsanity.com/paper/2408.02349/) (2024)
- [Transforming Precision: A Comparative Analysis of Vision Transformers, CNNs, and Traditional ML for Knee Osteoarthritis Severity Diagnosis](https://mlsanity.com/paper/2410.20062/) (2024)
- [Morphology-Aware KOA Classification: Integrating Graph Priors with Vision Models](https://mlsanity.com/paper/2510.21801/) (2025)

## Abstract (arXiv)

Knee osteoarthritis (OA) is one of the highest disability factors in the world. This musculoskeletal disorder is assessed from clinical symptoms, and typically confirmed via radiographic assessment. This visual assessment done by a radiologist requires experience, and suffers from moderate to high inter-observer variability. The recent literature has shown that deep learning methods can reliably perform the OA severity assessment according to the gold standard Kellgren-Lawrence (KL) grading system. However, these methods require large amounts of labeled data, which are costly to obtain. In this study, we propose the Semixup algorithm, a semi-supervised learning (SSL) approach to leverage unlabeled data. Semixup relies on consistency regularization using in- and out-of-manifold samples, together with interpolated consistency. On an independent test set, our method significantly outperformed other state-of-the-art SSL methods in most cases. Finally, when compared to a well-tuned fully supervised baseline that yielded a balanced accuracy (BA) of 70.9±0.8% on the test set, Semixup had comparable performance -- BA of 71±0.8% (p=0.368) while requiring 6 times less labeled data. These results show that our proposed SSL method allows building fully automatic OA severity assessment tools with datasets that are available outside research settings.