# Self-Supervised Learning for Spinal MRIs

arXiv: https://arxiv.org/abs/1708.00367 · HTML: https://mlsanity.com/paper/1708.00367/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2017.

## Built on by (most cited first, 24 of 24)

- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [Self-supervised learning methods and applications in medical imaging analysis: A survey](https://mlsanity.com/paper/2109.08685/) (2021)
- [ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Genetics](https://mlsanity.com/paper/2111.13424/) (2021)
- [Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG Modeling](https://mlsanity.com/paper/2104.04569/) (2021)
- [Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes](https://mlsanity.com/paper/2403.16499/) (2024)
- [An Evaluation of Self-Supervised Pre-Training for Skin-Lesion Analysis](https://mlsanity.com/paper/2106.09229/) (2021)
- [A Review of Predictive and Contrastive Self-supervised Learning for Medical Images](https://mlsanity.com/paper/2302.05043/) (2023)
- [Context-Aware Transformers For Spinal Cancer Detection and Radiological Grading](https://mlsanity.com/paper/2206.13173/) (2022)
- [Self-Supervised Multi-Modal Alignment for Whole Body Medical Imaging](https://mlsanity.com/paper/2107.06652/) (2021)
- [Learning of Inter-Label Geometric Relationships Using Self-Supervised Learning: Application To Gleason Grade Segmentation](https://mlsanity.com/paper/2110.00404/) (2021)
- [X-Diffusion: Generating Detailed 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion Models](https://mlsanity.com/paper/2404.19604/) (2024)
- [Self-Supervised Learning for Segmentation](https://mlsanity.com/paper/2101.05456/) (2021)
- [UKBOB: One Billion MRI Labeled Masks for Generalizable 3D Medical Image Segmentation](https://mlsanity.com/paper/2504.06908/) (2025)
- [Self-Supervised U-Net for Segmenting Flat and Sessile Polyps](https://mlsanity.com/paper/2110.08776/) (2021)
- [Classification and Self-Supervised Regression of Arrhythmic ECG Signals Using Convolutional Neural Networks](https://mlsanity.com/paper/2210.14253/) (2022)
- [Knowing What to Label for Few Shot Microscopy Image Cell Segmentation](https://mlsanity.com/paper/2211.10244/) (2022)
- [A Survey of the Impact of Self-Supervised Pretraining for Diagnostic Tasks with Radiological Images](https://mlsanity.com/paper/2309.02555/) (2023)
- [A Positive/Unlabeled Approach for the Segmentation of Medical Sequences using Point-Wise Supervision](https://mlsanity.com/paper/2107.08394/) (2021)
- [Intelligent Masking: Deep Q-Learning for Context Encoding in Medical Image Analysis](https://mlsanity.com/paper/2203.13865/) (2022)
- [Unsupervised Feature Clustering Improves Contrastive Representation Learning for Medical Image Segmentation](https://mlsanity.com/paper/2211.08557/) (2022)
- [About Explicit Variance Minimization: Training Neural Networks for Medical Imaging With Limited Data Annotations](https://mlsanity.com/paper/2105.14117/) (2021)
- [Learning to segment with limited annotations: Self-supervised pretraining with regression and contrastive loss in MRI](https://mlsanity.com/paper/2205.13109/) (2022)
- [Multi-modal Masked Siamese Network Improves Chest X-Ray Representation Learning](https://mlsanity.com/paper/2407.04449/) (2024)
- [Task-Aligned Self-Supervised Learning for Medical Image Analysis: A Task-Oriented Review with Practical Design Guidelines](https://mlsanity.com/paper/2605.23995/) (2026)

## Abstract (arXiv)

A significant proportion of patients scanned in a clinical setting have follow-up scans. We show in this work that such longitudinal scans alone can be used as a form of 'free' self-supervision for training a deep network. We demonstrate this self-supervised learning for the case of T2-weighted sagittal lumbar Magnetic Resonance Images (MRIs). A Siamese convolutional neural network (CNN) is trained using two losses: (i) a contrastive loss on whether the scan is of the same person (i.e. longitudinal) or not, together with (ii) a classification loss on predicting the level of vertebral bodies. The performance of this pre-trained network is then assessed on a grading classification task. We experiment on a dataset of 1016 subjects, 423 possessing follow-up scans, with the end goal of learning the disc degeneration radiological gradings attached to the intervertebral discs. We show that the performance of the pre-trained CNN on the supervised classification task is (i) superior to that of a network trained from scratch; and (ii) requires far fewer annotated training samples to reach an equivalent performance to that of the network trained from scratch.