# Towards contrast-agnostic soft segmentation of the spinal cord

arXiv: https://arxiv.org/abs/2310.15402 · HTML: https://mlsanity.com/paper/2310.15402/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 55 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 30 of 30)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1910.02923/) (2019)
- [Data augmentation using learned transformations for one-shot medical image segmentation](https://mlsanity.com/paper/1902.09383/) (2019)
- [Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression](https://mlsanity.com/paper/1904.07399/) (2019)
- [Unsupervised domain adaptation in brain lesion segmentation with adversarial networks](https://mlsanity.com/paper/1612.08894/) (2016)
- [Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization](https://mlsanity.com/paper/2009.12829/) (2020)
- [Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/1901.08211/) (2019)
- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [Learning to predict crisp boundaries](https://mlsanity.com/paper/1807.10097/) (2018)
- [Source-Free Domain Adaptation for Image Segmentation](https://mlsanity.com/paper/2108.03152/) (2021)
- [Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2211.14805/) (2022)
- [A Learning Strategy for Contrast-agnostic MRI Segmentation](https://mlsanity.com/paper/2003.01995/) (2020)
- [SoftSeg: Advantages of soft versus binary training for image segmentation](https://mlsanity.com/paper/2011.09041/) (2020)
- [Partial Volume Segmentation of Brain MRI Scans of any Resolution and Contrast](https://mlsanity.com/paper/2004.10221/) (2020)
- [Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks](https://mlsanity.com/paper/1805.06349/) (2018)
- [Optimization with soft Dice can lead to a volumetric bias](https://mlsanity.com/paper/1911.02278/) (2019)
- [Automatically Segmenting the Left Atrium from Cardiac Images Using Successive 3D U-Nets and a Contour Loss](https://mlsanity.com/paper/1812.02518/) (2018)
- [Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation](https://mlsanity.com/paper/2304.02720/) (2023)
- [Penalizing small errors using an Adaptive Logarithmic Loss](https://mlsanity.com/paper/1910.09717/) (2019)

## Built on by (most cited first, 2 of 2)

- [Rootlets-based registration to the spinal cord PAM50 template](https://mlsanity.com/paper/2505.00115/) (2025)
- [Monitoring morphometric drift in lifelong learning segmentation of the spinal cord](https://mlsanity.com/paper/2505.01364/) (2025)

## Abstract (arXiv)

Spinal cord segmentation is clinically relevant and is notably used to compute spinal cord cross-sectional area (CSA) for the diagnosis and monitoring of cord compression or neurodegenerative diseases such as multiple sclerosis. While several semi and automatic methods exist, one key limitation remains: the segmentation depends on the MRI contrast, resulting in different CSA across contrasts. This is partly due to the varying appearance of the boundary between the spinal cord and the cerebrospinal fluid that depends on the sequence and acquisition parameters. This contrast-sensitive CSA adds variability in multi-center studies where protocols can vary, reducing the sensitivity to detect subtle atrophies. Moreover, existing methods enhance the CSA variability by training one model per contrast, while also producing binary masks that do not account for partial volume effects. In this work, we present a deep learning-based method that produces soft segmentations of the spinal cord. Using the Spine Generic Public Database of healthy participants (n=267; contrasts=6), we first generated participant-wise soft ground truth (GT) by averaging the binary segmentations across all 6 contrasts. These soft GT, along with aggressive data augmentation and a regression-based loss function, were used to train a U-Net model for spinal cord segmentation. We evaluated our model against state-of-the-art methods and performed ablation studies involving different loss functions and domain generalization methods. Our results show that using the soft segmentations along with a regression loss function reduces CSA variability (p < 0.05, Wilcoxon signed-rank test). The proposed spinal cord segmentation model generalizes better than the state-of-the-art methods amongst unseen datasets, vendors, contrasts, and pathologies (compression, lesions), while accounting for partial volume effects.