Towards contrast-agnostic soft segmentation of the spinal cord

Abstract

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 ($\text{n}=267$; $\text{contrasts}=6$), 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.

arXiv commentRevision Submitted to Medical Image Analysis

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Domain Adaptation for Medical Image Analysis: A Survey
• When Does Label Smoothing Help?
• SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining
• A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis
• MONAI: An open-source framework for deep learning in healthcare
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
• A Learning Strategy for Contrast-agnostic MRI Segmentation
• Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentation
• Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation