Monitoring morphometric drift in lifelong learning segmentation of the spinal cord

2025-05-02

AI Summary

This work addresses the challenge of real-time monitoring of morphometric drift during iterative updates of spinal cord segmentation models. We propose the first automated morphological drift monitoring framework specifically designed for spinal cord segmentation. Methodologically, we develop a multi-center U-Net variant capable of generalizing across nine MRI contrasts and diverse pathologies, integrated with lifelong learning and continuous integration (via GitHub Actions) to enable automated model versioning and temporal quantification of key morphometric metrics—including cross-sectional area and cord length. Our key contribution lies in extending model monitoring beyond conventional performance evaluation to anatomical stability validation. On challenging lumbar cases, the model achieves a Dice score of 0.95 ± 0.03. Drift detection is rapid and robust: scaling factors calibrated on the database exhibit a coefficient of variation <2.1% across vertebral levels, substantially improving the reliability of clinical reference-value modeling.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Life-Long and Continual Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Morphometric measures derived from spinal cord segmentations can serve as diagnostic and prognostic biomarkers in neurological diseases and injuries affecting the spinal cord. While robust, automatic segmentation methods to a wide variety of contrasts and pathologies have been developed over the past few years, whether their predictions are stable as the model is updated using new datasets has not been assessed. This is particularly important for deriving normative values from healthy participants. In this study, we present a spinal cord segmentation model trained on a multisite $(n=75)$ dataset, including 9 different MRI contrasts and several spinal cord pathologies. We also introduce a lifelong learning framework to automatically monitor the morphometric drift as the model is updated using additional datasets. The framework is triggered by an automatic GitHub Actions workflow every time a new model is created, recording the morphometric values derived from the model's predictions over time. As a real-world application of the proposed framework, we employed the spinal cord segmentation model to update a recently-introduced normative database of healthy participants containing commonly used measures of spinal cord morphometry. Results showed that: (i) our model outperforms previous versions and pathology-specific models on challenging lumbar spinal cord cases, achieving an average Dice score of $0.95 pm 0.03$; (ii) the automatic workflow for monitoring morphometric drift provides a quick feedback loop for developing future segmentation models; and (iii) the scaling factor required to update the database of morphometric measures is nearly constant among slices across the given vertebral levels, showing minimum drift between the current and previous versions of the model monitored by the framework. The model is freely available in Spinal Cord Toolbox v7.0.

Problem

• Assessing stability of spinal cord segmentation models during updates
• Monitoring morphometric drift in lifelong learning segmentation frameworks
• Updating normative databases with consistent spinal cord morphometric measures

Innovation

• Multisite MRI dataset with diverse contrasts and pathologies
• Lifelong learning framework monitors morphometric drift
• Automatic GitHub Actions workflow triggers model updates