Monitoring morphometric drift in lifelong learning segmentation of the spinal cord

100%

Research Article

Imaging Neuroscience

Monitoring morphometric drift in lifelong learning segmentation of the spinal cord

ABSTRACT

Morphometric measures derived from spinal cord segmentations can serve as diagnostic and prognostic biomarkers in neurological diseases and injuries affecting the spinal cord. For instance, the spinal cord cross-sectional area can be used to monitor cord atrophy in multiple sclerosis and to characterize compression in degenerative cervical myelopathy. 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 dataset, including nine 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 performs well compared with its previous versions and existing pathology-specific models on the lumbar spinal cord, images with severe compression, and in the presence of intramedullary lesions and/or atrophy achieving an average Dice score of zero point nine five zero point zero three; (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 code and model are open source and accessible via Spinal Cord Toolbox version seven point zero.

One. INTRODUCTION

Two. MATERIALS AND METHODS

Two point one point one. Data and participants

Two point one point two. Generating ground-truth masks

Two point two. Training protocol

Two point two point two. Network architecture and training hyperparameters

Two point three. Lifelong learning for morphometric drift monitoring

Two point four. Validation protocol

Two point four point two. Evaluation of segmentations on various contrasts and pathologies

Two point four point three. Quantitative evaluation of morphometric drift

Two point four point four. Ablation study with recursively generated GT spinal cord masks

Two point four point five. Updating the normative database of spinal cord morphometrics

Two point four point six. Statistical analysis

Three. RESULTS

Three point one point one. Qualitative comparison of segmentations

Three point one point two. Quantitative evaluation on healthy controls and pathologies

Three point two. Quantitative evaluation of morphometric drift across model versions

Three point two point two. CSA variability with recursively generated GT masks

Three point two point three. Normative database results

Four. DISCUSSION

Four point one. Data curation

Four point two. Lifelong learning segmentation of the spinal cord

Four point two point two. Automatic monitoring of morphometric drift

Four point two point three. Training on recursively generated labels

Four point two point four. Binary versus soft masks

Four point three. Application on normative database of morphometrics

Four point four. Limitations

Five. CONCLUSION

DATA AND CODE AVAILABILITY

AUTHOR CONTRIBUTIONS

ETHICS

DECLARATION OF COMPETING INTEREST

Overview

The study presents a novel spinal cord segmentation approach that utilizes a lifelong learning framework to reliably monitor morphometric drift in spinal cord segmentations. Through a multi-site dataset and an automatic workflow, it aims to improve the accuracy of diagnostic metrics used in neurological diseases.

Key Points

1The spinal cord segmentation model is trained on a diverse dataset from 75 sites globally
2The lifelong learning framework enables continuous monitoring of morphometric drift
3The model successfully updates a normative database of morphometric measures
4Results indicate stability in the model's performance across various pathologies
5The methodology incorporates automatic workflows to enhance segmentation processes.

Details

Authors: Enamundram Naga Karthik, Sandrine Bédard, Jan Valošek
Category: Biology and Natural Sciences

PDF
Preserved topography, lateralization, selectivity, and functional connectivity of the language network in older brains
This study investigates the structural and functional changes in the language network of older adults compared to younger individuals using precision fMRI techniques. It focuses on how these changes affect language processing and executive functions in relation to healthy aging.
PDF
Evolutionary associations among pollen scopa structure, floral breadth and eusociality in Halictidae (Hymenoptera: Apoidea)
This paper explores the evolutionary relationships between pollen scopa structure, floral breadth, and eusociality in Halictidae bees through a comparative analysis of 207 species. The research aims to uncover the ecological and morphological factors influencing social behavior among these bees.
PDF
On the Origin of Mitosing Cells
This paper presents a theory on the origin of eukaryotic cells, proposing that certain organelles, like mitochondria and plastids, originated from free-living prokaryotic cells through a series of endosymbiotic events.
PDF
Architects of Order: The History & Evolution of Biological Taxonomy
This document explores the history and evolution of biological taxonomy, detailing key figures and their contributions to the classification of life forms from ancient times to the pre-Linnaean period.
PDF
Novel molecular requirements for CRISPR RNA-guided transposition
This study investigates the molecular requirements for CRISPR RNA-guided transposition, revealing novel sequence determinants and interactions necessary for DNA integration by CRISPR-associated transposases (CASTs).