Monitoring morphometric drift in lifelong learning segmentation of the spinal cord
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914104659148800 |
|---|---|
| author | Karthik, Enamundram Naga Bédard, Sandrine Valošek, Jan Aigner, Christoph S. Bannier, Elise Bednařík, Josef Callot, Virginie Combes, Anna Curt, Armin David, Gergely Eippert, Falk Farner, Lynn Fehlings, Michael G Freund, Patrick Granberg, Tobias Granziera, Cristina Group, RHSCIR Network Imaging Horn, Ulrike Horák, Tomáš Humphreys, Suzanne Hupp, Markus Kerbrat, Anne Kinany, Nawal Kolind, Shannon Kudlička, Petr Lebret, Anna Lee, Lisa Eunyoung Mainero, Caterina Martin, Allan R. McGrath, Megan Nair, Govind O'Grady, Kristin P. Oh, Jiwon Ouellette, Russell Pfender, Nikolai Pfyffer, Dario Pradat, Pierre-François Prat, Alexandre Pravatà, Emanuele Reich, Daniel S. Ricchi, Ilaria Rotem-Kohavi, Naama Schading-Sassenhausen, Simon Seif, Maryam Smith, Andrew Smith, Seth A Sweeney, Grace Tam, Roger Traboulsee, Anthony Treaba, Constantina Andrada Tsagkas, Charidimos Vavasour, Zachary Van De Ville, Dimitri Weber II, Kenneth Arnold Chandar, Sarath Cohen-Adad, Julien |
| author_facet | Karthik, Enamundram Naga Bédard, Sandrine Valošek, Jan Aigner, Christoph S. Bannier, Elise Bednařík, Josef Callot, Virginie Combes, Anna Curt, Armin David, Gergely Eippert, Falk Farner, Lynn Fehlings, Michael G Freund, Patrick Granberg, Tobias Granziera, Cristina Group, RHSCIR Network Imaging Horn, Ulrike Horák, Tomáš Humphreys, Suzanne Hupp, Markus Kerbrat, Anne Kinany, Nawal Kolind, Shannon Kudlička, Petr Lebret, Anna Lee, Lisa Eunyoung Mainero, Caterina Martin, Allan R. McGrath, Megan Nair, Govind O'Grady, Kristin P. Oh, Jiwon Ouellette, Russell Pfender, Nikolai Pfyffer, Dario Pradat, Pierre-François Prat, Alexandre Pravatà, Emanuele Reich, Daniel S. Ricchi, Ilaria Rotem-Kohavi, Naama Schading-Sassenhausen, Simon Seif, Maryam Smith, Andrew Smith, Seth A Sweeney, Grace Tam, Roger Traboulsee, Anthony Treaba, Constantina Andrada Tsagkas, Charidimos Vavasour, Zachary Van De Ville, Dimitri Weber II, Kenneth Arnold Chandar, Sarath Cohen-Adad, Julien |
| contents | 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 code and model are open-source and accessible via Spinal Cord Toolbox v7.0. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Monitoring morphometric drift in lifelong learning segmentation of the spinal cord Karthik, Enamundram Naga Bédard, Sandrine Valošek, Jan Aigner, Christoph S. Bannier, Elise Bednařík, Josef Callot, Virginie Combes, Anna Curt, Armin David, Gergely Eippert, Falk Farner, Lynn Fehlings, Michael G Freund, Patrick Granberg, Tobias Granziera, Cristina Group, RHSCIR Network Imaging Horn, Ulrike Horák, Tomáš Humphreys, Suzanne Hupp, Markus Kerbrat, Anne Kinany, Nawal Kolind, Shannon Kudlička, Petr Lebret, Anna Lee, Lisa Eunyoung Mainero, Caterina Martin, Allan R. McGrath, Megan Nair, Govind O'Grady, Kristin P. Oh, Jiwon Ouellette, Russell Pfender, Nikolai Pfyffer, Dario Pradat, Pierre-François Prat, Alexandre Pravatà, Emanuele Reich, Daniel S. Ricchi, Ilaria Rotem-Kohavi, Naama Schading-Sassenhausen, Simon Seif, Maryam Smith, Andrew Smith, Seth A Sweeney, Grace Tam, Roger Traboulsee, Anthony Treaba, Constantina Andrada Tsagkas, Charidimos Vavasour, Zachary Van De Ville, Dimitri Weber II, Kenneth Arnold Chandar, Sarath Cohen-Adad, Julien Computer Vision and Pattern Recognition 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 code and model are open-source and accessible via Spinal Cord Toolbox v7.0. |
| title | Monitoring morphometric drift in lifelong learning segmentation of the spinal cord |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.01364 |