Academic Journal
View in EDS

Mitigating the Impact of MR Sequence Parameters: Increasing the Robustness of DL-Based Cortical Thickness Estimates.

Bibliographic Details
Title: Mitigating the Impact of MR Sequence Parameters: Increasing the Robustness of DL-Based Cortical Thickness Estimates.
Authors: Blattner T; Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland., Romascano D; Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland., McKinley R; Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland., Rebsamen M; Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland.; Balgrist University Hospital, Zurich, Switzerland., Salmen A; Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland., Pistor M; Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland., Hoepner R; Department of Neurology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland., Wiest R; Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland.; Translational Imaging Center (TIC), Swiss Institute for Translational and Entrepreneurial Medicine, Sitem-Insel, Bern, Switzerland., Radojewski P; Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland.; Translational Imaging Center (TIC), Swiss Institute for Translational and Entrepreneurial Medicine, Sitem-Insel, Bern, Switzerland., Rummel C; Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland.; European Campus Rottal-Inn, Technische Hochschule Deggendorf, Pfarrkirchen, Germany., Capiglioni M; Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland.; High-Field MR Center, Max Planck Institute for Biological Cybernetics, Tübingen, Germany.
Source: Human brain mapping [Hum Brain Mapp] 2026 Jun 01; Vol. 47 (8), pp. e70560.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: Wiley Country of Publication: United States NLM ID: 9419065 Publication Model: Print Cited Medium: Internet ISSN: 1097-0193 (Electronic) Linking ISSN: 10659471 NLM ISO Abbreviation: Hum Brain Mapp Subsets: MEDLINE
Imprint Name(s): Publication: New York : Wiley
Original Publication: New York : Wiley-Liss, c1993-
MeSH Terms: Magnetic Resonance Imaging*/methods , Magnetic Resonance Imaging*/standards , Cerebral Cortex*/diagnostic imaging , Cerebral Cortex*/pathology , Multiple Sclerosis, Relapsing-Remitting*/diagnostic imaging , Multiple Sclerosis, Relapsing-Remitting*/pathology , Image Processing, Computer-Assisted*/methods , Image Processing, Computer-Assisted*/standards , Neuroimaging*/methods , Neuroimaging*/standards , Deep Learning* , Brain Cortical Thickness*, Atrophy/pathology ; Humans ; Female ; Male ; Adult ; Middle Aged
Abstract: Cortical thickness measurements from MRI are increasingly used as biomarkers for neurodegenerative disease progression. However, variations in MRI acquisition parameters, such as inversion time (TI) and repetition time (TR), which are common in clinical settings, can compromise the reliability and sensitivity of these measurements. We fine-tuned a deep-learning-based segmentation tool (DL+DiReCT) to reduce its dependence to image contrast variations by training it on simulated MPRAGE images derived from quantitative relaxation maps. Fine-tuning markedly reduced contrast sensitivity, with the Pearson correlation coefficient decreasing from INLINEMATH to INLINEMATH . Evaluation on a synthetic atrophy dataset demonstrated that our model accurately replicated atrophy trends with minimal underestimation, outperforming FreeSurfer and SynthSeg. When applied to a dataset of relapsing-remitting multiple sclerosis (RRMS) patients, the fine-tuned model showed a substantial reduction in contrast sensitivity and maintained stable performance after controlling for covariates such as age, sex, field strength, and Expanded Disability Status Scale (EDSS) score. Overall, the proposed approach achieves robust contrast invariance without sacrificing sensitivity to cortical atrophy, offering a practical improvement for longitudinal and multi-center clinical studies.
(© 2026 The Author(s). Human Brain Mapping published by Wiley Periodicals LLC.)
References: Alexander‐Bloch, A., L. Clasen, M. Stockman, et al. 2016. “Subtle In‐Scanner Motion Biases Automated Measurement of Brain Anatomy From In Vivo MRI.” Human Brain Mapping 37, no. 7: 2385–2397.
Alfaro‐Almagro, F., P. McCarthy, S. Afyouni, et al. 2021. “Confound Modelling in UK Biobank Brain Imaging.” NeuroImage 224: 117002.
Billot, B., D. N. Greve, O. Puonti, et al. 2023. “Synthseg: Segmentation of Brain MRI Scans of Any Contrast and Resolution Without Retraining.” Medical Image Analysis 86: 102789.
Blattner, T., R. McKinley, R. Wiest, C. Rummel, and M. Capiglioni. 2025. “Enhancing Reliability of MRI‐Based Brain Morphometry by Synthetic Mprage Generation.” In Proceedings of the Annual Meeting of the International Society for Magnetic Resonance in Medicine (ISMRM) (Program No. 4314). ISMRM.
Borges, P., R. Shaw, T. Varsavsky, et al. 2024. “Acquisition‐Invariant Brain MRI Segmentation With Informative Uncertainties.” Medical Image Analysis 92: 103058.
Borges, P., C. Sudre, T. Varsavsky, et al. 2019. “Physics‐Informed Brain MRI Segmentation.” Simulation and Synthesis in Medical Imaging: 4th International Workshop, SASHIMI 2019, Held in Conjunction With MICCAI 2019, Shenzhen, China, October 13, 2019, Proceedings 4, Springer. 100–109.
Clark, I. A., and E. A. Maguire. 2023b. “Release of Cognitive and Multimodal MRI Data Including Real‐World Tasks and Hippocampal Subfield Segmentations.” Scientific Data 10, no. 1: 540.
Das, S. R., B. B. Avants, M. Grossman, and J. C. Gee. 2009. “Registration Based Cortical Thickness Measurement.” NeuroImage 45, no. 3: 867–879.
De Stefano, N., L. Airas, N. Grigoriadis, et al. 2014. “Clinical Relevance of Brain Volume Measures in Multiple Sclerosis.” CNS Drugs 28: 147–156.
Deichmann, R., C. Good, O. Josephs, J. Ashburner, and R. Turner. 2000. “Optimization of 3‐d Mp‐Rage Sequences for Structural Brain Imaging.” NeuroImage 12, no. 1: 112–127.
Desikan, R. S., F. Ségonne, B. Fischl, et al. 2006. “An Automated Labeling System for Subdividing the Human Cerebral Cortex on MRI Scans Into Gyral Based Regions of Interest.” NeuroImage 31, no. 3: 968–980.
Dieckmeyer, M., A. G. Roy, J. Senapati, et al. 2021. “Effect of MRI Acquisition Acceleration via Compressed Sensing and Parallel Imaging on Brain Volumetry.” Magnetic Resonance Materials in Physics, Biology and Medicine 34: 487–497.
Duché, Q., H. Saint‐Jalmes, O. Acosta, et al. 2017. “Partial Volume Model for Brain MRI Scan Using MP2RAGE.” Human Brain Mapping 38, no. 10: 5115–5127.
Duning, T., S. Kloska, O. Steinstrater, H. Kugel, W. Heindel, and S. Knecht. 2005. “Dehydration Confounds the Assessment of Brain Atrophy.” Neurology 64, no. 3: 548–550.
Fischl, B. 2012. “Freesurfer.” NeuroImage 62, no. 2: 774–781.
Fischl, B., and A. M. Dale. 2000. “Measuring the Thickness of the Human Cerebral Cortex From Magnetic Resonance Images.” Proceedings of the National Academy of Sciences 97, no. 20: 11050–11055.
George, A., R. Kuzniecky, H. Rusinek, H. R. Pardoe, and H. E. P. Investigators. 2020. “Standardized Brain MRI Acquisition Protocols Improve Statistical Power in Multicenter Quantitative Morphometry Studies.” Journal of Neuroimaging 30, no. 1: 126–133.
Haller, S., P. Falkovskiy, R. Meuli, et al. 2016. “Basic Mr Sequence Parameters Systematically Bias Automated Brain Volume Estimation.” Neuroradiology 58: 1153–1160.
Han, X., J. Jovicich, D. Salat, et al. 2006. “Reliability of MRI‐Derived Measurements of Human Cerebral Cortical Thickness: The Effects of Field Strength, Scanner Upgrade and Manufacturer.” NeuroImage 32, no. 1: 180–194.
Hedges, E. P., M. Dimitrov, U. Zahid, et al. 2022. “Reliability of Structural MRI Measurements: The Effects of Scan Session, Head Tilt, Inter‐Scan Interval, Acquisition Sequence, Freesurfer Version and Processing Stream.” NeuroImage 246: 118751.
Hornak, J. P. 1996. The Basics of MRI. Rochester Institute of Technology.
Jenkinson, M., and S. Smith. 2001. “A Global Optimisation Method for Robust Affine Registration of Brain Images.” Medical Image Analysis 5, no. 2: 143–156.
Jovicich, J., M. Marizzoni, R. Sala‐Llonch, et al. 2013. “Brain Morphometry Reproducibility in Multi‐Center 3 T MRI Studies: A Comparison of Cross‐Sectional and Longitudinal Segmentations.” NeuroImage 83: 472–484.
Kappos, L., N. De Stefano, M. S. Freedman, et al. 2016. “Inclusion of Brain Volume Loss in a Revised Measure of ‘no Evidence of Disease Activity’(Neda‐4) in Relapsing–Remitting Multiple Sclerosis.” Multiple Sclerosis Journal 22, no. 10: 1297–1305.
Kruggel, F., J. Turner, L. T. Muftuler, et al. 2010. “Impact of Scanner Hardware and Imaging Protocol on Image Quality and Compartment Volume Precision in the Adni Cohort.” NeuroImage 49, no. 3: 2123–2133.
Lin, T.‐Y., P. Goyal, R. Girshick, K. He, and P. Dollár. 2017. “Focal Loss for Dense Object Detection.” In Proceedings of the IEEE International Conference on Computer Vision, 2980–2988. IEEE.
Mckinley, R., M. Rebsamen, R. Meier, M. Reyes, C. Rummel, and R. Wiest. 2019. “Few‐Shot Brain Segmentation From Weakly Labeled Data With Deep Heteroscedastic Multi‐Task Networks,” Preprint. arXiv. https://doi.org/10.48550/arXiv.1904.02436.
McKinley, R., R. Wepfer, F. Aschwanden, et al. 2021. “Simultaneous Lesion and Brain Segmentation in Multiple Sclerosis Using Deep Neural Networks.” Scientific Reports 11, no. 1: 1087.
McKinley, R., R. Wepfer, T. Gundersen, et al. 2016. “Nabla‐Net: A Deep Dag‐Like Convolutional Architecture for Biomedical Image Segmentation.” In International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, edited by B. Menze, M. Reyes, A. Crimi, O. Maier, S. Winzeck, and H. Handels, 119–128. Springer.
Narayana, P. A., K. A. Govindarajan, P. Goel, et al. 2013. “Regional Cortical Thickness in Relapsing Remitting Multiple Sclerosis: A Multi‐Center Study.” NeuroImage: Clinical 2: 120–131.
Panman, J. L., Y. Y. To, E. L. van der Ende, et al. 2019. “Bias Introduced by Multiple Head Coils in MRI Research: An 8 Channel and 32 Channel Coil Comparison.” Frontiers in Neuroscience 13: 729.
Pérez‐García, F., R. Sparks, and S. Ourselin. 2021. “Torchio: A Python Library for Efficient Loading, Preprocessing, Augmentation and Patch‐Based Sampling of Medical Images in Deep Learning.” Computer Methods and Programs in Biomedicine 208: 106236.
Posselt, C., M. Y. Avci, M. Yigitsoy, et al. 2024. “Simulation of Acquisition Shifts in t2 Weighted Fluid‐Attenuated Inversion Recovery Magnetic Resonance Images to Stress Test Artificial Intelligence Segmentation Networks.” Journal of Medical Imaging 11, no. 2: 024013.
Rebsamen, M., M. Capiglioni, R. Hoepner, et al. 2024. “Growing Importance of Brain Morphometry Analysis in the Clinical Routine: The Hidden Impact of MR Sequence Parameters.” Journal of Neuroradiology 51, no. 1: 5–9.
Rebsamen, M., R. McKinley, P. Radojewski, et al. 2023. “Reliable Brain Morphometry From Contrast‐Enhanced T1w‐MRI in Patients With Multiple Sclerosis.” Human Brain Mapping 44, no. 3: 970–979.
Rebsamen, M., D. Romascano, M. Capiglioni, R. Wiest, P. Radojewski, and C. Rummel. 2023. The Phantom of Bern: Repeated Scans of Two Volunteers With Eight Different Combinations of MR Sequence Parameters.” https://openneuro.org/datasets/ds004560/.
Rebsamen, M., C. Rummel, M. Reyes, R. Wiest, and R. McKinley. 2020. “Direct Cortical Thickness Estimation Using Deep Learning‐Based Anatomy Segmentation and Cortex Parcellation.” Human Brain Mapping 41, no. 17: 4804–4814.
Reuter, M., N. J. Schmansky, H. D. Rosas, and B. Fischl. 2012. “Within‐Subject Template Estimation for Unbiased Longitudinal Image Analysis.” NeuroImage 61, no. 4: 1402–1418.
Reuter, M., M. D. Tisdall, A. Qureshi, R. L. Buckner, A. J. van der Kouwe, and B. Fischl. 2015. “Head Motion During MRI Acquisition Reduces Gray Matter Volume and Thickness Estimates.” NeuroImage 107: 107–115.
Romascano, D., M. Rebsamen, P. Radojewski, et al. 2024. “Cortical Thickness and Grey‐Matter Volume Anomaly Detection in Individual MRI Scans: Comparison of Two Methods.” NeuroImage: Clinical 43: 103624.
Rummel, C., F. Aschwanden, R. McKinley, et al. 2018. “A Fully Automated Pipeline for Normative Atrophy in Patients With Neurodegenerative Disease.” Frontiers in Neurology 8: 727.
Rummel, C., N. Slavova, A. Seiler, et al. 2017. “Personalized Structural Image Analysis in Patients With Temporal Lobe Epilepsy.” Scientific Reports 7, no. 1: 10883.
Rusak, F., R. Santa Cruz, L. Lebrat, et al. 2021. “Synthetic Brain MRI Dataset for Testing of Cortical Thickness Estimation Methods.” https://data.csiro.au/collection/csiro:53241v1/.
Rusak, F., R. Santa Cruz, L. Lebrat, et al. 2022. “Quantifiable Brain Atrophy Synthesis for Benchmarking of Cortical Thickness Estimation Methods.” Medical Image Analysis 82: 102576.
Stanisz, G. J., E. E. Odrobina, J. Pun, et al. 2005. “T1, T2 Relaxation and Magnetization Transfer in Tissue at 3T.” Magnetic Resonance in Medicine: An Official Journal of the International Society for Magnetic Resonance in Medicine 54, no. 3: 507–512.
Tabelow, K., E. Balteau, J. Ashburner, et al. 2019. “HMRI—A Toolbox for Quantitative MRI in Neuroscience and Clinical Research.” NeuroImage 194: 191–210.
Trefler, A., N. Sadeghi, A. G. Thomas, C. Pierpaoli, C. I. Baker, and C. Thomas. 2016. “Impact of Time‐Of‐Day on Brain Morphometric Measures Derived From t1‐Weighted Magnetic Resonance Imaging.” NeuroImage 133: 41–52.
Uhr, V., I. Diaz, C. Rummel, and R. McKinley. 2025. “Exploring Robustness of Cortical Morphometry in the Presence of White Matter Lesions, Using Diffusion Models for Lesion Filling.” Preprint. arXiv. https://doi.org/10.48550/arXiv.2503.20571.
Walters, R., N. Fox, W. Crum, D. Taube, and D. Thomas. 2001. “Haemodialysis and Cerebral Oedema.” Nephron 87, no. 2: 143–147.
Weiner, M. W., D. P. Veitch, P. S. Aisen, et al. 2017. “The Alzheimer's Disease Neuroimaging Initiative 3: Continued Innovation for Clinical Trial Improvement.” Alzheimer's & Dementia 13, no. 5: 561–571.
Grant Information: 204593 United Kingdom WT_ Wellcome Trust
Contributed Indexing: Keywords: MR; brain morphometry; contrast; cortical thickness; deep learning; multiple sclerosis; robustness
Entry Date(s): Date Created: 20260608 Date Completed: 20260612 Latest Revision: 20260726
Update Code: 20260726
PubMed Central ID: PMC13243191
DOI: 10.1002/hbm.70560
PMID: 42252567
Database: MEDLINE
Description
ISSN:1097-0193
DOI:10.1002/hbm.70560