Evaluating SynthSR for MRI harmonization and quantitative analysis of hippocampal volume in autoimmune neurologic diseases

Variability in acquisition protocols limit the use of retrospective clinical magnetic resonance imaging (MRI) for quantitative analysis. SynthSR is an AI tool that harmonizes heterogeneous brain scans into synthetic 1-mm isotropic structural images. We evaluated SynthSR performance in autoimmune encephalitis (AE) and mimics.

This multicentre study included 102 patients from the Australian Autoimmune Encephalitis Consortium, and 28 controls, comparing high-resolution reference standard T1-weighted structural scans against low-resolution (n = 27) or contrast-enhanced counterparts (n = 76), with one patient having both. Images were processed via SynthSR, with hippocampal volume measured using FastSurfer. SynthSR processing systematically overestimated hippocampal volume, with high inter-individual variability.

Nevertheless, relative consistency between SynthSR-processed and original reference standard remained high (ICC = 0.88, 95% CI 0.74–0.94). Contrast enhancement did not substantially alter performance, but inclusion may require caution. While agreement between synthetic images derived from low-resolution scans and reference standard was moderate (ICC = 0.75, 95% CI 0.36–0.90), agreement with SynthSR-processed reference standard was excellent (ICC = 0.90, 95% CI 0.76–0.96).

Longitudinally, no statistically significant difference in volumetric change was detected, although wide limits of agreement indicated substantial individual-level variability. SynthSR facilitates harmonization of heterogeneous MRI for group-level volumetric analyses, provided a consistent processing pipeline is maintained. However, it is not reliable for individual-level patient assessments.

This study was supported by the Medical Research Future Fund (MRFF; MRF2030667). Department of Neuroscience, School of Translational Medicine, Monash University, The Alfred Centre, Level 6, 99 Commercial Road, Melbourne, VIC, 3004, Australia Nabil Seery, Ella Rowsthorn, Robb Wesselingh, Tiffany Rushen, Lucy Vivash, Paul Sanfilippo, Helmut Butzkueven, Ian H. Harding & Mastura Monif Department of Neurology, Alfred Health, Melbourne, Australia Nabil Seery, Robb Wesselingh, Helmut Butzkueven & Mastura Monif Department of Radiology, Alfred Health, Melbourne, Australia Adil Zia, Paul Beech, Helen Kavnoudias & Meng Law Department of Radiology, Monash Health, Melbourne, Australia Department of Surgery, Monash School of Medicine, Nursing and Health Sciences, Clayton, VIC, Australia Department of Neuroscience, Monash School of Medicine, Nursing and Health Sciences, Clayton, VIC, Australia Department of Electrical and Computer Systems Engineering, Monash School of Medicine, Nursing and Health Sciences, Clayton, VIC, Australia QIMR Berghofer Medical Research Institute, 300 Herston Road, Herston, Brisbane, QLD, 4006, Australia P.

Beech – nothing to declare H. Butzkueven is an employee of Monash University and has accepted travel compensation from Merck; his institution receives honoraria for talks, steering committee activities, and research grants from Roche, Merck, Biogen, Novartis, and UCB Pharma, Medical Research Future Fund Australia, NHMRC Australia, Trish MS Foundation, MS Australia and the Pennycook Foundation. He receives personal compensation for steering group activities for the Brain Health Initiative from Oxford Health Policy Forum and is funded by an NHMRC Australia Investigator Grant.