Publications

Selected publications from my research on neuroimaging biomarkers in ALS.

J. Neurology
2026
#### [Data-driven disease subgrouping in ALS: a multicenter cerebral functional connectivity study](https://doi.org/10.1007/s00415-026-13624-4) *Journal of Neurology* · 2026 · Co-Author Dey A, Baumeister TR, Evans KC, Koppelmans V, Luk C, McLaren DG, **Parnianpour P**, Seres P, Kalra S, Canadian ALS Neuroimaging Consortium. This multicenter study used functional connectivity data from CALSNIC to identify distinct ALS patient subgroups based on cerebral functional connectivity patterns, advancing our understanding of disease heterogeneity and supporting precision medicine approaches in ALS.
Ann. Neurology
2025
#### An individual-level MRI approach reveals corticospinal tract degeneration and its heterogeneity in ALS *Annals of Neurology* · 2025 · Co-Author · *(submitted)* Harrison M, Liu G, **Parnianpour P**, Dey A, Baumeister TR, Abrahao A, Dupre N, Genge A, Zinman L, CALSNIC, CAPTURE ALS, Kalra S. Using an individual-level analysis of MRI data, this study reveals heterogeneity in corticospinal tract degeneration across ALS patients -- an important step toward personalized imaging-based stratification in clinical trials.
AJNR
2025
#### [Progressive and short-interval changes observed in the corticospinal tract and corpus callosum of ALS patients: A texture analysis study](https://doi.org/10.3174/ajnr.A9013) *American Journal of Neuroradiology* · 2025 · **First Author** **Parnianpour P**, Harrison M, Benatar M, Briemberg H, Dionne A, Dupre N, Frayne R, Genge A, Graham SJ, Korngut L, Seres P, Wilman A, Zinman L, Kalra S, Canadian ALS Neuroimaging Consortium. Using standard T1-weighted MRI, we applied sectional texture analysis to track ALS-related changes over 4--8 months. We observed progressive degeneration starting asymmetrically in the right corticospinal tract, with corpus callosum changes emerging later -- correlated with upper motor neuron dysfunction.
Brain Comms
2024
#### [T1-weighted MRI texture analyses in ALS patients stratified by the D50 progression model](https://doi.org/10.1093/braincomms/fcae389) *Brain Communications* · 2024 · **First Author** **Parnianpour P**, Steinbach R, Buchholz IJ, Grosskreutz J, Kalra S. This study explores texture analysis on T1-weighted 1.5T MRI scans, stratifying ALS patients by disease severity using the D50 disease progression model. Our findings demonstrate that texture analysis can differentiate ALS progression stages, offering a promising biomarker applicable across MRI scanner strengths.
J. Neurology
2024
#### [Mismatch between clinically defined classification of ALS stage and the burden of cerebral pathology](https://doi.org/10.1007/s00415-024-12190-x) *Journal of Neurology* · 2024 · **First Author** **Parnianpour P**, Benatar M, Briemberg H, Dey A, Dionne A, Dupre N, Evans KC, Frayne R, Genge A, Graham SJ, Korngut L, McLaren DG, Seres P, Welsh RC, Wilman A, Zinman L, Kalra S. The traditional clinical staging of ALS does not accurately reflect the level of neurodegeneration. This study demonstrates the mismatch between clinical stage and cerebral pathology burden, arguing that imaging should be incorporated into disease stratification in clinical trials.
Sci. Reports
2023
#### [Accurate personalized survival prediction for amyotrophic lateral sclerosis patients](https://doi.org/10.1038/s41598-023-47935-7) *Scientific Reports* · 2023 · Co-Author Kuan LH, **Parnianpour P**, Kushol R, Kumar N, Anand T, Kalra S, Greiner R. A machine-learned tool that accurately predicts ALS patient survival time by integrating clinical features with cortical thickness data from brain MRI. Predictions are expressed as individual survival distributions (ISDs), giving probabilistic estimates at multiple future time points.
Sci. Reports
2023
#### [Effects of MRI scanner manufacturers in classification tasks with deep learning models](https://doi.org/10.1038/s41598-023-43715-5) *Scientific Reports* · 2023 · Co-Author Kushol R, **Parnianpour P**, Wilman AH, Kalra S, Yang YH. This study investigates domain shift in deep learning for multi-center MRI data across scanner manufacturers (GE, Philips, Siemens), evaluating harmonization strategies for robust classification in clinical neuroimaging pipelines.

PhD Thesis

MRI-Based Texture Analysis for Characterizing Cerebral Degeneration Progression in Amyotrophic Lateral Sclerosis

University of Alberta, 2024 · Supervisor: Dr. Sanjay Kalra

This thesis leverages MRI-based texture analysis to delineate cerebral degeneration progression in ALS: assessing gray and white matter changes by disease stage, detecting longitudinal cerebral changes, analyzing degeneration within specific neural tracts, and classifying ALS patients based on cerebral degeneration patterns.

Conference Abstracts

Podium Presentations

Poster Presentations