Back to all papers

Deep learning-based cortical thickness maps for diagnosis of neurodegenerative diseases: a rater study.

August 25, 2026pubmed logopapers

Authors

Riedel EO,Bongratz F,Zott B,Berberich C,Eichinger P,Yakushev I,Grimmer T,Wachinger C,Hedderich DM

Affiliations (5)

  • Department of Neuroradiology School of Medicine and Health, TUM Klinikum Rechts der Isar, Technical University of Munich Munich Germany.
  • Department of Radiology School of Medicine and Health, TUM Klinikum Rechts der Isar, Technical University of Munich Munich Germany.
  • Munich Center for Machine Learning Munich Germany.
  • Department of Nuclear Medicine School of Medicine and Health, TUM Klinikum Rechts der Isar, Technical University of Munich Munich Germany.
  • Department of Neurology School of Medicine and Health, TUM Klinikum Rechts der Isar, Technical University of Munich Munich Germany.

Abstract

Cortical atrophy patterns on magnetic resonance imaging (MRI) are essential for diagnosing neurodegenerative diseases (NDs), but remain challenging to assess visually. Deep learning enables quantitative evaluation of cortical thickness (CTh) and z-score maps. 3T three-dimensional T1 MRI from 40 ND patients (Alzheimer's dementia, posterior cortical atrophy, behavioral variant frontotemporal dementia, semantic variant primary progressive aphasia) and 10 controls were retrospectively analyzed. Cortical surfaces were extracted with FreeSurfer and registered to fsaverage, and z-score maps were generated using stochastic cortical self-reconstruction (SCSR). Three neuroradiologists rated CTh or z-score maps, each with or without 3D T1 for ND presence and differential diagnosis. Conventional 3D T1 served as baseline reading condition. Diagnostic accuracy (Acc) was quantitatively highest for z-score maps with 3D T1 (Acc = 0.98) for the detection of ND, though it did not reach statistical significance. However, diagnostic confidence improved for z-score maps versus baseline 3D T1 (adjusted <i>p =</i> 0.017 for Rater 2). Inter-rater agreement improved from <i>κ =</i> 0.525 (baseline 3D T1) to <i>κ =</i> 0.792 (z-score with 3D T1). SCSR-generated z-score maps show promise for diagnostic evaluation of ND.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.