BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Iceland//AI Centre//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:1ff15adc-781e-4f74-8340-fed65effa32e@ai.hi.is
DTSTAMP:20261011T043454Z
DTSTART:20260317T090000Z
DTEND:20260317T100000Z
SUMMARY:A deep learning-based image processing pipeline for deep-brain stru
 ctures: Application to atypical Parkinsonian disorders
DESCRIPTION:Early diagnosis of atypical Parkinsonian disorders (APD) remain
 s a major clinical challenge due to overlapping symptoms with Parkinson’
 s disease (PD). Segmentation of deep-brain structures from MRI may provide
  supportive imaging biomarkers. Here we present a fully automated\, deep l
 earning–based image processing pipeline to support differential diagnosi
 s of APD. A region-based U-net segments 12 deep-brain structures by dividi
 ng MRI volumes into anatomically targeted regions\, thereby reducing GPU d
 emands and training time while maintaining competitive segmentation accura
 cy. Segmentation masks and volumetric features are then combined with T1-w
 eighted MRI in a hybrid classification framework to explore subtype differ
 entiation in APD. The proposed approach provides a computational framework
  that may contribute to improved differential classification of APD.\n\nht
 tps://ai.hi.is/is/events/colloquium-in-statistics-and-ai-15/
LOCATION:Íslensk erfðagreining\, Tjarnarsalur
URL:https://ai.hi.is/is/events/colloquium-in-statistics-and-ai-15/
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR