BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//labri.fr//NONSGML kigkonsult.se iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:3f9b6c8b-2a5b-47ba-8318-848f05da362f
X-WR-CALNAME:Cross-modal Swin Transformer for computer-assisted diagnosis o
 f age-related macular degeneration
X-WR-TIMEZONE:Europe/Paris
BEGIN:VTIMEZONE
TZID:Europe/Paris
TZUNTIL:20260329T010000Z
BEGIN:STANDARD
TZNAME:CET
DTSTART:20231029T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20241027T030000
RDATE:20251026T030000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:CEST
DTSTART:20240331T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RDATE:20250330T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:3f9b6c8b-2a5b-47ba-8318-848f05da362f
DTSTAMP:20260510T232231Z
CLASS:PUBLIC
DESCRIPTION:Age-related macular degeneration (AMD) is one of the leading ca
 uses of legal blindness worldwide. However\, manual screening of the retin
 a for diagnosis is impractical for large populations\,and computer-assiste
 d diagnosis models provide a scalable alternative. Existing approaches oft
 en rely on a single imaging modality\, overlooking modality-specific infor
 mation\, and typically depend on single or few curated datasets that do no
 t reflect real-world clinical variability\, resulting in poor generalizati
 on. To address these challenges\, we introduce a cross-modal Swin-Transfor
 mer model that integrates optical coherence tomography (OCT) and color fun
 dus photography (CFP) for AMD diagnosis. This model focuses on one key bio
 marker and use multi-label classification. Our approach leverages a meta-d
 ataset compiled from international sources\, including both labeled and un
 labeled data. The model is trained through a two-stage process: first usin
 g a self-supervised multimodal pretraining method based on Barlow's Twins\
 , followed by fine-tuning with loose pairing and spatially-limited cross a
 ttention with 2.5D integration. Experimental results demonstrate that this
  approach improve classification metrics over baseline.\n
DTSTART;TZID=Europe/Paris:20240620T130000
DTEND;TZID=Europe/Paris:20240620T140000
LOCATION:Salle 76
SEQUENCE:0
SUMMARY:Cross-modal Swin Transformer for computer-assisted diagnosis of age
 -related macular degeneration
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR
