BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
BEGIN:STANDARD
DTSTART:19451014T230000
TZOFFSETFROM:+0630
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241025T072620Z
UID:E3DE8E40-9C58-43CF-9602-FFD7294F0BDE
DTSTART;TZID=Asia/Kolkata:20241025T110000
DTEND;TZID=Asia/Kolkata:20241025T120000
DESCRIPTION:Retinal detachment (RD) is a severe disorder that leads to visi
 on loss\, although it can be highly treatable with prompt and appropriate 
 medical intervention. Early detection of RD can increase the probability o
 f successful reattachment and improve visual outcomes\, mainly before the 
 macular involvement. Manual screening of RD is tedious and laborious\, mak
 ing it challenging to implement on a wide scale of healthcare applications
 . Therefore\, an automated screening tool for early RD detection is very e
 ssential. This work proposes a novel multiclass RD grading framework using
  a Graph neural network (GNN) model. For this study\, the simple linear it
 erative clustering method has been employed\, which considers all samples\
 , training\, and testing samples as nodes and establishes a set of edges o
 r connections between them to form a graph structure. In addition\, three 
 graph neural networks\, namely the graph convolutional network\, GraphSAGE
 \, and graph attention network\, were used as feature extractors to learn 
 the graph's semantic relations and local-global features effectively. Fina
 lly\, an ensemble learning approach with a majority voting mechanism was u
 tilized to assign weights to the retrieved graph features\, leading to the
  final prediction.\n\nSpeaker(s): Dr. R. Murugan\, \n\nVirtual: https://ev
 ents.vtools.ieee.org/m/442009
LOCATION:Virtual: https://events.vtools.ieee.org/m/442009
ORGANIZER:ieee.embs.sbc.iitkgp@gmail.com
SEQUENCE:11
SUMMARY:Graph Neural Network for retinal detachment classification through 
 fundus images
URL;VALUE=URI:https://events.vtools.ieee.org/m/442009
X-ALT-DESC:Description: <br /><p>Retinal detachment (RD) is a severe disord
 er that leads to vision loss\, although it can be highly treatable with pr
 ompt and appropriate medical intervention. Early detection of RD can incre
 ase the probability of successful reattachment and improve visual outcomes
 \, mainly before the macular involvement. Manual screening of RD is tediou
 s and laborious\, making it challenging to implement on a wide scale of he
 althcare applications. Therefore\, an automated screening tool for early R
 D detection is very essential. This work proposes a novel multiclass RD gr
 ading framework using a Graph neural network (GNN) model. For this study\,
  the simple linear iterative clustering method has been employed\, which c
 onsiders all samples\, training\, and testing samples as nodes and establi
 shes a set of edges or connections between them to form a graph structure.
  In addition\, three graph neural networks\, namely the graph convolutiona
 l network\, GraphSAGE\, and graph attention network\, were used as feature
  extractors to learn the graph's semantic relations and local-global featu
 res effectively. Finally\, an ensemble learning approach with a majority v
 oting mechanism was utilized to assign weights to the retrieved graph feat
 ures\, leading to the final prediction.&nbsp\;</p>
END:VEVENT
END:VCALENDAR