BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Automated Detection of Vascular Lesions in Fluorescein Angiography
  Retinal Images by Image Processing Methods
DTSTART;VALUE=DATE-TIME:20111107T113000Z
DTEND;VALUE=DATE-TIME:20111107T123000Z
DTSTAMP;VALUE=DATE-TIME:20260617T184755Z
UID:indico-event-1820@indico.ific.uv.es
DESCRIPTION:Early detection of microaneurysms (MAs)\, the first sign of Di
 abetic Retinopathy (DR)\, is an essential first step in automated detectio
 n of DR to prevent vision loss and blindness. This study presents a novel 
 and different algorithm for automatic detection of MAs in fluorescein angi
 ography fundus images\, based on Radon transform (RT) and multi-overlappin
 g windows. This project addresses a novel method\, in detection of retinal
  land marks and lesions to diagnose the DR. At the first step\, optic nerv
 e head (ONH) was detected and masked. In preprocessing stage\, top-hat tra
 nsformation and averaging filter were applied to remove the background. In
  main processing section\, firstly\, we divided the whole preprocessed ima
 ge into sub-images and then we segmented and masked the vascular tree by a
 pplying RT in each sub-image. After detecting and masking retinal vessels 
 and ONH\, MAs were detected and numbered by using RT and appropriated thre
 sholding. The results of the proposed method were evaluated reported on tw
 o different retinal images databases\, the Mashhad Database with 120 fluor
 escein angiography (FA) fundus images and Second Local Database from Tehra
 n with 50 FA retinal images. Automated DR detection demonstrated a sensiti
 vity and specificity of 94% and 75% for Mashhad database and 100% and 70% 
 for the Second Local Database respectively.\n\nhttps://indico.ific.uv.es/e
 vent/1820/
LOCATION:Nave experimental del IFIC Sala de Audiovisuales
URL:https://indico.ific.uv.es/event/1820/
END:VEVENT
END:VCALENDAR