BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20181221T160904Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181115T083000
DTEND;TZID=America/Chicago:20181115T170000
UID:submissions.supercomputing.org_SC18_sess324_post177@linklings.com
SUMMARY:Convolutional Neural Networks for Coronary Plaque Classification i
 n Intravascular Optical Coherence Tomography (IVOCT) Images
DESCRIPTION:Poster\nTech Program Reg Pass, Exhibits Reg Pass\n\nConvolutio
 nal Neural Networks for Coronary Plaque Classification in Intravascular Op
 tical Coherence Tomography (IVOCT) Images\n\nKolluru, Prabhu, Gharaibeh, W
 ilson, Gajurel\n\nCurrently, IVOCT is the only imaging technique with the 
 resolution necessary to identify vulnerable thin cap fibro-atheromas (TCFA
 s). IVOCT also has greater penetration depth in calcified plaques as compa
 red to Intravascular Ultrasound (IVUS). Despite its advantages, IVOCT imag
 e interpretation is challenging and time consuming with over 500 images ge
 nerated in a single pullback. In this poster, we propose a method to autom
 atically classify A-lines in IVOCT images using a convolutional neural net
 work. Conditional random fields were used to clean network predictions acr
 oss frames. The neural network was trained using a dataset of nearly 4,500
  image frames across 48 IVOCT pullbacks. Ten-fold cross validation with he
 ld-out pullbacks resulted in a classification accuracy of roughly 76% for 
 fibrocalcific, 84% for fibrolipidic, and 85% for other. Classification res
 ults across frames displayed in en face view matched closely to annotated 
 counterparts.
URL:https://sc18.supercomputing.org/presentation/?id=post177&sess=sess324
END:VEVENT
END:VCALENDAR