BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//linuxsoftware.nz//NONSGML Joyous v1.4//EN
BEGIN:VEVENT
SUMMARY:DeepPlanner4Cardio: An automatic multi-view planning tool for Card
 iac MRI
DTSTART:20241128T103000Z
DTEND:20241128T123000Z
DTSTAMP:20260630T053705Z
UID:cb088489-939a-45fc-8538-eccec4e9907b
SEQUENCE:2
CREATED:20241123T145323Z
DESCRIPTION:Cardiac magnetic resonance imaging (Cardiac MRI) is an ionizin
 g radiation-free medical imaging technology used to monitor the function a
 nd structure of the cardiovascular system. Its disadvantage is that it’s
  a lengthy exam\, demanding high levels of patient cooperation\, and can t
 ake up to an hour\, depending on the operator’s skill. A time-consuming 
 element is the planning of the four standard cardiac views (2-chamber\, 3-
 chamber\, 4-chamber\, short axis) needed for obtaining cardiac volumes and
  other measurements essential for a precise diagnosis. As cardiovascular d
 iseases (CVDs) are the leading cause of death globally\, simplifying and a
 utomating parts of the Cardiac MR exam is vital for accessibility. Manual 
 cardiac view planning is a multi-step process customized for the patient
 ’s anatomy and subject to operator variability. Deep learning (DL) is ra
 pidly advancing in the medical field and has been proposed to address this
 \; however\, previous DL-based methods rely on extensive manual annotation
 s and involve multiple models.This thesis builds on DeepCardioPlanner\, a 
 single-view planning DL tool. We proposed DeepPlanner4Cardio\, a multi-vie
 w DL model predicting four cardiac views simultaneously from low-resolutio
 n 3D Cardiac MRI by leveraging inter-view relationships\, reducing computa
 tional demands\, and improving scalability. DeepPlanner4Cardio trains in u
 nder 3 minutes\, a significant improvement over models requiring up to 19 
 hours. Two Cardiac MRI experts evaluated the planning accuracy of DeepPlan
 ner4Cardio\, confirming its clinical relevance with 67.5% accurate predict
 ions and 26.5% acceptable ones. This fully automated tool offers a faster\
 , more accessible solution for Cardiac MRI planning.
LAST-MODIFIED:20241123T145622Z
LOCATION:DF Seminar Room (2-8.3)\, 2nd floor of Physics Building/Online  (
 Password: 041022)
URL:http://df.vps.tecnico.ulisboa.pt/pt/eventos/deepplanner4cardio-an-auto
 matic-multi-view-planning-tool-for-cardiac-mri/
X-ALT-DESC;FMTTYPE=text/html:<p data-block-key="nl097">Cardiac magnetic re
 sonance imaging (Cardiac MRI) is an ionizing radiation-free medical imagin
 g technology used to monitor the function and structure of the cardiovascu
 lar system. Its disadvantage is that it’s a lengthy exam\, demanding hig
 h levels of patient cooperation\, and can take up to an hour\, depending o
 n the operator’s skill. A time-consuming element is the planning of the 
 four standard cardiac views (2-chamber\, 3-chamber\, 4-chamber\, short axi
 s) needed for obtaining cardiac volumes and other measurements essential f
 or a precise diagnosis.<br/><br/> As cardiovascular diseases (CVDs) are th
 e leading cause of death globally\, simplifying and automating parts of th
 e Cardiac MR exam is vital for accessibility. Manual cardiac view planning
  is a multi-step process customized for the patient’s anatomy and subjec
 t to operator variability. Deep learning (DL) is rapidly advancing in the 
 medical field and has been proposed to address this\; however\, previous D
 L-based methods rely on extensive manual annotations and involve multiple 
 models.<br/></p><p data-block-key="2rjr9">This thesis builds on DeepCardio
 Planner\, a single-view planning DL tool. We proposed DeepPlanner4Cardio\,
  a multi-view DL model predicting four cardiac views simultaneously from l
 ow-resolution 3D Cardiac MRI by leveraging inter-view relationships\, redu
 cing computational demands\, and improving scalability.<br/><br/> DeepPlan
 ner4Cardio trains in under 3 minutes\, a significant improvement over mode
 ls requiring up to 19 hours. Two Cardiac MRI experts evaluated the plannin
 g accuracy of DeepPlanner4Cardio\, confirming its clinical relevance with 
 67.5% accurate predictions and 26.5% acceptable ones. This fully automated
  tool offers a faster\, more accessible solution for Cardiac MRI planning.
 </p>
END:VEVENT
END:VCALENDAR