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:20230124T171523Z
LOCATION:D222
DTSTART;TZID=America/Chicago:20221113T110000
DTEND;TZID=America/Chicago:20221113T111500
UID:submissions.supercomputing.org_SC22_sess432_ws_cafcws102@linklings.com
SUMMARY:Machine Learning in 4DCT Lung Stereotactic Body Radiotherapy (SBRT
 ) Treatment Planning
DESCRIPTION:Workshop\n\nMachine Learning in 4DCT Lung Stereotactic Body Ra
 diotherapy (SBRT) Treatment Planning\n\nGonzalez, Bartol, Taylor, Dhabaan,
  Khan...\n\nThe current project seeks to enhance current 4DCTlung cancer p
 atient image processing, image guidance, and adaptive radiotherapy verific
 ation through the integration of machine learning (Artificial Intelligence
  - AI) methods in an existing clinical radiation oncology framework. The c
 urrent state-of-the-art for Lung SBRT treatment planning begins with the a
 ccurate delineation of target organ volumes and their surrounding structur
 es, which is usually done using semi-automatic methods, mixing computer-as
 sisted tools, and dedicated physicians. When it comes to 4DCT scans, what 
 is usually done is to compute a visual average of the images across the di
 fferent respiratory phases and the contours for those organs (in one speci
 fic phase) are delineated. In the last few years, deformable image registr
 ation (DIR) techniques have been developed and used in this field to propa
 gate the contour delineation from one specific phase to the rest of the re
 spiratory phases in the CT. Results of the target region delineation are t
 hen used by physicians and clinicians to select an optimal treatment phase
 . Rather than the mostly manual and slow/iterative process introduced abov
 e, our current project seeks to create more accurate and more robust delin
 eations through improved machine learning models, decreasing time spent pe
 r patient plan, and applying a more mathematically rigorous and objective 
 manner of selecting the optimal radiation treatment gating window, while e
 nhancing image resolution, enhancing target definition, and treatment deli
 very. \n\nThe project is subsequently divided in various phases. One phase
  consists of deriving the deformation parameters to describe the three-dim
 ensional movement of the patient's target treatment region through deforma
 tion propagation. The second phase involves a surrogate model for fast rec
 onstruction of the dose distribution in the gross tumor volume(s), GTV(s),
  and organs at risk ,OAR(s), across all the phases, accounting for the def
 ormed target region in time. With these dose profiles, the physicians will
  have the bounds (within a confidence interval) for the absorbed dose by d
 ifferent organs and tumors across all the respiratory cycle and they will 
 be able to determine if the treatment plan for that patient is accurate an
 d appropriate or if it needs to be replanned. \n\nAdditional phases of the
  algorithm use AI approached to enhance this step. The project's algorithm
  is unique and captures a higher degree of individualization based on the 
 patient's specific organ movement compared with prior non-AI algorithms. A
 lthough other studies in the past have explored integrating AI for image s
 egmentation for auto-contouring, our project's novelty lies in the manner 
 of initialized parameters and the specific operations performed. Our proje
 ct furthers patient-specific treatment planning while adopting a more stre
 amlined approach and helps make more informed decisions using AI, to arriv
 e at improved radiation treatment plans for lung cancer patients undergoin
 g SBRT. We have tested our algorithm in several patients and have seen enc
 ouraging improvements.\n\nSession Format: Recorded\n\nRegistration Categor
 y: Workshop Reg Pass
END:VEVENT
END:VCALENDAR