S82
ESTRO 36
_______________________________________________________________________________________________
methods for CT and CBCT radiomics features in rectal
cancer, and to provide a harmonization evaluation
method.
Material and Methods
Three harmonization strategies were tested in this study,
including no correction, simple correction and phantom
based correction. 50 rectal cancer patients with both
planning CT images and positioning CBCT images before
the first fraction of treatment were collected for
harmonization performance evaluation. 203 features were
extracted from CT and CBCT images. For the phantom
based correction, a texture phantom comprised of 30
different materials was designed for features selection
and nonlinear functions generation for normalizing CT and
CBCT features.The Main workflow was shown in Figure 1.
Mixed datasets consisting of CT and CBCT features were
generated for harmonization performance evaluation
using cluster analysis. The harmonization performance
was evaluated by Chi-square testing between clustering
results and scanner machines, and the clustering
consistency with original CT feature. These tests were
repeated for 50 times with randomized sample
generation.
Figure 1. Main Workflow. Four steps of this study:(I)
Feature selection by features range comparison.
(II)Feature selection by spearman correlation test. (III)
Nonlinear mapping function generation using texture
phantom. (IV)Correction methods performance evaluation
on patients.
Results
41 of the 203 radiomics features were selected by range
comparison and spearman correlation test. Among 50
randomized sampling processes, all clustering (100%)
results without any correction showed high correlation
with imaging machine (p>0.05, χ^
2
test), while this
probability reduced to 0 % and 42% respectively when
simple correction or phantom based correction were
applied. Average accuracy and Kappa index increased
significantly (p<0.05, t-test), respectively to 0.71±0.07
and 0.42±0.12 for simple correction method and 0.68±0.06
and 0.36±0.14 for phantom based correction method, from
0.61±0.06 and 0.23±0.13 without any correction.
Table1. Performance evaluation result for different
harmonization strategies.
Conclusion
This is the first study focused on feature harmonization for
CT images. Two proposed correction methods, simple
correction and phantom based correction, were verified
to be feasible for CT and CBCT harmonization, which could
significantly improve the modeling consistency.
Proffered Papers: Novelties in image guidance
OC-0161 patient tolerance of stereotactic MR-guided
adaptive radiation therapy: an assessment using PRO’s
R. Bakker
1
, M. Jeulink
1
, S. Tetar
1
, S. Senan
1
, B. Slotman
1
,
F. Lagerwaard
1
, A. Bruynzeel
1
1
VU University Medical Center, Radiotherapy,
Amsterdam, The Netherlands
Purpose or Objective
Recently, SMART has been introduced in our center using
the MRIdian (Viewray). One key feature of SMART is
delivery of radiation while patients are positioned for a
prolonged period within the MRI bore, and therefore may
experience procedure-related problems such as anxiety,
noise and other MR-related undesired signals. Briefly,
patients are positioned on the MRIdian with body coils and
headphones, after which 0.35T MR-scans are performed
prior to each fraction. After alignment of the target
volume and re-contouring, re-optimization of the original
treatment plan and patient-specific QA is performed while
patient remains in treatment position. Treatment is
delivered under real-time MR-guidance, with or without
breath-hold, depending on location. On average, the
duration of a single fraction ranges from 45 minutes
(prostate SBRT) up to 75 minutes (breath-hold pancreas
SBRT). To gain insight into patient tolerance and
experiences of SMART delivery, we prospectively collected
patient-reported outcome questionnaires (PRO-Q) in
treated patients since May 2016.
Material and Methods
The intake visit of SMART patients includes providing
procedural information by the radiation oncologist, and in
case of video-feedback for breath-hold, also by
dosimetrists. During the same visit, a MRI-safety
questionnaire is completed. Immediately after the intake,
a simulation MR-scan is performed on the MRIdian. PRO-Q
were collected in 55 patients after the last SMART
fraction. The PRO-Q includes questions on anxiety,
temperature, noise, and other potential MR-related
undesired signals. It also includes a question on the
tolerance of the duration of the SMART procedure. Items
could be scored as: 1) 'not at all”, 2) 'a bit” 3) 'moderate”
and 4) 'considerable”.
Results
Two of 57 patients withdrew from SMART because of
severe claustrophobia during the simulation MRI.
Furthermore, anxiety during treatment was reported by
12/55 patients (22%), with half of these reporting anxiety
to be considerable. A majority of patients (52%) reported
sensations of feeling cold related to the cooling air flow of
the MRIdian. Although the MRIdian combines noise of the
gradient coils of the MR and retraction of the radiation
sources, this sound was experienced to be really disturbing
by two patients only. Troublesome paresthesia was
reported by two patients, mainly related to prolonged
positioning of the arms above the head. Other relevant
MR-related undesired signals such as dizziness, local heat
sensations or metallic taste sensations were only
occasionally reported. Although the total fraction
duration was judged to be long by some extent in 22% of
patients, only a single patient scored this as being
unacceptably long (Fig.1).