565 / 1082
S550
ESTRO 36 2017
_______________________________________________________________________________________________
“similar” to those defined by the Radiation Oncologist.
PO-1006 Evaluation of an auto-segmentation software
for definition of organs at risk in radiotherapy
M.D. Herraiz Lablanca
1
, S. Paul
1
, M. Chiesa
1
, K.H.
Grosser
1
, W. Harms
1
1
St. Claraspital, Radioonkologie, Basel, Switzerland
Purpose or Objective
The aim of this work is to evaluate the capability of a
commercial software performing automatic segmentation
of relevant structures for radiotherapy planning, as well
as the time saving of it use on a daily Basis.
Material and Methods
The software Smart Segmentation Knowledge Based
Contouring (Version 13.6) from Varian Medical System was
evaluated according to segmentation quality and time
saving. For that purpose, 5 consecutive prostate and
breast patients were contoured manually and
automatically using the software, recording the time
needed in both, manual and automatic contouring with
corrections. This task was performed by the RTTs, since
they are responsible of the OARs contouring in our
department.
Segmentation quality was qualitatively scored in four
levels: 'excellent”(1), 'good”(2), 'acceptable”(3) and 'not
acceptable”(4) and quantitatively evaluated calculating
five parameters: Relative difference in volume, DICE
similarity coefficient, Sensitivity Index, Inclusiveness
Index, Mass Center Location.
Results
Mean values of the qualitative evaluation and acceptance
are summarized in Table 1. The acceptance of the
structures automatically contoured is higher for breast
cancer than for prostate patients, as well as the mean
time saving, that is above four minutes for breast and
around 1 minute for prostate.
Good agreement was found between manual and
automated segmentation for heart with a mean difference
in volume of 7%, DICE of 0.87 and deviation of mass center
less than 2mm in all directions and for liver with a mean
difference in volume of 11%, DICE of 0.91 and deviation of
mass center less than 2mm in all directions. Poor
acceptance was found in complex structures as penile
bulb, small bowel, sigma and rectum wall anterior and
posterior.
Conclusion
Smart Segmentation software is a useful tool for the
delineation of relevant structures for breast although did
not generate useful delineation for neither the mammilla
nor the esophagus. For relevant structures for prostate as
penile bulb, small bowel, sigma and rectum wall anterior
and posterior the software was not good enough. Further
analysis will be performed including more patients.
Poster: RTT track: Treatment planning and dose
calculation / QC and QA
PO-1007 The effect of VMAT on tumor coverage and
organs at risk for head and neck cancer patients
M. Kertevig
1
1
Rigshospitalet, Department of Oncology- Section for
Radiotherapy, Copenhagen, Denmark
Purpose or Objective
Throughout the course of radiotherapy in head and neck
patients tumor shrinkage occurs. This may influence the
dose to organs at risk (OAR) around the tumor area, as
tumor shrinkage can lead to different dose distribution in
the patient than originally calculated. As Volumetric
Modulated Arc Therapy (VMAT) technique is frequently
used for head and neck patients, it is relevant to study the
impact of VMAT treatment on tumor coverage and OAR,
during a course of radiotherapy, and the necessity to
adaptive plans during the course of treatment.
Material and Methods
A retrospective study has been carried out on 13
consecutive patients who have been treated with VMAT for
head and neck cancer. The Cone-beam Computed
Tomography (CBCT) from the first treatment fraction was
compared with the CBCT from the last fraction. Dose and
volume comparison was performed for planning target
volume (PTV), spinal cord, brainstem and both parotid
glands. A paired t-test was used to test for significance
and
p
-values <0.05 were considered statistically
significant
Results
The mean volume of PTV on the CBCT from the first
treatment fraction was 283.98 cm
3
compared with the
CBCT from the last fraction which was 270.33 cm
3
. The
mean volume of the PTV decreased significantly with 5%
(
p =
0.003), due to tumor shrinkage during the course of
treatment. The mean D
95
to the PTV decreased by less than
1% from 62.34 Gy to 61.88 Gy. The mean D
max
to the spinal
cord increased by 1% from 41.33 Gy to 41.78 Gy and to the
brainstem by 3.8% from 32.11 Gy to 33.33 Gy. The mean
dose to the left parotid gland decreased with less than 1%
from 22.08 Gy to 22.06 Gy. In contrast, the mean dose to
the right parotid gland was significantly increased by 6.5%
(
p
= 0.033) (table 1). There were no significant differences
in the mean dose to either PTV (
p
= 0.12) spinal cord (
p
=
0.27), brainstem (
p =
0.22) and left parotid gland (
p
=
0.98), which means that treatment with VMAT, had
negative effect on dose to spinal cord, brainstem and left
parotid gland with a 95% probability for this patient
cohort. Even though the dose to the right parotid gland
increased significantly, the dose to all OAR remained
within the defined constraints. In addition, the tumor
coverage remained sufficient throughout the treatment.
This need to be studied further with larger sample sizes
together with a dose study for all the OAR in the head and
neck region to fully determine the necessity to adapt the
patients plan, especially since it might be possible to
reduce the dose to the parotid glands for patients
suffering from xerostomia.
Conclusion