ESTRO 36 Abstract Book

569 / 1096

S554 ESTRO 36
_______________________________________________________________________________________________
Conclusion
Machine learning methods can be competitive with
standard image processing algorithms in the field of organ
segmentation.
PO-1005 Automatic segmentation of cardiac sub-
structures in the treatment of HL
C. Fiandra 1, M. Levis1, F. Cadoni1, V. De Luca1, F.
Procacci1, A. Cannizzaro1, R. Ragona 1, U. Ricardi1
1 University of Torino, Oncology, Torino, Italy
Purpose or Objective
to validate, in the context of treatment of Hodgkin
Lymphoma, three commercial software solutions for atlas-
based segmentation of cardiac sub-structures
Material and Methods
25 patients were selected and then divided into two
groups: 15 patients will make up the personalized atlas
and 10 patients on which will be applied atlases created
in order to assess its quality. For the selection of patients,
the following inclusion criteria were selected: patients
with HL presentation of a mediastinal mass at the onset of
the disease and the availability of CT imaging with
contrast. Two expert physicians have delineated on the
diagnostic CT with contrast the selected 15 patients
cardiac structures: the heart as a whole, the four
chambers of the heart, the coronary artery and valvular
structures; which will compose the atlas. We use three
commercial solutions (Velocity AI, MIM and RayStation) in
order to compare their results; the structures delineated
by doctors on the 5 control patients will be compared with
those automatically drawn by atlases, through the
conformality function (Dice Index (DI)). In addition, the
atlases underwent a clinical evaluation of the involved
physicians: in particular it was asked to a Radiation
Oncologist to analyze contours made by the three
software on reference patients to evaluate the goodness
of the warp made from atlases than those performed by
him. Clinical judgments were recorded on a scale of
numerical values: 1 = poor; 2 = medium; 3 = good.
Results
in terms of statistical analysis, the data obtained from the
values of Dice Index were compared structure by structure
between the three platforms. The Figure 1 shows only
structures with a Dice Index more than 0.5 (right atrium,
left atrium, the heart, the left side wall, interventricular
septum, aortic valve, left ventricle and right ventricle).
The differences between the 3 software were calculated
and the structures delineated by MIM have more
frequently higher values of Dice Index, compared to those
of Velocity and RayStation, with respectively 0.03 to 0.01
p-value. Instead the difference between Velocity and
RayStation is not statistically significant (p-value = 0.8).
Regarding the evaluation of the Radiation Oncologist as
compared to DI, values show that RayStation is the
software that realizes contours more applicable in clinical
practice, with statistically significant differences from
Velocity and MIM, with p-value respectively of 0.038 and
0.046. While the difference between Velocity and MIM is
not statistically significant (p-value = 0.083).
Conclusion
In general we can say that the contours applied by atlases
are valid, even if not yet optimal and they may represent
a starting point for the step of contouring, useful to speed
up this process; based on the values of Dice Index
collected in this study, MIM performs better while
RayStation appears the most powerful software from a
clinical point of view thus obtaining contours more
“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 Lablanca1, S. Paul1, M. Chiesa1, K.H.
Grosser 1, W. Harms1
1St. 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.