S496
ESTRO 36
_______________________________________________________________________________________________
Physics, Odense, Denmark
16
Hospital of Næstved, Oncology, Næstved, Denmark
Purpose or Objective
To internally and externally validate an atlas based
automated segmentation (ABAS) tool for loco-regional
radiation therapy of early breast cancer based on the
ESTRO consensus guideline for target volume delineation.
Material and Methods
Structures of 60 patients manually delineated according to
the ESTRO consensus guideline were included in four
categorized multi-atlas libraries (based on laterality and
surgery) using MIM Maestro
™
software. These libraries were
used for automated segmentation of primary and nodal
target volumes and organs at risk. Internal Validation of
ABAS was done by comparing ABAS before and after
correction against a gold standard manual segmentation
(MS) in 50 patients from the local institution using Dice
Similarity Coefficient (DSC), Average Hausdorff Distance
(AHD), difference in volume (∆V) and time. External
validation was done by comparing ABAS without correction
against MS in 40 patients from other institutions using DSC
and AHD. In the internal validation phase MS and
correction of ABAS was performed by only one observer,
while in the external validation phase MS was performed
by multiple observers from 10 different institutions.
Results
ABAS reduced the time of MS before and after correction
by 93% and 32%, respectively.
In the internal validation
phase, ABAS showed high agreement with MS for lung,
heart, breast and humeral head, moderate agreement for
chest wall and axillary nodal levels and poor agreement
for inter-pectoral, internal mammary nodal regions and
left anterior descending coronary artery (Figure 1).
Correcting ABAS significantly improved all the parameters
defined as increased DSC and decreased AHD and ∆V.
Applying ABAS in an external group of patients with
different arm positions, immobilization techniques and
respiratory gating status showed comparable results
(Table 1).
Table 1.
Figure 1.
Conclusion
ABAS is a clinically useful tool for segmenting structures in
breast cancer loco-regional radiation therapy in a multi-
institutional setting. The introduction of ABAS in daily
clinical practice will significantly reduce the workload
especially in departments where the radiation therapy
technologists (RTTs) are responsible for target volume
delineation and treatment planning. Manual correction of
some structures is important before clinical use.
Moreover, applying ABAS may be a reasonable alternative
for consistent segmentation and easy quality assurance
testing in multi-institutional trials. Careful selection and
stratification of atlas subjects seems to be the most
influencing factor in the outcome of the ABAS. Further
investigation to find out the best stratification factors is
encouraged.
Based on these results, ABAS is now made
available for Danish patients.
PO-0899 Tumor volume delineation us ing non-EPI
diffusion weighted MRI and FDG-PET in he ad-and-neck
patients.
B. Peltenburg
1
, T. Schakel
1
, J.W. Dankbaar
2
, M.
Aristophanous
3
, C.H.J. Terhaard
1
, J.M. Hoogduin
2
, M.E.P.
Philippens
1
1
UMC Utrecht, Radiation Oncology, Utrecht, The
Netherlands
2
UMC Utrecht, Radiology, Utrecht, The Netherlands
3
MD Anderson Cancer Center, Radiation Physics,
Houston, USA
Purpose or Objective
Diffusion weighted (DW) MRI shows high contrast between
tumor and the surrounding tissue, which makes it a
candidate to facilitate target volume delineation in head-
and-neck (HN) radiotherapy treatment planning. In this
study we assess the performance of geometrically
undistorted DW MRI for target delineation in terms of
interobserver agreement and spatial concordance with
automatic delineation on
18
F-fluorodeoxyglucose (FDG)
positron emission tomography (PET).
Material and Methods
Fifteen head-and-neck cancer patients underwent both
standard echo-planar imaging based (EPI) and undistorted
fast spin-echo based (SPLICE) DW MRI in addition to FDG-
PET for RT treatment planning. Target delineation on DW
MRI was performed by 3 observers, while for PET a semi-
automatic segmentation was performed using a Gaussian
mixture model. Volumes, overlap metrics, defined as dice
similarity coefficient and generalized conformity index,
and hausdorff distances were calculated from the
delineations.
Results
The median volumes delineated by the 3 observers on DW
MRI were 10.8, 10.5 and 9.0 mL respectively. The median
conformity index over all patients was 0.73 (range 0.38 –
0.80). On PET, a significantly smaller median volume of
8.0 mL was found. Compared with PET, the delineations