924 / 1082
S908
ESTRO 36 2017
_______________________________________________________________________________________________
areas with atypically high signal on high b-value images.
ROI volumes where then analyzed using a radiomics
approach where 67 image features were extracted from
each volume. Tumor response to treatment was
determined by pathologists examining the surgical
specimen and scoring the tumor response using the
Mandard Tumor Regression Grade (TRG). Data were
analyzed both by visual examination of the data and by
applying a decision tree algorithm.
Results
From visual inspection of the data we found that using only
initial entropy and mean values for the ADC image as well
as their change during the first 2 weeks of treatment, we
could correctly classify 24 of the 25 patients as either
major response (TRG 1 or 2) or minor response (TRG 3 or
4). This was confirmed by building a decision tree for the
entire dataset. Applying machine learning techniques
where the data are divided into a training and a test
sample, we were hampered by the small data set, which
meant building a model on only part of the data set and
using the remaining patients to test the model gave large
variations in both the selected parameters and the ability
of the model to correctly predict the response of the
remaining patients (from 40% to 100%).
Conclusion
DWI imaging can provide information on the tumor
response as early as 2 weeks into CRT. Further work is
needed to improve the model and especially testing on an
larger data set is necessary.
[1] High-dose chemoradiotherapy and watchful waiting
for distal rectal cancer: a prospective observational study
Appelt, Ane L et al.
The Lancet Oncology , Volume 16 , Issue 8 , 919 - 927
[2] Watch-and-wait approach versus surgical resection
after chemoradiotherapy for patients with rectal cancer
(the OnCoRe project): a propensity-score matched cohort
analysis
Renehan, Andrew G et al.
The Lancet Oncology , Volume 17 , Issue 2 , 174 - 183
EP-1687 Texture analysis of 18F-FDG PET/CT predicts
local control of stage I NSCLC treated by SBRT
K. Takeda
1
, K. Takanami
2
, Y. Shirata
1
, T. Yamamoto
1
, N.
Takahashi
1
, K. Ito
1
, K. Takase
2
, K. Jingu
1
1
Tohoku University Graduate School of Medicine,
Radiation Oncology, Sendai, Japan
2
Tohoku University Graduate School of Medicine,
Diagnostic Radiology, Sendai, Japan
Purpose or Objective
Recently, there are some reports that texture analysis of
18F-FDG PET/CT has better potential to predict outcome
of radiotherapy than existing PET parameters such as
maximum SUV. We evaluated reproducibility and
predictive value of some texture parameters based on
gradient-based delineation method and existing
parameters of 18F-FDG PET/CT image in patients with
early stage non-small cell lung cancer (NSCLC) treated by
stereotactic body radiation therapy (SBRT).
Material and Methods
Thirty patients with early stage NSCLC (T1-2N0M0) were
retrospectively investigated. SBRT was delivered with
total dose of 40-48Gy in 4 fractions for peripheral regions
or 50-60Gy in 7-15 fractions for central regions or regions
nearby other organ at risk. All patients underwent 18F-
FDG PET/CT scan before treatment. Each tumor was
delineated using PET Edge (MIM Software Inc., Cleveland)
and texture parameters were calculated using open-
source code CGITA (Fang,
et.al., 2014). From 18F-FDG
PET/CT image, three conventional parameters including
metabolic tumor volume (MTV), maximum standardized
uptake value (SUV) and total lesion glycolysis (TLG) and
four textural parameters including entropy and
dissimilarity derived from co-occurrence matrix and high-
intensity large-area emphasis and zone percentage
derived from size-zone matrix were analyzed.
Reproducibility was evaluated using two independent
delineation conducted by two observers using intraclass
correlation coefficients (ICC). The ability to predict local
control (LC) was tested for each parameter using Cox
proportional hazards model.
Results
Median follow-up period was 30.1 month and 8 (23%)
patients occurred local relapse. Between two observers,
six parameters besides zone percentage (ICC value 0.59)
showed ICC value ranged between 0.81 and 1.00. In
univariate analysis, there were significant correlations
between LC and tumor diameter>30mm (hazard ratio
7.21, p=0.02), MTV≥5.14cm3 (HR 9.38, p=0.01), TLG≥59.7
(HR 5.86, p=0.04), entropy≥-34.3 (HR 0.13, p=0.02),
dissimilarity≥2235 (HR 6.87, p=0.03) and treatment
biological equivalent dose≥100Gy (HR 0.02, p=0.04),
respectively. Maximum SUV≥10.4 was not a significant
predictor for LC (p=0.09).
Conclusion
Texture analysis based on gradient-based delineation
method has high reproducibility in most parameters.
Entropy and dissimilarity calculated from co-occurrence
matrix is potentially beneficial to predict LC with
reproducibility in patients with NSCLC treated by SBRT. To
establish utility of texture analysis in 18F-FDG PET/CT
image, further study including prospective trial will be
needed.
EP-1688 Voxelbased analysis of FMISO-PET and
diffusion-weighted MRI of two different HNSCC models
in mice
R. Winter
1
, S. Boeke
2
, M. Krueger
3
, A. Menegakis
2
, E.
Sezgin
2
, L. Wack
1
, G. Reischl
3
, B. Pichler
3
, D. Zips
2
, D.
Thorwarth
1
1
University Hospital Tübingen, Section for Biomedical
Physics, Tübingen, Germany
2
University Hospital Tübingen, Radiation Oncology,
Tübingen, Germany
3
Werner Siemens Imaging Center, Preclinical Imaging and
Radiopharmacy, Tübingen, Germany
Purpose or Objective
Hypoxia is an important prognostic marker for
radiotherapy (RT) response, particularly for head and neck
squamous cell carcinoma (HNSCC) and may be measured