Title: Normal Tissue Complication Probability Modeling Techniques Using Bootstrap Replicates of the Variabl
1Normal Tissue Complication Probability Modeling
Techniques Using Bootstrap Replicates of the
Variable Selection Process
- Angel Blanco, MD, Joe Deasy, PhD, and Issam El
Naqa, PhD - Dept of Radiation Oncology
Now at M.D. Anderson Cancer Center
2Obstacles to better NTCP models
- Retrieving data
- Extraction from the treatment planning system
- Modeling data
- Model exploration Data Mining
- Parameter determination
- Multiple term regression models including
various factors
3How do we conveniently get and analyze data from
3-D treatment planning systems?
4CERR A Computational Environment for
Radiotherapy Research
- Extracts structures, dose distributions, DVHs,
images, from academic and commercial treatment
planning systems - Into the highly convenient data analysis and
visualization environment, Matlab - Freely available via webpage http//deasylab.info
- Available for non-clinical ( non-commercial)
research
5Successful imports from
- CMS Focus (RTOG)
- Pinnacle (RTOG)
- TMS Helax (RTOG)
- Helios (DICOM)
- NOMOS (RTOG)
- No failures so far, but tweaking required
6CERR version 2.5 beta (latest released version)
7Recomputed DVHs generally the same to within RMSE
of 1
(Zakarian et al., 2003 AAPM mtg)
8CERR can automatically extract
- GTV volumes
- DVHs
- DVH parameters
- Dose surface histograms
- Positional information (e.g., GTV-SI)
- Anything that can be programmed
9How do we model the data?
10NTCP modeling via multi-metric logistic regression
The metric can be a sum of various terms
11Self-correlation matrix
(Deasy, Bradley et al, ASTRO 2003)
12Example Pneumonitis/fibrosis due to lung cancer
RT
- N 166 WUSTL patients
- Grade 2 or greater
- Vx (e.g., V20) data extracted with CERR
- Does mean dose best predict complications?
- Does chemotherapy matter?
13Grade 2 and greater n 168.
(Hope, Deasy, Bradley et al, ASTRO 2004,
submitted)
14(Deasy, Bradley et al, ASTRO 2003)
15The bootstrap method (Efron)
- Pseudo datasets can be created by sampling
patient data from original dataset, repeatedly. - Buteach patient may be represented more than one
time. - The idea is that the true population data
distribution can be represented by the
distribution in the sampled data.
16Bootstrap applied to regression analysis
- Are the four variables selected in the regression
analysis really the best? - Method repeat regression analysis on bootstrap
replicates.
17Bootstrap stability tests of regression
?
(N166)
18Summary
- CERR/Matlab provides a convenient format for
extracting and analyzing large sets of
radiotherapy treatment planning data. - The bootstrap method can be applied to regression
analysis to increase our understanding and
confidence in multi-term logistic regression.