A study on the effect of imaging acquisition parameters on lung nodule image interpretation

1
A study on the effect of imaging acquisition
parameters on lung nodule image interpretation

• Presenters
• Shirley Yu (University of Southern California)
• Joe Wantroba (DePaul University)
• Mentors
• Daniela Raicu
• Jacob Furst

2
Outline

• Motivation
• Purpose
• Related Work
• Methodology
• Results
• Post-Processing Analysis
• Conclusion

3
Motivation Why are CT image acquisition
parameters important?

• Studies develop CAD systems using images from one
  CT scanner
• Different CT scanners use different parameters.
• Do varying parameters affect the image features
  read by CAD systems?
• How do we know if these CAD systems apply to
  other CT scanners?

4
Purpose

• Extension of previous work Semantic Mapping
• What CT parameters influence predicting of
  Semantic Characteristics?

Raicu, Medical Imaging Projects at Depaul CDM,
2008
5
Project Goals

• Study the effects of CT parameters on semantic
  mapping.
• Identify most important parameters.
• Normalize differences of these important
  parameters.

6
Related Work

• Effect on image quality1
• Slice Thickness, Manufacturer, kVp, Convolution
  kernel
• Effect on volumetric measurement2
• Threshold, Section Thickness
• Manufacturer, Collimation, Section Thickness
• Effect on nodule detection algorithm3
• Convolution Kernel

1 Zerhouni et.al, 1982, Birnbaum et al, 2007 2
Goo et. Al, 2005, Das et al, 2007, Way et al,
2008 3 Armato et al, 2003
7
Methods LIDC Dataset

• All cases from the LIDC
• Dataset
• 85 cases
• 60 cases with 149 nodules
• Multiple slices per nodule
• Up to 4 radiologist ratings per nodule per slice
  1

8
Diagram of Methodology
9
Methods Data Collection

• Extracted DICOM header information
• Previous Work Automatic feature extraction
• Merged header information with image features.

10
Methods Data Pre-Processing
Slice Thickness 2. Pixel Spacing 1
3. kVp 4. Pixel Spacing 2
5. Reconstruction Diameter 6. Bits Stored
7. Distance SourceToPatient 8. High Bit
9. Exposure 10. Pixel Representation
11. Bit Depth 12. Rescale Intercept
13. Convolution Kernel 14. Z Nodule Location

• 103 variables ?
• 14 variables
• Eliminated if
• Unique identifiers
• Missing values
• Confounding variables

11
Methods Z Nodule Location
Lung Apex 1

• Lung Base 5

12
Results Decision Tree

• Target Variables Texture, Subtlety, Sphericity,
  Spiculation, Margin, Malignancy, Lobulation
• Specifications
• Cross-validation 10 folds
• Growth Method C RT
• Max Tree Depth 50
• Parent Node 5
• Child Node 2

13
Results Texture DT
Reconstruction Diameter
14
Results CT parameters and semantic
characteristics they predict for
Convolution Kernel Reconstruction Diameter Exposure Distance Source to Patient Z Nodule Location kVp Slice Thickness
Texture (0.032, 3) (0.018, 8) - - - - -
Subtlety (0.032, 3) (0.014, 8) - (0.022, 6) - (0.017, 10) - -
Spiculation - - (0.043, 2) (0.016, 6) - - (0.016, 9)
Sphericity - - - - (0.019, 6) (0.036, 3) -
Margin (0.020, 9) (0.019, 10) - - - - -
Malignancy - - (0.015, 3) - (0.019, 6) - -
Lobulation - - (0.052, 2) (0.021, 6) - - -
15
Outline

• Motivation
• Purpose
• Related Work
• Methodology
• Results
• Post-Processing Analysis
• Box plots Analyze influence of CT parameters on
  image features
• Binning values Minimize influence of
  wide-ranging values
• Conclusion

16
Results Box Plots of Image Features
CT Parameters Image Features
Convolution Kernel (B30f, B31f, B31s, Bone, C, D, FC01 , Stan) Gabor, Inverse Variance, Major Axis Length, Elongation, Compactness
Reconstruction Diameter (260-390 mm) Markov
Exposure (25-2108 mAs) Gabor, Minimum Intensity, Circularity, Homogeneity, Compactness
kVp(120, 130, 135, 140) Elongation, Perimeter
Z Nodule Location (1-5 1 lung apex, 5 lung base) Radial Distance, Minimum Intensity
Distance Source to Patient (535, 541, and 570 mm) Contrast, Gabor
17
Convolution Kernel Reconstruction Diameter Exposure Distance Source to Patient Z Nodule Location kVp Slice Thickness
Texture (0.032, 3) (0.018, 8) - - - - -
Subtlety (0.032, 3) (0.014, 8) - (0.022, 6) - (0.017, 10) - -
Spiculation - - (0.043, 2) (0.016, 6) - - (0.016, 9)
Sphericity - - - - (0.019, 6) (0.036, 3) -
Margin (0.020, 9) (0.019, 10) - - - - -
Malignancy - - (0.015, 3) - (0.019, 6) - -
Lobulation - - (0.052, 2) (0.021, 6) - - -
18
Post-Processing Box Plots

• Box plots on image features above and below the
  CT parameter split
• Two graphs with no overlapping values Radial
  Diameter for Exposure and 3rd Order for Z Nodule
  Location
• Number of cases in child node too small (2 or 3
  cases)
• Run box plot on all image features for leaf nodes
  lt 2 cases and remaining cases (Are they
  outliers?)

19
(No Transcript)
20
Results Box Plot
Convolution Kernel influencing intensity features
for Texture DT
21
Post-Processing Normalization

• Image feature values normalized between 0-1
• Convolution kernel influences 6 intensity
  features
• Z-transformation to normalize curves (X- avg)/ s

Distribution Curve for Min Intensity values
before Normalizing
After Normalizing
22
Box Plots Normalized vs. Un-Normalized
Minimum Intensity BEFORE normalization
AFTER normalization
23
Normalizing No effect
Convolution Kernel still appears
24
Post-Processing Binned Values

• 14 variables ?10 Variables
• Equal-size binning (2-3 bins)
• Convolution Kernel
• Smoothing vs. Edge vs. Neither

25
Results Binned Values
Z Nodule Location Distance Source to Patient KVP Rescale Intercept
Texture - - - -
Subtlety X - - X
Spiculation X X - -
Sphericty - - X -
Margin - - - -
Malignancy - - - -
Lobulation - X - -

• Eliminated! Convolution Kernel, Reconstruction
  Diameter, Exposure
• New parameter Rescale Intercept

26
Conclusion

• Influential CT parameters
• Convolution Kernel
• Reconstruction Diameter
• Exposure
• Distance Source to Patient
• Slice Thickness
• kVp
• Z Nodule Location

• Influential CT parameters post-binning
• Z Nodule Location
• Distance Source to Patient
• kVp
• Rescale Intercept

27
Future Work

• Logistic Regression
• Perform similar experiment on a larger dataset
• Normalize parameters so they no longer are
  influential

28
References

• Horsthemke, William H., D. S. Raicu, J. D. Furst,
  "Evaluation Challenges for Bridging Semantic Gap
  Shape Disagreements on Pulmonary Nodules in the
  Lung Image Database Consortium", International
  Journal of Healthcare Information Systems and
  Informatics (IJHISI) Special Edition on
  Content-based Medical Image Retrieval., 2008
• Goo et al. Volumetric Measurement of Synthetic
  Lung Nodules with MultiDetector Row CT Effect
  of Various Image Reconstruction Parameters and
  Segmentation Thresholds on Measurement Accuracy,
  Radiology 2005 235 850-856.
• Zerhouni et al. Factors influencing quantitative
  CT measurements of solitary pulmonary nodules. J
  Comput Assist Tomogr 1982 61075-1087
• Way, TW Chan, HP Goodsitt, MM, et al. Effect
  of CT scanning parameters on volumetric
  measurements of pulmonary nodules by 3D active
  contour segmentation a phantom study. Physic in
  Medicine and Biology, 2008. 53 1295-1312
• Birnbaum, B Hindman, N Lee, J Babb, J.
  Multi-detector row CT attentuation measurements
  assessment of intra- and interscanner variability
  with an anthropomorphic body CT phantom.
  Radiology, 2007. 242 110-119.
• Das, M Ley-Zaporozhan, J Gietema, H.A., et al.
  Accuracy of automated volumetry of pulmonary
  nodules across different multislice CT scanners.
  European Radiology, 2007. 17 1979-1984.
• Armato, S G., M B. Altman, and P J. La Riviere.
  "Automated Detection of Lung Nodules in CT Scans
  Effect of Image Reconstruction Algorithm."
  Medical Physics 30 (2003) 461-472.