Modeling Respiratory Signals by Deformable Image Registration on 4DCT Lung Images

Algorithm 5

Entropy error rate.

1. Input the source slice: SrcSliceIM (contains only the left and right lungs) and the target slice: TarSliceIM (contains only the left and right lungs)

2. Compute the entropy of each source and target slices

   SrcEntropyFeatures = ExtractEntropyFeatures(SrcSliceIM)

   TarEntropyFeatures = ExtractEntropyFeatures(TarSliceIM)

3. Entropy Error Rate

   EntropyErrorRate = abs(TarEntropyFeatures - SrcEntropyFeatures)

4. End

5. Result in EntropyErrorRate

Appendix

ExtractEntropyFeatures method

1. Calculated p contains the normalized histogram counts returned from the image

2. Entropy is defined as -sum(p.log2(p))