[ITK-users] airway enhancement using Hessian3DToVesselnessMeasureImageFilter

[samah]

 Hi,

I tried to use Hessian3DToVesselnessMeasureImageFilter to segment airways
tree in the lung. i have modified the
Hessian3DToVesselnessMeasureImageFilter.hxx as follow:

   // Get the eigen value
    eigenValue = it.Get();

    // dark tubular structures will have a low value of $\lambda_1$ and
large positive values of $\lambda_2$ and $\lambda_3$

    double normalizeValue = vnl_math_min( eigenValue[1],  eigenValue[0]);

    // Similarity measure to a line structure
    if ( normalizeValue > 0 )
      {
      double lineMeasure;
      if ( eigenValue[2] <= 0 )
        {
        lineMeasure =
          std::exp( -0.5 * vnl_math_sqr( eigenValue[2] / ( m_Alpha1 *
normalizeValue ) ) );
        }
      else
        {
        lineMeasure =
          std::exp( -0.5 * vnl_math_sqr( eigenValue[2] / ( m_Alpha2 *
normalizeValue ) ) );
        }

      lineMeasure *= normalizeValue;
      oit.Set( static_cast< OutputPixelType >( lineMeasure ) );
      }
    else
      {
      oit.Set(NumericTraits< OutputPixelType >::ZeroValue());
      }

    ++it;
    ++oit;
    }

but it doesn't work, any suggestion please.

Regards
Samah,



--
View this message in context: http://itk-insight-users.2283740.n2.nabble.com/airway-enhancement-using-Hessian3DToVesselnessMeasureImageFilter-tp7588475.html
Sent from the ITK Insight Users mailing list archive at Nabble.com.