Poster — Thur Eve — 70: Automatic lung bronchial and vessel bifurcations detection algorithm for deformable image registration assessment

Authors

  • Labine Alexandre,

    1. Centre hospitalier de l'Université de Montréal
    2. Laboratoire de recherche en imagerie et d'orthopédie-CRCHUM
    3. École de technologie supérieure
    Search for more papers by this author
  • Chav Ramnada,

    1. Centre hospitalier de l'Université de Montréal
    2. Laboratoire de recherche en imagerie et d'orthopédie-CRCHUM
    3. École de technologie supérieure
    Search for more papers by this author
  • De Guise Jacques,

    1. Centre hospitalier de l'Université de Montréal
    2. Laboratoire de recherche en imagerie et d'orthopédie-CRCHUM
    3. École de technologie supérieure
    Search for more papers by this author
  • Carrier Jean-François,

    1. Centre hospitalier de l'Université de Montréal
    2. Laboratoire de recherche en imagerie et d'orthopédie-CRCHUM
    3. École de technologie supérieure
    Search for more papers by this author
  • Bedwani Stéphane

    1. Centre hospitalier de l'Université de Montréal
    2. Laboratoire de recherche en imagerie et d'orthopédie-CRCHUM
    3. École de technologie supérieure
    Search for more papers by this author

Abstract

Purpose:

To investigate an automatic bronchial and vessel bifurcations detection algorithm for deformable image registration (DIR) assessment to improve lung cancer radiation treatment.

Methods:

4DCT datasets were acquired and exported to Varian treatment planning system (TPS) EclipseTM for contouring. The lungs TPS contour was used as the prior shape for a segmentation algorithm based on hierarchical surface deformation that identifies the deformed lungs volumes of the 10 breathing phases. Hounsfield unit (HU) threshold filter was applied within the segmented lung volumes to identify blood vessels and airways. Segmented blood vessels and airways were skeletonised using a hierarchical curve-skeleton algorithm based on a generalized potential field approach. A graph representation of the computed skeleton was generated to assign one of three labels to each node: the termination node, the continuation node or the branching node.

Results:

320 ± 51 bifurcations were detected in the right lung of a patient for the 10 breathing phases. The bifurcations were visually analyzed. 92 ± 10 bifurcations were found in the upper half of the lung and 228 ± 45 bifurcations were found in the lower half of the lung. Discrepancies between ten vessel trees were mainly ascribed to large deformation and in regions where the HU varies.

Conclusions:

We established an automatic method for DIR assessment using the morphological information of the patient anatomy. This approach allows a description of the lung's internal structure movement, which is needed to validate the DIR deformation fields for accurate 4D cancer treatment planning.

Ancillary