Atlas-based segmentation in breast cancer radiotherapy: Evaluation of specific and generic-purpose atlases

Delia Ciardo, Marianna Alessandra Gerardi, Sabrina Vigorito, Anna Morra, Veronica Dell'acqua, Federico Javier Diaz, Federica Cattani, Paolo Zaffino, Rosalinda Ricotti, Maria Francesca Spadea, Marco Riboldi, Roberto Orecchia, Guido Baroni, Maria Cristina Leonardi, Barbara Alicja Jereczek-Fossa

Research output: Contribution to journalArticle

Abstract

Objectives Atlas-based automatic segmentation (ABAS) addresses the challenges of accuracy and reliability in manual segmentation. We aim to evaluate the contribution of specific-purpose in ABAS of breast cancer (BC) patients with respect to generic-purpose libraries. Materials and methods One generic-purpose and 9 specific-purpose libraries, stratified according to type of surgery and size of thorax circumference, were obtained from the computed tomography of 200 BC patients. Keywords about contralateral breast volume and presence of breast expander/prostheses were recorded. ABAS was validated on 47 independent patients, considering manual segmentation from scratch as reference. Five ABAS datasets were obtained, testing single-ABAS and multi-ABAS with simultaneous truth and performance level estimation (STAPLE). Center of mass distance (CMD), average Hausdorff distance (AHD) and Dice similarity coefficient (DSC) between corresponding ABAS and manual structures were evaluated and statistically significant differences between different surgeries, structures and ABAS strategies were investigated. Results Statistically significant differences between patients who underwent different surgery were found, with superior results for conservative-surgery group, and between different structures were observed: ABAS of heart, lungs, kidneys and liver was satisfactory (median values: CMD<2 mm, DSC≥0.80, AHD<1.5 mm), whereas chest wall, breast and spinal cord obtained moderate performance (median values: 2 mm ≤ CMD<5 mm, 0.60 ≤ DSC<0.80, 1.5 mm ≤ AHD<4 mm) and esophagus, stomach, brachial plexus and supraclavicular nodes obtained poor performance (median CMD≥5 mm, DSC<0.60, AHD≥4 mm). The application of STAPLE algorithm generally yields higher performance and the use of keywords improves results for breast ABAS. Conclusion The homogeneity in the selection of atlases based on multiple anatomical and clinical features and the use of specific-purpose libraries can improve ABAS performance with respect to generic-purpose libraries.

Original languageEnglish
Pages (from-to)44-52
Number of pages9
JournalBreast
Volume32
DOIs
Publication statusPublished - Apr 1 2017

    Fingerprint

Keywords

  • Atlas-based segmentation
  • Automatic contouring
  • Breast cancer radiotherapy
  • STAPLE contours

ASJC Scopus subject areas

  • Surgery

Cite this