TY - JOUR
T1 - Atlas-based segmentation in breast cancer radiotherapy
T2 - Evaluation of specific and generic-purpose atlases
AU - Ciardo, Delia
AU - Gerardi, Marianna Alessandra
AU - Vigorito, Sabrina
AU - Morra, Anna
AU - Dell'acqua, Veronica
AU - Diaz, Federico Javier
AU - Cattani, Federica
AU - Zaffino, Paolo
AU - Ricotti, Rosalinda
AU - Spadea, Maria Francesca
AU - Riboldi, Marco
AU - Orecchia, Roberto
AU - Baroni, Guido
AU - Leonardi, Maria Cristina
AU - Jereczek-Fossa, Barbara Alicja
PY - 2017/4/1
Y1 - 2017/4/1
N2 - 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.
AB - 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.
KW - Atlas-based segmentation
KW - Automatic contouring
KW - Breast cancer radiotherapy
KW - STAPLE contours
UR - http://www.scopus.com/inward/record.url?scp=85007240058&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85007240058&partnerID=8YFLogxK
U2 - 10.1016/j.breast.2016.12.010
DO - 10.1016/j.breast.2016.12.010
M3 - Article
AN - SCOPUS:85007240058
VL - 32
SP - 44
EP - 52
JO - Breast
JF - Breast
SN - 0960-9776
ER -