Delia Ciardo1, Marianna Alessandra Gerardi1, Sabrina Vigorito2, Anna Morra1, Veronica Dell'acqua1, Federico Javier Diaz3, Federica Cattani2, Paolo Zaffino4, Rosalinda Ricotti1, Maria Francesca Spadea4, Marco Riboldi5, Roberto Orecchia6, Guido Baroni5, Maria Cristina Leonardi7, Barbara Alicja Jereczek-Fossa8. 1. Department of Radiation Oncology, European Institute of Oncology, Milan, Italy. 2. Unit of Medical Physics, European Institute of Oncology, Milan, Italy. 3. Medical Radiation Oncology, Mevaterapia, Buenos Aires, Argentina. 4. Department of Experimental and Clinical Medicine, Magna Graecia University, Catanzaro, Italy. 5. Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy; Bioengineering Unit, National Center for Oncologic Hadrontherapy, CNAO Foundation, Pavia, Italy. 6. Scientific Direction, European Institute of Oncology, Milan, Italy; Department of Oncology and Hemato-oncology, University of Milan, Milan, Italy. 7. Department of Radiation Oncology, European Institute of Oncology, Milan, Italy. Electronic address: cristina.leonardi@ieo.it. 8. Department of Radiation Oncology, European Institute of Oncology, Milan, Italy; Department of Oncology and Hemato-oncology, University of Milan, Milan, Italy.
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.
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.
Authors: Olaf Wittenstein; Patrick Hiepe; Lars Henrik Sowa; Elias Karsten; Iris Fandrich; Juergen Dunst Journal: Strahlenther Onkol Date: 2019-04-29 Impact factor: 3.621
Authors: Robert Neil Finnegan; Lucia Orlandini; Xiongfei Liao; Jun Yin; Jinyi Lang; Jason Dowling; Davide Fontanarosa Journal: PLoS One Date: 2021-01-14 Impact factor: 3.240
Authors: Rita Simões; Geert Wortel; Terry G Wiersma; Tomas M Janssen; Uulke A van der Heide; Peter Remeijer Journal: Phys Imaging Radiat Oncol Date: 2019-11-30