Sofie A M Gernaat1, Sanne G M van Velzen2, Vicky Koh3, Marleen J Emaus4, Ivana Išgum2, Nikolas Lessmann2, Shinta Moes2, Anouk Jacobson4, Poey W Tan3, Diederick E Grobbee5, Desiree H J van den Bongard6, Johann I Tang3, Helena M Verkooijen4. 1. Julius Center, University Medical Center Utrecht, Utrecht University, The Netherlands. Electronic address: s.a.m.gernaat-2@umcutrecht.nl. 2. Image Sciences Institute, University Medical Center Utrecht, The Netherlands. 3. Radiation Oncology, National University Cancer Institute, National University Hospital Singapore, Singapore. 4. Imaging Division, University Medical Center Utrecht, Utrecht University, The Netherlands. 5. Julius Center, University Medical Center Utrecht, Utrecht University, The Netherlands. 6. Department of Radiation Oncology, University Medical Center Utrecht, Utrecht University, The Netherlands.
Abstract
PURPOSE: This study automatically quantified calcifications in coronary arteries (CAC) and thoracic aorta (TAC) on breast planning computed tomography (CT) scans and assessed its reproducibility compared to manual scoring. MATERIAL AND METHODS: Dutch (n = 1199) and Singaporean (n = 1090) breast cancer patients with radiotherapy planning CT scan were included. CAC and TAC were automatically scored using deep learning algorithm. CVD risk categories were based on Agatson CAC: 0, 1-10, 11-100, 101-400 and >400. Reliability between automatic and manual scoring was assessed in 120 randomly selected CT scans from each population, with linearly weighted kappa for CAC categories and intraclass correlation coefficient for TAC. RESULTS: Median age was higher in Dutch patients than Singaporean patients: 57 versus 52 years. CAC and TAC increased with age and were more present in Dutch patients than Singaporean patients: 24.2% versus 17.3% and 73.0% versus 62.2%, respectively. Reliability of CAC categories and TAC was excellent in the Netherlands (0.85 (95% confidence interval (CI) = 0.77-0.93) and 0.98 (95% CI = 0.96-0.98) respectively) and Singapore (0.90 (95% CI = 0.84-0.96) and 0.99 (95% CI = 0.98-0.99) respectively). CONCLUSIONS: CAC and TAC prevalence was considerable and increased with age. Deep learning software is a reliable method to automatically measure CAC and TAC on radiotherapy breast CT scans.
PURPOSE: This study automatically quantified calcifications in coronary arteries (CAC) and thoracic aorta (TAC) on breast planning computed tomography (CT) scans and assessed its reproducibility compared to manual scoring. MATERIAL AND METHODS: Dutch (n = 1199) and Singaporean (n = 1090) breast cancerpatients with radiotherapy planning CT scan were included. CAC and TAC were automatically scored using deep learning algorithm. CVD risk categories were based on Agatson CAC: 0, 1-10, 11-100, 101-400 and >400. Reliability between automatic and manual scoring was assessed in 120 randomly selected CT scans from each population, with linearly weighted kappa for CAC categories and intraclass correlation coefficient for TAC. RESULTS: Median age was higher in Dutch patients than Singaporean patients: 57 versus 52 years. CAC and TAC increased with age and were more present in Dutch patients than Singaporean patients: 24.2% versus 17.3% and 73.0% versus 62.2%, respectively. Reliability of CAC categories and TAC was excellent in the Netherlands (0.85 (95% confidence interval (CI) = 0.77-0.93) and 0.98 (95% CI = 0.96-0.98) respectively) and Singapore (0.90 (95% CI = 0.84-0.96) and 0.99 (95% CI = 0.98-0.99) respectively). CONCLUSIONS: CAC and TAC prevalence was considerable and increased with age. Deep learning software is a reliable method to automatically measure CAC and TAC on radiotherapy breast CT scans.
Authors: Andrew Lin; Márton Kolossváry; Manish Motwani; Ivana Išgum; Pál Maurovich-Horvat; Piotr J Slomka; Damini Dey Journal: Radiol Cardiothorac Imaging Date: 2021-02-25
Authors: Roxanne Gal; Sanne G M van Velzen; Maartje J Hooning; Marleen J Emaus; Femke van der Leij; Madelijn L Gregorowitsch; Erwin L A Blezer; Sofie A M Gernaat; Nikolas Lessmann; Margriet G A Sattler; Tim Leiner; Pim A de Jong; Arco J Teske; Janneke Verloop; Joan J Penninkhof; Ilonca Vaartjes; Hanneke Meijer; Julia J van Tol-Geerdink; Jean-Philippe Pignol; Desirée H J G van den Bongard; Ivana Išgum; Helena M Verkooijen Journal: JAMA Oncol Date: 2021-07-01 Impact factor: 31.777
Authors: Marleen J Emaus; Ivana Išgum; Sanne G M van Velzen; H J G Desirée van den Bongard; Sofie A M Gernaat; Nikolas Lessmann; Margriet G A Sattler; Arco J Teske; Joan Penninkhof; Hanneke Meijer; Jean-Philippe Pignol; Helena M Verkooijen Journal: BMJ Open Date: 2019-07-27 Impact factor: 2.692
Authors: Sanne G M van Velzen; Nikolas Lessmann; Birgitta K Velthuis; Ingrid E M Bank; Desiree H J G van den Bongard; Tim Leiner; Pim A de Jong; Wouter B Veldhuis; Adolfo Correa; James G Terry; John Jeffrey Carr; Max A Viergever; Helena M Verkooijen; Ivana Išgum Journal: Radiology Date: 2020-02-11 Impact factor: 29.146