Martin Tammemagi1, Alex J Ritchie2, Sukhinder Atkar-Khattra3, Brendan Dougherty4, Calvin Sanghera3, John R Mayo5, Ren Yuan3, Daria Manos6, Annette M McWilliams7, Heidi Schmidt8, Michel Gingras9, Sergio Pasian9, Lori Stewart10, Scott Tsai10, Jean M Seely11, Paul Burrowes12, Rick Bhatia13, Ehsan A Haider10, Colm Boylan10, Colin Jacobs14, Bram van Ginneken14, Ming-Sound Tsao8, Stephen Lam15. 1. Department of Health Sciences, Brock University, St. Catharine's, Ontario, Canada. 2. Royal Brisbane and Women's Hospital, Brisbane, Australia. 3. British Columbia Cancer, Vancouver, British Columbia, Canada. 4. Flinders Medical Centre, Adelaide, Australia. 5. Department of Radiology, Vancouver Coastal Health, Vancouver, British Columbia, Canada. 6. Dalhousie University, Halifax, Nova Scotia, Canada. 7. Fiona Stanley Hospital and Sir Charles Gairdner Hospital, Perth, Western Australia, Australia. 8. University Health Network and Princess Margaret Cancer Centre, Toronto, Ontario, Canada. 9. University Institute of Cardiology and Pneumology of Quebec, Quebec, Canada. 10. Department of Diagnostic Imaging, Henderson Hospital, Hamilton, Ontario, Canada. 11. Ottawa Hospital Research Institute and the University of Ottawa, Ottawa, Ontario, Canada. 12. University of Calgary, Foothills Medical Centre, Calgary, Alberta, Canada. 13. Memorial University, St. John's, Newfoundland, Canada. 14. Radboud University Medical Center, Nijmegen, The Netherlands. 15. British Columbia Cancer, Vancouver, British Columbia, Canada. Electronic address: slam@bccancer.bc.ca.
Abstract
OBJECTIVE: In lung cancer screening practice low-dose computed tomography, diameter, and volumetric measurement have been used in the management of screen-detected lung nodules. The aim of this study was to compare the performance of nodule malignancy risk prediction tools using diameter or volume and between computer-aided detection (CAD) and radiologist measurements. METHODS: Multivariable logistic regression models were prepared by using data from two multicenter lung cancer screening trials. For model development and validation, baseline low-dose computed tomography scans from the Pan-Canadian Early Detection of Lung Cancer Study and a subset of National Lung Screening Trial (NLST) scans with lung nodules 3 mm or more in mean diameter were analyzed by using the CIRRUS Lung Screening Workstation (Radboud University Medical Center, Nijmegen, the Netherlands). In the NLST sample, nodules with cancer had been matched on the basis of size to nodules without cancer. RESULTS: Both CAD-based mean diameter and volume models showed excellent discrimination and calibration, with similar areas under the receiver operating characteristic curves of 0.947. The two CAD models had predictive performance similar to that of the radiologist-based model. In the NLST validation data, the CAD mean diameter and volume models also demonstrated excellent discrimination: areas under the curve of 0.810 and 0.821, respectively. These performance statistics are similar to those of the Pan-Canadian Early Detection of Lung Cancer Study malignancy probability model with use of these data and radiologist-measured maximum diameter. CONCLUSION: Either CAD-based nodule diameter or volume can be used to assist in predicting a nodule's malignancy risk.
OBJECTIVE: In lung cancer screening practice low-dose computed tomography, diameter, and volumetric measurement have been used in the management of screen-detected lung nodules. The aim of this study was to compare the performance of nodule malignancy risk prediction tools using diameter or volume and between computer-aided detection (CAD) and radiologist measurements. METHODS: Multivariable logistic regression models were prepared by using data from two multicenter lung cancer screening trials. For model development and validation, baseline low-dose computed tomography scans from the Pan-Canadian Early Detection of Lung Cancer Study and a subset of National Lung Screening Trial (NLST) scans with lung nodules 3 mm or more in mean diameter were analyzed by using the CIRRUS Lung Screening Workstation (Radboud University Medical Center, Nijmegen, the Netherlands). In the NLST sample, nodules with cancer had been matched on the basis of size to nodules without cancer. RESULTS: Both CAD-based mean diameter and volume models showed excellent discrimination and calibration, with similar areas under the receiver operating characteristic curves of 0.947. The two CAD models had predictive performance similar to that of the radiologist-based model. In the NLST validation data, the CAD mean diameter and volume models also demonstrated excellent discrimination: areas under the curve of 0.810 and 0.821, respectively. These performance statistics are similar to those of the Pan-Canadian Early Detection of Lung Cancer Study malignancy probability model with use of these data and radiologist-measured maximum diameter. CONCLUSION: Either CAD-based nodule diameter or volume can be used to assist in predicting a nodule's malignancy risk.
Authors: Matthijs Oudkerk; ShiYuan Liu; Marjolein A Heuvelmans; Joan E Walter; John K Field Journal: Nat Rev Clin Oncol Date: 2020-10-12 Impact factor: 66.675
Authors: Emeline Darçot; Mario Jreige; David C Rotzinger; Stacey Gidoin Tuyet Van; Alessio Casutt; Jean Delacoste; Julien Simons; Olivier Long; Flore Buela; Jean-Baptiste Ledoux; John O Prior; Alban Lovis; Catherine Beigelman-Aubry Journal: Front Med (Lausanne) Date: 2022-04-28