Alexander J Ritchie1, Calvin Sanghera2, Colin Jacobs3, Wei Zhang4, John Mayo5, Heidi Schmidt6, Michel Gingras7, Sergio Pasian7, Lori Stewart8, Scott Tsai8, Daria Manos9, Jean M Seely10, Paul Burrowes11, Rick Bhatia12, Sukhinder Atkar-Khattra2, Bram van Ginneken3, Martin Tammemagi13, Ming Sound Tsao14, Stephen Lam15. 1. Department of Integrative Oncology, British Columbia Cancer Research Center, Vancouver, Canada; Royal Brisbane Hospital, Brisbane, Australia. 2. Department of Integrative Oncology, British Columbia Cancer Research Center, Vancouver, Canada. 3. Diagnostic Image Analysis Group, Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands. 4. Department of Integrative Oncology, British Columbia Cancer Research Center, Vancouver, Canada; Peking University First Hospital, Beijing, China. 5. Department of Radiology, Vancouver Coastal Health, Vancouver, Canada. 6. Department of Radiology, University Health Network-Princess Margaret Cancer Centre, Toronto, Ontario, Canada; Toronto General Hospital, Toronto, Ontario, Canada. 7. Department of Radiology, Institut Universitaire de Cardiologie et de Pneumologie de Québec, Quebec, Canada. 8. Department of Radiology, Juravinski Hospital and Cancer Center, Hamilton, Ontario, Canada. 9. Department of Radiology, Dalhousie University, Halifax, Nova Scotia, Canada. 10. Department of Radiology, The Ottawa Hospital and University of Ottawa, Ottawa, Canada. 11. Department of Radiology, University of Calgary, Calgary, Alberta, Canada. 12. Department of Radiology, Memorial University, Newfoundland, Canada. 13. Department of Health Sciences, Brock University, St. Catharines, Ontario, Canada. 14. Toronto General Hospital, Toronto, Ontario, Canada; Department of Pathology, University Health Network-Princess Margaret Cancer Centre, Toronto, Ontario, Canada. 15. Department of Integrative Oncology, British Columbia Cancer Research Center, Vancouver, Canada. Electronic address: slam@bccancer.bc.ca.
Abstract
OBJECTIVES: To implement a cost-effective low-dose computed tomography (LDCT) lung cancer screening program at the population level, accurate and efficient interpretation of a large volume of LDCT scans is needed. The objective of this study was to evaluate a workflow strategy to identify abnormal LDCT scans in which a technician assisted by computer vision (CV) software acts as a first reader with the aim to improve speed, consistency, and quality of scan interpretation. METHODS: Without knowledge of the diagnosis, a technician reviewed 828 randomly batched scans (136 with lung cancers, 556 with benign nodules, and 136 without nodules) from the baseline Pan-Canadian Early Detection of Lung Cancer Study that had been annotated by the CV software CIRRUS Lung Screening (Diagnostic Image Analysis Group, Nijmegen, The Netherlands). The scans were classified as either normal (no nodules ≥1 mm or benign nodules) or abnormal (nodules or other abnormality). The results were compared with the diagnostic interpretation by Pan-Canadian Early Detection of Lung Cancer Study radiologists. RESULTS: The overall sensitivity and specificity of the technician in identifying an abnormal scan were 97.8% (95% confidence interval: 96.4-98.8) and 98.0% (95% confidence interval: 89.5-99.7), respectively. Of the 112 prevalent nodules that were found to be malignant in follow-up, 92.9% were correctly identified by the technician plus CV compared with 84.8% by the study radiologists. The average time taken by the technician to review a scan after CV processing was 208 ± 120 seconds. CONCLUSIONS: Prescreening CV software and a technician as first reader is a promising strategy for improving the consistency and quality of screening interpretation of LDCT scans.
OBJECTIVES: To implement a cost-effective low-dose computed tomography (LDCT) lung cancer screening program at the population level, accurate and efficient interpretation of a large volume of LDCT scans is needed. The objective of this study was to evaluate a workflow strategy to identify abnormal LDCT scans in which a technician assisted by computer vision (CV) software acts as a first reader with the aim to improve speed, consistency, and quality of scan interpretation. METHODS: Without knowledge of the diagnosis, a technician reviewed 828 randomly batched scans (136 with lung cancers, 556 with benign nodules, and 136 without nodules) from the baseline Pan-Canadian Early Detection of Lung Cancer Study that had been annotated by the CV software CIRRUS Lung Screening (Diagnostic Image Analysis Group, Nijmegen, The Netherlands). The scans were classified as either normal (no nodules ≥1 mm or benign nodules) or abnormal (nodules or other abnormality). The results were compared with the diagnostic interpretation by Pan-Canadian Early Detection of Lung Cancer Study radiologists. RESULTS: The overall sensitivity and specificity of the technician in identifying an abnormal scan were 97.8% (95% confidence interval: 96.4-98.8) and 98.0% (95% confidence interval: 89.5-99.7), respectively. Of the 112 prevalent nodules that were found to be malignant in follow-up, 92.9% were correctly identified by the technician plus CV compared with 84.8% by the study radiologists. The average time taken by the technician to review a scan after CV processing was 208 ± 120 seconds. CONCLUSIONS: Prescreening CV software and a technician as first reader is a promising strategy for improving the consistency and quality of screening interpretation of LDCT scans.
Authors: Arjun Nair; Natalie Gartland; Bruce Barton; Diane Jones; Leigh Clements; Nicholas J Screaton; John A Holemans; Stephen W Duffy; John K Field; David R Baldwin; David M Hansell; Anand Devaraj Journal: Br J Radiol Date: 2016-07-27 Impact factor: 3.039
Authors: Huy M Do; Lillian G Spear; Moozhan Nikpanah; S Mojdeh Mirmomen; Laura B Machado; Alexandra P Toscano; Baris Turkbey; Mohammad Hadi Bagheri; James L Gulley; Les R Folio Journal: Acad Radiol Date: 2020-01 Impact factor: 3.173
Authors: Arjun Nair; Nicholas J Screaton; John A Holemans; Diane Jones; Leigh Clements; Bruce Barton; Natalie Gartland; Stephen W Duffy; David R Baldwin; John K Field; David M Hansell; Anand Devaraj Journal: Eur Radiol Date: 2017-06-22 Impact factor: 5.315
Authors: Sam M Janes; Helen Hall; Mamta Ruparel; Samantha L Quaife; Jennifer L Dickson; Carolyn Horst; Sophie Tisi; James Batty; Nicholas Woznitza; Asia Ahmed; Stephen Burke; Penny Shaw; May Jan Soo; Magali Taylor; Neal Navani; Angshu Bhowmik; David R Baldwin; Stephen W Duffy; Anand Devaraj; Arjun Nair Journal: Eur Radiol Date: 2022-05-14 Impact factor: 7.034