Artificial Intelligence as Supporting Reader in Breast Screening: A Novel Workflow to Preserve Quality and Reduce Workload

Abstract

Objective To evaluate the effectiveness of a new strategy for using artificial intelligence (AI) as supporting reader for the detection of breast cancer in mammography-based double reading screening practice. Methods Large-scale multi-site, multi-vendor data were used to retrospectively evaluate a new paradigm of AI-supported reading. Here, the AI served as the second reader only if it agrees with the recall/no-recall decision of the first human reader. Otherwise, a second human reader made an assessment followed by the standard clinical workflow. The data included 280 594 cases from 180 542 female participants screened for breast cancer at seven screening sites in two countries and using equipment from four hardware vendors. The statistical analysis included non-inferiority and superiority testing of cancer screening performance and evaluation of the reduction in workload, measured as arbitration rate and number of cases requiring second human reading. Results AI as a supporting reader was found to be superior or non-inferior on all screening metrics compared with human double reading while reducing the number of cases requiring second human reading by up to 87% (245 395/280 594). Compared with AI as an independent reader, the number of cases referred to arbitration was reduced from 13% (35 199/280 594) to 2% (5056/280 594). Conclusion The simulation indicates that the proposed workflow retains screening performance of human double reading while substantially reducing the workload. Further research should study the impact on the second human reader because they would only assess cases in which the AI prediction and first human reader disagree.

Saliency of breast lesions in breast cancer detection using artificial intelligence

“…Recent literature has proposed that stand-alone AI algorithms could, independently or in conjunction with a radiologist, detect breast cancer or triage mammograms. Triaged normal studies could be read in an adapted manner (e.g., by only one reader), and mammograms with suspicious findings could be prioritized 37 . AI systems that detect mammograms with findings suggestive of malignancy, albeit with limited ability to localize the tumor, would be especially beneficial for the triaging purposes of the mammograms.…”

Expanding Horizons: The Realities of CAD, the Promise of Artificial Intelligence, and Machine Learning’s Role in Breast Imaging beyond Screening Mammography

“…In this vein of continuous improvement the proficiency of AI has drastically exceeded the performance of traditional CAD techniques, approaching or exceeding the accuracy of radiologists at various tasks in mammography including lesion detection [ 1 , 8 , 9 ]. AI is also gaining increasing traction for a role as a digital second reader [ 10 , 11 ], with some studies proposing the use of AI to sort confidently negative studies for worklist reduction [ 12 , 13 ].…”

Systematic Review of Challenges in Implementing Artificial Intelligence in Breast Cancer Screening Programs: Towards a Framework for Safe Adoption (Preprint)

“…The need for a comprehensive AI governance framework is critical as the medical community considers adopting AI as second readers in screening programs. Hence there is an urgent need to develop a holistic AI governance framework in the face of the ongoing consideration of adopting AI as second readers in screening programs [7][8][9]. characteristics of the institution and its broader environment, as well as the attributes of the individuals delivering the service, who are often practitioners rather than researchers [10,11].…”