Can AI serve as an independent second reader of mammograms? a simulation study
| Autor: | Albert Gubern-Mérida, Matthew G. Wallis, Sophia Zackrisson, Ioannis Sechopoulos, Paola Clauser, Thomas Mertelmeier, Gisella Gennaro, Alejandro Rodriguez-Ruiz, Ingvar Andersson, Ritse M. Mann, Thomas H. Helbich, Mireille J. M. Broeders, Margarita Chevalier, Kristina Lång |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
medicine.diagnostic_test
Bootstrapping Computer science business.industry media_common.quotation_subject Double reading Reading strategy Workload computer.software_genre Breast cancer screening Reading (process) medicine Screening programs Mammography Artificial intelligence business computer Natural language processing media_common |
| Zdroj: | 15th International Workshop on Breast Imaging (IWBI2020). |
| Popis: | In this study we used a large previously built database of 2,892 mammograms and 31,650 single mammogram radiologists’ assessments to simulate the impact of replacing one radiologist by an AI system in a double reading setting. The double human reading scenario and the double hybrid reading scenario (second reader replaced by an AI system) were simulated via bootstrapping using different combinations of mammograms and radiologists from the database. The main outcomes of each scenario were sensitivity, specificity and workload (number of necessary readings). The results showed that when using AI as a second reader, workload can be reduced by 44%, sensitivity remains similar (difference -0.1%; 95% CI = - 4.1%, 3.9%), and specificity increases by 5.3% (P |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|