Kristina Lång1,2, Magnus Dustler3, Victor Dahlblom3,4, Anna Åkesson5, Ingvar Andersson3,6, Sophia Zackrisson3,4. 1. Diagnostic Radiology, Department of Translational Medicine, Lund University, Inga Maria Nilssons gata 47, SE-20502, Malmö, Sweden. kristina.lang@med.lu.se. 2. Unilabs Mammography Unit, Skåne University Hospital, Jan Waldenströms gata 22, SE-20502, Malmö, Sweden. kristina.lang@med.lu.se. 3. Diagnostic Radiology, Department of Translational Medicine, Lund University, Inga Maria Nilssons gata 47, SE-20502, Malmö, Sweden. 4. Radiology Department, Skåne University Hospital, Inga Maria Nilssons gata 47, SE-20502, Malmö, Sweden. 5. Clinical Studies Sweden - Forum South, Skåne University Hospital, Lund, Sweden. 6. Unilabs Mammography Unit, Skåne University Hospital, Jan Waldenströms gata 22, SE-20502, Malmö, Sweden.
Abstract
OBJECTIVES: To evaluate the potential of artificial intelligence (AI) to identify normal mammograms in a screening population. METHODS: In this retrospective study, 9581 double-read mammography screening exams including 68 screen-detected cancers and 187 false positives, a subcohort of the prospective population-based Malmö Breast Tomosynthesis Screening Trial, were analysed with a deep learning-based AI system. The AI system categorises mammograms with a cancer risk score increasing from 1 to 10. The effect on cancer detection and false positives of excluding mammograms below different AI risk thresholds from reading by radiologists was investigated. A panel of three breast radiologists assessed the radiographic appearance, type, and visibility of screen-detected cancers assigned low-risk scores (≤ 5). The reduction of normal exams, cancers, and false positives for the different thresholds was presented with 95% confidence intervals (CI). RESULTS: If mammograms scored 1 and 2 were excluded from screen-reading, 1829 (19.1%; 95% CI 18.3-19.9) exams could be removed, including 10 (5.3%; 95% CI 2.1-8.6) false positives but no cancers. In total, 5082 (53.0%; 95% CI 52.0-54.0) exams, including 7 (10.3%; 95% CI 3.1-17.5) cancers and 52 (27.8%; 95% CI 21.4-34.2) false positives, had low-risk scores. All, except one, of the seven screen-detected cancers with low-risk scores were judged to be clearly visible. CONCLUSIONS: The evaluated AI system can correctly identify a proportion of a screening population as cancer-free and also reduce false positives. Thus, AI has the potential to improve mammography screening efficiency. KEY POINTS: • Retrospective study showed that AI can identify a proportion of mammograms as normal in a screening population. • Excluding normal exams from screening using AI can reduce false positives.
OBJECTIVES: To evaluate the potential of artificial intelligence (AI) to identify normal mammograms in a screening population. METHODS: In this retrospective study, 9581 double-read mammography screening exams including 68 screen-detected cancers and 187 false positives, a subcohort of the prospective population-based Malmö Breast Tomosynthesis Screening Trial, were analysed with a deep learning-based AI system. The AI system categorises mammograms with a cancer risk score increasing from 1 to 10. The effect on cancer detection and false positives of excluding mammograms below different AI risk thresholds from reading by radiologists was investigated. A panel of three breast radiologists assessed the radiographic appearance, type, and visibility of screen-detected cancers assigned low-risk scores (≤ 5). The reduction of normal exams, cancers, and false positives for the different thresholds was presented with 95% confidence intervals (CI). RESULTS: If mammograms scored 1 and 2 were excluded from screen-reading, 1829 (19.1%; 95% CI 18.3-19.9) exams could be removed, including 10 (5.3%; 95% CI 2.1-8.6) false positives but no cancers. In total, 5082 (53.0%; 95% CI 52.0-54.0) exams, including 7 (10.3%; 95% CI 3.1-17.5) cancers and 52 (27.8%; 95% CI 21.4-34.2) false positives, had low-risk scores. All, except one, of the seven screen-detected cancers with low-risk scores were judged to be clearly visible. CONCLUSIONS: The evaluated AI system can correctly identify a proportion of a screening population as cancer-free and also reduce false positives. Thus, AI has the potential to improve mammography screening efficiency. KEY POINTS: • Retrospective study showed that AI can identify a proportion of mammograms as normal in a screening population. • Excluding normal exams from screening using AI can reduce false positives.
Entities:
Keywords:
Artificial intelligence; Breast cancer; Mammography; Mass screening
Authors: Alejandro Rodríguez-Ruiz; Elizabeth Krupinski; Jan-Jurre Mordang; Kathy Schilling; Sylvia H Heywang-Köbrunner; Ioannis Sechopoulos; Ritse M Mann Journal: Radiology Date: 2018-11-20 Impact factor: 11.105
Authors: Alejandro Rodriguez-Ruiz; Kristina Lång; Albert Gubern-Merida; Jonas Teuwen; Mireille Broeders; Gisella Gennaro; Paola Clauser; Thomas H Helbich; Margarita Chevalier; Thomas Mertelmeier; Matthew G Wallis; Ingvar Andersson; Sophia Zackrisson; Ioannis Sechopoulos; Ritse M Mann Journal: Eur Radiol Date: 2019-04-16 Impact factor: 5.315
Authors: Xueping Jing; Mirjam Wielema; Ludo J Cornelissen; Margo van Gent; Willie M Iwema; Sunyi Zheng; Paul E Sijens; Matthijs Oudkerk; Monique D Dorrius; Peter M A van Ooijen Journal: Eur Radiol Date: 2022-05-26 Impact factor: 5.315
Authors: Marthe Larsen; Camilla F Aglen; Christoph I Lee; Solveig R Hoff; Håkon Lund-Hanssen; Kristina Lång; Jan F Nygård; Giske Ursin; Solveig Hofvind Journal: Radiology Date: 2022-03-29 Impact factor: 29.146
Authors: Hyunsuk Yoo; Eun Young Kim; Hyungjin Kim; Ye Ra Choi; Moon Young Kim; Sung Ho Hwang; Young Joong Kim; Young Jun Cho; Kwang Nam Jin Journal: Korean J Radiol Date: 2022-10 Impact factor: 7.109
Authors: Karoline Freeman; Julia Geppert; Chris Stinton; Daniel Todkill; Samantha Johnson; Aileen Clarke; Sian Taylor-Phillips Journal: BMJ Date: 2021-09-01