"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Mammography screening supported by deep learning-based artificial intelligence (AI) solutions can potentially reduce workload without compromising breast cancer detection accuracy, but the site of deployment in the workflow might be crucial. This retrospective study compared three simulated AI-integrated screening scenarios with standard double reading with arbitration in a sample of 249,402 mammograms from a representative screening population. A commercial AI system replaced the first reader (Scenario 1: Integrated AI_first), the second reader (Scenario 2: Integrated AI_second), or both readers for triaging of low- and high-risk cases (Integrated AI_triage). AI threshold values were partly chosen based on previous validation and fixing screen-read volume reduction at approximately 50% across scenarios. Detection accuracy measures were calculated. Compared with standard double reading, Integrated AI_first showed no evidence of a difference in accuracy metrics except for a higher arbitration rate (+0.99%; P < .001). Integrated AI_second had lower sensitivity (-1.58%; P < 0.001), negative predictive value (NPV) (- 0.01%; P < .001) and recall rate (< 0.06%; P = 0.04), but a higher positive predictive value (PPV) (+0.03%; P < .001) and arbitration rate (+1.22%; P < .001). Integrated AI_triage achieved higher sensitivity (+1.33%; P < .001), PPV (+0.36%; P = .03), and NPV (+0.01%; P < .001) but lower arbitration rate (-0.88%; P < .001). Replacing one or both readers with AI seems feasible, however, the site of application in the workflow can have clinically relevant effects on accuracy and workload. ©RSNA, 2024.

Objectives: To validate an AI system for standalone breast cancer detection on an entire screening population in comparison to first-reading breast radiologists. Materials and methods: All mammography screenings performed between August 4, 2014, and August 15, 2018, in the Region of Southern Denmark with follow-up within 24 months were eligible. Screenings were assessed as normal or abnormal by breast radiologists through double reading with arbitration. For an AI decision of normal or abnormal, two AI-score cut-off points were applied by matching at mean sensitivity (AI_sens) and specificity (AI_spec) of first readers. Accuracy measures were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and recall rate (RR). Results: The sample included 249,402 screenings (149,495 women) and 2033 breast cancers (72.6% screen-detected cancers, 27.4% interval cancers). AI_sens had lower specificity (97.5% vs 97.7%; p < 0.0001) and PPV (17.5% vs 18.7%; p = 0.01) and a higher RR (3.0% vs 2.8%; p < 0.0001) than first readers. AI_spec was comparable to first readers in terms of all accuracy measures. Both AI_sens and AI_spec detected significantly fewer screen-detected cancers (1166 (AI_sens), 1156 (AI_spec) vs 1252; p < 0.0001) but found more interval cancers compared to first readers (126 (AI_sens), 117 (AI_spec) vs 39; p < 0.0001) with varying types of cancers detected across multiple subgroups. Conclusion: Standalone AI can detect breast cancer at an accuracy level equivalent to the standard of first readers when the AI threshold point was matched at first reader specificity. However, AI and first readers detected a different composition of cancers. Clinical relevance statement: Replacing first readers with AI with an appropriate cut-off score could be feasible. AI-detected cancers not detected by radiologists suggest a potential increase in the number of cancers detected if AI is implemented to support double reading within screening, although the clinicopathological characteristics of detected cancers would not change significantly. Key Points: • Standalone AI cancer detection was compared to first readers in a double-read mammography screening population. • Standalone AI matched at first reader specificity showed no statistically significant difference in overall accuracy but detected different cancers. • With an appropriate threshold, AI-integrated screening can increase the number of detected cancers with similar clinicopathological characteristics.

Background: Artificial intelligence (AI) systems are proposed as a replacement of the first reader in double reading within mammography screening. We aimed to assess cancer detection accuracy of an AI system in a Danish screening population. Methods: We retrieved a consecutive screening cohort from the Region of Southern Denmark including all participating women between Aug 4, 2014, and August 15, 2018. Screening mammograms were processed by a commercial AI system and detection accuracy was evaluated in two scenarios, Standalone AI and AI-integrated screening replacing first reader, with first reader and double reading with arbitration (combined reading) as comparators, respectively. Two AI-score cut-off points were applied by matching at mean first reader sensitivity (AI_sens) and specificity (AI_spec). Reference standard was histopathology-proven breast cancer or cancer-free follow-up within 24 months. Coprimary endpoints were sensitivity and specificity, and secondary endpoints were positive predictive value (PPV), negative predictive value (NPV), recall rate, and arbitration rate. Accuracy estimates were calculated using McNemar’s test or exact binomial test. Results: Out of 272,008 screening mammograms from 158,732 women, 257,671 (94.7%) with adequate image data were included in the final analyses. Sensitivity and specificity were 63.7% (95% CI 61.6%-65.8%) and 97.8% (97.7-97.8%) for first reader, and 73.9% (72.0-75.8%) and 97.9% (97.9-98.0%) for combined reading, respectively. Standalone AI_sens showed a lower specificity (-1.3%) and PPV (-6.1%), and a higher recall rate (+ 1.3%) compared to first reader (p < 0.0001 for all), while Standalone AI_spec had a lower sensitivity (-5.1%; p < 0.0001), PPV (-1.3%; p = 0.01) and NPV (-0.04%; p = 0.0002). Compared to combined reading, Integrated AI_sens achieved higher sensitivity (+ 2.3%; p = 0.0004), but lower specificity (-0.6%) and PPV (-3.9%) as well as higher recall rate (+ 0.6%) and arbitration rate (+ 2.2%; p < 0.0001 for all). Integrated AI_spec showed no significant difference in any outcome measures apart from a slightly higher arbitration rate (p < 0.0001). Subgroup analyses showed higher detection of interval cancers by Standalone AI and Integrated AI at both thresholds (p < 0.0001 for all) with a varying composition of detected cancers across multiple subgroups of tumour characteristics. Conclusions: Replacing first reader in double reading with an AI could be feasible but choosing an appropriate AI threshold is crucial to maintaining cancer detection accuracy and workload.

Background: A causal relationship between statin use and intracerebral hemorrhage (ICH) is uncertain. We hypothesized that an association between long-term statin exposure and ICH risk might vary for different ICH locations. Methods: We conducted this analysis using linked Danish nationwide registries. Within the Southern Denmark Region (population 1.2 million), we identified all first-ever cases of ICH between 2009-2018 in persons ages >55 years. Patients with medical record verified diagnoses were classified as having a lobar or non-lobar ICH and matched for age, sex, and calendar year to general population controls. We used a nationwide prescription registry to ascertain prior statin and other medication use that we classified for recency, duration, and intensity. Using conditional logistic regression adjusted for potential confounders, we calculated adjusted odds ratios (aORs) and corresponding 95% Confidence Intervals (CIs) for the risk of lobar and non-lobar ICH. Results: We identified 989 patients with lobar ICH (52.2% women, mean age 76.3-years) who we matched to 39,500 controls, and 1,175 patients with non-lobar ICH (46.5% women, mean age 75.1-years) who we matched to 46,755 controls. Current statin use was associated with a lower risk of lobar (aOR 0.83; 95%CI, 0.70-0.98) and non-lobar ICH (aOR 0.84; 95%CI, 0.72-0.98). Longer duration of statin use was also associated with lower risk of lobar (<1 year: aOR 0.89; 95%CI, 0.69-1.14; ≥1 year to <5years aOR 0.89; 95%CI 0.73-1.09; ≥5 years aOR 0.67; 95%CI, 0.51-0.87; p for trend 0.040) and non-lobar ICH (<1 year: aOR1.00; 95%CI, 0.80-1.25; ≥1 year to <5years aOR 0.88; 95%CI 0.73-1.06; ≥5 years aOR 0.62; 95%CI, 0.48-0.80; p for trend <0.001). Estimates stratified by statin intensity were similar to the main estimates for low-medium intensity therapy (lobar aOR 0.82; non-lobar aOR 0.84); the association with high intensity therapy was neutral. Discussion: We found that statin use was associated with a lower risk of ICH, particularly with longer treatment duration. This association did not vary by hematoma location.