Use of an AI Score Combining Cancer Signs, Masking, and Risk to Select Patients for Supplemental Breast Cancer Screening.

Background Mammographic density measurements are used to identify patients who should undergo supplemental imaging for breast cancer detection, but artificial intelligence (AI) image analysis may be more effective. Purpose To assess whether AISmartDensity-an AI-based score integrating cancer signs, masking, and risk-surpasses measurements of mammographic density in identifying patients for supplemental breast imaging after a negative screening mammogram. Materials and Methods This retrospective study included randomly selected individuals who underwent screening mammography at Karolinska University Hospital between January 2008 and December 2015. The models in AISmartDensity were trained and validated using nonoverlapping data. The ability of AISmartDensity to identify future cancer in patients with a negative screening mammogram was evaluated and compared with that of mammographic density models. Sensitivity and positive predictive value (PPV) were calculated for the top 8% of scores, mimicking the proportion of patients in the Breast Imaging Reporting and Data System "extremely dense" category. Model performance was evaluated using area under the receiver operating characteristic curve (AUC) and was compared using the DeLong test. Results The study population included 65 325 examinations (median patient age, 53 years [IQR, 47-62 years])-64 870 examinations in healthy patients and 455 examinations in patients with breast cancer diagnosed within 3 years of a negative screening mammogram. The AUC for detecting subsequent cancers was 0.72 and 0.61 (P < .001) for AISmartDensity and the best-performing density model (age-adjusted dense area), respectively. For examinations with scores in the top 8%, AISmartDensity identified 152 of 455 (33%) future cancers with a PPV of 2.91%, whereas the best-performing density model (age-adjusted dense area) identified 57 of 455 (13%) future cancers with a PPV of 1.09% (P < .001). AISmartDensity identified 32% (41 of 130) and 34% (111 of 325) of interval and next-round screen-detected cancers, whereas the best-performing density model (dense area) identified 16% (21 of 130) and 9% (30 of 325), respectively. Conclusion AISmartDensity, integrating cancer signs, masking, and risk, outperformed traditional density models in identifying patients for supplemental imaging after a negative screening mammogram. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Kim and Chang in this issue.

Women's perceptions and attitudes towards the use of AI in mammography in Sweden: a qualitative interview study.

BACKGROUND: Understanding women's perspectives can help to create an effective and acceptable artificial intelligence (AI) implementation for triaging mammograms, ensuring a high proportion of screening-detected cancer. This study aimed to explore Swedish women's perceptions and attitudes towards the use of AI in mammography. METHOD: Semistructured interviews were conducted with 16 women recruited in the spring of 2023 at Capio S:t Görans Hospital, Sweden, during an ongoing clinical trial of AI in screening (ScreenTrustCAD, NCT04778670) with Philips equipment. The interview transcripts were analysed using inductive thematic content analysis. RESULTS: In general, women viewed AI as an excellent complementary tool to help radiologists in their decision-making, rather than a complete replacement of their expertise. To trust the AI, the women requested a thorough evaluation, transparency about AI usage in healthcare, and the involvement of a radiologist in the assessment. They would rather be more worried because of being called in more often for scans than risk having overlooked a sign of cancer. They expressed substantial trust in the healthcare system if the implementation of AI was to become a standard practice. CONCLUSION: The findings suggest that the interviewed women, in general, hold a positive attitude towards the implementation of AI in mammography; nonetheless, they expect and demand more from an AI than a radiologist. Effective communication regarding the role and limitations of AI is crucial to ensure that patients understand the purpose and potential outcomes of AI-assisted healthcare.

Differences and similarities in false interpretations by AI CAD and radiologists in screening mammography.

OBJECTIVE: We aimed to evaluate the false interpretations between artificial intelligence (AI) and radiologists in screening mammography to get a better understanding of how the distribution of diagnostic mistakes might change when moving from entirely radiologist-driven to AI-integrated breast cancer screening. METHODS AND MATERIALS: This retrospective case-control study was based on a mammography screening cohort from 2008 to 2015. The final study population included screening examinations for 714 women diagnosed with breast cancer and 8029 randomly selected healthy controls. Oversampling of controls was applied to attain a similar cancer proportion as in the source screening cohort. We examined how false-positive (FP) and false-negative (FN) assessments by AI, the first reader (RAD 1) and the second reader (RAD 2), were associated with age, density, tumor histology and cancer invasiveness in a single- and double-reader setting. RESULTS: For each reader, the FN assessments were distributed between low- and high-density females with 53 (42%) and 72 (58%) for AI; 59 (36%) and 104 (64%) for RAD 1 and 47 (36%) and 84 (64%) for RAD 2. The corresponding numbers for FP assessments were 1820 (47%) and 2016 (53%) for AI; 1568 (46%) and 1834 (54%) for RAD 1 and 1190 (43%) and 1610 (58%) for RAD 2. For ductal cancer, the FN assessments were 79 (77%) for AI CAD; with 120 (83%) for RAD 1 and with 96 (16%) for RAD 2. For the double-reading simulation, the FP assessments were distributed between younger and older females with 2828 (2.5%) and 1554 (1.4%) for RAD 1 + RAD 2; 3850 (3.4%) and 2940 (2.6%) for AI+RAD 1 and 3430 (3%) and 2772 (2.5%) for AI+RAD 2. CONCLUSION: The most pronounced decrease in FN assessments was noted for females over the age of 55 and for high density-women. In conclusion, AI could have an important complementary role when combined with radiologists to increase sensitivity for high-density and older females. ADVANCES IN KNOWLEDGE: Our results highlight the potential impact of integrating AI in breast cancer screening, particularly to improve interpretation accuracy. The use of AI could enhance screening outcomes for high-density and older females.

Artificial intelligence for breast cancer detection in screening mammography in Sweden: a prospective, population-based, paired-reader, non-inferiority study.

BACKGROUND: Artificial intelligence (AI) as an independent reader of screening mammograms has shown promise, but there are few prospective studies. Our aim was to conduct a prospective clinical trial to examine how AI affects cancer detection and false positive findings in a real-world setting. METHODS: ScreenTrustCAD was a prospective, population-based, paired-reader, non-inferiority study done at the Capio Sankt Göran Hospital in Stockholm, Sweden. Consecutive women without breast implants aged 40-74 years participating in population-based screening in the geographical uptake area of the study hospital were included. The primary outcome was screen-detected breast cancer within 3 months of mammography, and the primary analysis was to assess non-inferiority (non-inferiority margin of 0·15 relative reduction in breast cancer diagnoses) of double reading by one radiologist plus AI compared with standard-of-care double reading by two radiologists. We also assessed single reading by AI alone and triple reading by two radiologists plus AI compared with standard-of-care double reading by two radiologists. This study is registered with ClinicalTrials.gov, NCT04778670. FINDINGS: From April 1, 2021, to June 9, 2022, 58 344 women aged 40-74 years underwent regular mammography screening, of whom 55 581 were included in the study. 269 (0·5%) women were diagnosed with screen-detected breast cancer based on an initial positive read: double reading by one radiologist plus AI was non-inferior for cancer detection compared with double reading by two radiologists (261 [0·5%] vs 250 [0·4%] detected cases; relative proportion 1·04 [95% CI 1·00-1·09]). Single reading by AI (246 [0·4%] vs 250 [0·4%] detected cases; relative proportion 0·98 [0·93-1·04]) and triple reading by two radiologists plus AI (269 [0·5%] vs 250 [0·4%] detected cases; relative proportion 1·08 [1·04-1·11]) were also non-inferior to double reading by two radiologists. INTERPRETATION: Replacing one radiologist with AI for independent reading of screening mammograms resulted in a 4% higher non-inferior cancer detection rate compared with radiologist double reading. Our study suggests that AI in the study setting has potential for controlled implementation, which would include risk management and real-world follow-up of performance. FUNDING: Swedish Research Council, Swedish Cancer Society, Region Stockholm, and Lunit.

Implications for downstream workload based on calibrating an artificial intelligence detection algorithm by standalone-reader or combined-reader sensitivity matching.

Purpose: In double-reading of screening mammograms, artificial intelligence (AI) algorithms hold promise as a potential replacement for one of the two readers. The choice of operating point, or abnormality threshold, for the AI algorithm will affect cancer detection and workload. In our retrospective study, the baseline approach was based on matching stand-alone reader sensitivity, while the alternative approach was based on matching the combined-reader sensitivity of two humans and of AI plus human. Approach: Full-field digital screening mammograms within the Stockholm County area between February 1, 2012, and December 30, 2015, acquired on Philips equipment, were collected. All exams of women with breast cancer within 23 months of screening and a random selection of healthy controls were included. An exam-level continuous AI abnormality score was generated (Insight MMG from Lunit Inc). Sensitivity and abnormal interpretation rates were estimated for operating points defined by the standalone-reader approach and the combined-reader approach. Results: The study population included 1684 exams of women with breast cancer and 5024 exams of healthy women. Observations of healthy women were up-sampled to attain a realistic proportion of cancer. The observed sensitivity for reader 1, 2 and 1+2 was 69.7%, 75.6%, and 78.6%, respectively, at an abnormal interpretation rate of 4.4%, 4.6%, and 6.1%, respectively. For the combination of reader 1 + AI we estimated a sensitivity of 82.4% for standalone-reader matching and 78.6% for combined-reader matching, at an abnormal interpretation rate of 12.6% and 7.0%, respectively. Conclusions: Setting the operating point by matching stand-alone AI stand-alone with a radiologist will nearly double the downstream workload compared to a modest increase of 15% for the alternative method of matching sensitivity between the combination of AI and a radiologist with two radiologists.

False-negative rate in the extended prospective TATTOO trial evaluating targeted axillary dissection by carbon tattooing in clinically node-positive breast cancer patients receiving neoadjuvant systemic therapy.

PURPOSE: In clinically node-positive breast cancer patients receiving neoadjuvant systemic therapy (NST), nodal metastases can be initially marked and then removed during surgical axillary staging. Marking methods vary significantly in terms of feasibility and cost. The purpose of the extended TATTOO trial was to report on the false-negative rate (FNR) of the low-cost method carbon tattooing. METHODS: The international prospective single-arm TATTOO trial included clinically node-positive breast cancer patients planned for NST from November 2017 to January 2021. For the present analysis, patients who received both the targeted procedure with or without an additional sentinel lymph node (SLN) biopsy and a completion axillary lymph node dissection (ALND) were selected. Primary endpoint was the FNR. RESULTS: Out of 172 included patients, 149 had undergone a completion ALND. The detection rate for the tattooed node was 94.6% (141 out of 149). SLN biopsy was attempted in 132 out of 149 patients with a detection rate of 91.7% (121 out of 132). SLN and tattooed node were identical in 58 out of 121 individuals (47.9%). The combined procedure, i.e. targeted axillary dissection (TAD) was successful in 147 of 149 cases (98.7%). Four out of 65 patients with a clinically node-negative status after NST had a negative TAD but metastases on ALND, corresponding to a FNR of 6.2%. All false-negative TAD procedures were performed in the first 2 years of the trial (2018-2019, p = 0.022). CONCLUSION: Carbon tattooing is a feasible marking method for TAD with a high detection rate and an acceptably low FNR. The TATTOO trial was preregistered as prospective trial before initiation at the University of Rostock, Germany (DRKS00013169).

Effect of artificial intelligence-based triaging of breast cancer screening mammograms on cancer detection and radiologist workload: a retrospective simulation study.

BACKGROUND: We examined the potential change in cancer detection when using an artificial intelligence (AI) cancer-detection software to triage certain screening examinations into a no radiologist work stream, and then after regular radiologist assessment of the remainder, triage certain screening examinations into an enhanced assessment work stream. The purpose of enhanced assessment was to simulate selection of women for more sensitive screening promoting early detection of cancers that would otherwise be diagnosed as interval cancers or as next-round screen-detected cancers. The aim of the study was to examine how AI could reduce radiologist workload and increase cancer detection. METHODS: In this retrospective simulation study, all women diagnosed with breast cancer who attended two consecutive screening rounds were included. Healthy women were randomly sampled from the same cohort; their observations were given elevated weight to mimic a frequency of 0·7% incident cancer per screening interval. Based on the prediction score from a commercially available AI cancer detector, various cutoff points for the decision to channel women to the two new work streams were examined in terms of missed and additionally detected cancer. FINDINGS: 7364 women were included in the study sample: 547 were diagnosed with breast cancer and 6817 were healthy controls. When including 60%, 70%, or 80% of women with the lowest AI scores in the no radiologist stream, the proportion of screen-detected cancers that would have been missed were 0, 0·3% (95% CI 0·0-4·3), or 2·6% (1·1-5·4), respectively. When including 1% or 5% of women with the highest AI scores in the enhanced assessment stream, the potential additional cancer detection was 24 (12%) or 53 (27%) of 200 subsequent interval cancers, respectively, and 48 (14%) or 121 (35%) of 347 next-round screen-detected cancers, respectively. INTERPRETATION: Using a commercial AI cancer detector to triage mammograms into no radiologist assessment and enhanced assessment could potentially reduce radiologist workload by more than half, and pre-emptively detect a substantial proportion of cancers otherwise diagnosed later. FUNDING: Stockholm City Council.

External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms.

Importance: A computer algorithm that performs at or above the level of radiologists in mammography screening assessment could improve the effectiveness of breast cancer screening. Objective: To perform an external evaluation of 3 commercially available artificial intelligence (AI) computer-aided detection algorithms as independent mammography readers and to assess the screening performance when combined with radiologists. Design, Setting, and Participants: This retrospective case-control study was based on a double-reader population-based mammography screening cohort of women screened at an academic hospital in Stockholm, Sweden, from 2008 to 2015. The study included 8805 women aged 40 to 74 years who underwent mammography screening and who did not have implants or prior breast cancer. The study sample included 739 women who were diagnosed as having breast cancer (positive) and a random sample of 8066 healthy controls (negative for breast cancer). Main Outcomes and Measures: Positive follow-up findings were determined by pathology-verified diagnosis at screening or within 12 months thereafter. Negative follow-up findings were determined by a 2-year cancer-free follow-up. Three AI computer-aided detection algorithms (AI-1, AI-2, and AI-3), sourced from different vendors, yielded a continuous score for the suspicion of cancer in each mammography examination. For a decision of normal or abnormal, the cut point was defined by the mean specificity of the first-reader radiologists (96.6%). Results: The median age of study participants was 60 years (interquartile range, 50-66 years) for 739 women who received a diagnosis of breast cancer and 54 years (interquartile range, 47-63 years) for 8066 healthy controls. The cases positive for cancer comprised 618 (84%) screen detected and 121 (16%) clinically detected within 12 months of the screening examination. The area under the receiver operating curve for cancer detection was 0.956 (95% CI, 0.948-0.965) for AI-1, 0.922 (95% CI, 0.910-0.934) for AI-2, and 0.920 (95% CI, 0.909-0.931) for AI-3. At the specificity of the radiologists, the sensitivities were 81.9% for AI-1, 67.0% for AI-2, 67.4% for AI-3, 77.4% for first-reader radiologist, and 80.1% for second-reader radiologist. Combining AI-1 with first-reader radiologists achieved 88.6% sensitivity at 93.0% specificity (abnormal defined by either of the 2 making an abnormal assessment). No other examined combination of AI algorithms and radiologists surpassed this sensitivity level. Conclusions and Relevance: To our knowledge, this study is the first independent evaluation of several AI computer-aided detection algorithms for screening mammography. The results of this study indicated that a commercially available AI computer-aided detection algorithm can assess screening mammograms with a sufficient diagnostic performance to be further evaluated as an independent reader in prospective clinical trials. Combining the first readers with the best algorithm identified more cases positive for cancer than combining the first readers with second readers.

Range of Radiologist Performance in a Population-based Screening Cohort of 1 Million Digital Mammography Examinations.

Background There is great interest in developing artificial intelligence (AI)-based computer-aided detection (CAD) systems for use in screening mammography. Comparative performance benchmarks from true screening cohorts are needed. Purpose To determine the range of human first-reader performance measures within a population-based screening cohort of 1 million screening mammograms to gauge the performance of emerging AI CAD systems. Materials and Methods This retrospective study consisted of all screening mammograms in women aged 40-74 years in Stockholm County, Sweden, who underwent screening with full-field digital mammography between 2008 and 2015. There were 110 interpreting radiologists, of whom 24 were defined as high-volume readers (ie, those who interpreted more than 5000 annual screening mammograms). A true-positive finding was defined as the presence of a pathology-confirmed cancer within 12 months. Performance benchmarks included sensitivity and specificity, examined per quartile of radiologists' performance. First-reader sensitivity was determined for each tumor subgroup, overall and by quartile of high-volume reader sensitivity. Screening outcomes were examined based on the first reader's sensitivity quartile with 10 000 screening mammograms per quartile. Linear regression models were fitted to test for a linear trend across quartiles of performance. Results A total of 418 041 women (mean age, 54 years ± 10 [standard deviation]) were included, and 1 186 045 digital mammograms were evaluated, with 972 899 assessed by high-volume readers. Overall sensitivity was 73% (95% confidence interval [CI]: 69%, 77%), and overall specificity was 96% (95% CI: 95%, 97%). The mean values per quartile of high-volume reader performance ranged from 63% to 84% for sensitivity and from 95% to 98% for specificity. The sensitivity difference was very large for basal cancers, with the least sensitive and most sensitive high-volume readers detecting 53% and 89% of cancers, respectively (P < .001). Conclusion Benchmarks showed a wide range of performance differences between high-volume readers. Sensitivity varied by tumor characteristics. © RSNA, 2020 Online supplemental material is available for this article.

A Multi-million Mammography Image Dataset and Population-Based Screening Cohort for the Training and Evaluation of Deep Neural Networks-the Cohort of Screen-Aged Women (CSAW).

For AI researchers, access to a large and well-curated dataset is crucial. Working in the field of breast radiology, our aim was to develop a high-quality platform that can be used for evaluation of networks aiming to predict breast cancer risk, estimate mammographic sensitivity, and detect tumors. Our dataset, Cohort of Screen-Aged Women (CSAW), is a population-based cohort of all women 40 to 74 years of age invited to screening in the Stockholm region, Sweden, between 2008 and 2015. All women were invited to mammography screening every 18 to 24 months free of charge. Images were collected from the PACS of the three breast centers that completely cover the region. DICOM metadata were collected together with the images. Screening decisions and clinical outcome data were collected by linkage to the regional cancer center registers. Incident cancer cases, from one center, were pixel-level annotated by a radiologist. A separate subset for efficient evaluation of external networks was defined for the uptake area of one center. The collection and use of the dataset for the purpose of AI research has been approved by the Ethical Review Board. CSAW included 499,807 women invited to screening between 2008 and 2015 with a total of 1,182,733 completed screening examinations. Around 2 million mammography images have currently been collected, including all images for women who developed breast cancer. There were 10,582 women diagnosed with breast cancer; for 8463, it was their first breast cancer. Clinical data include biopsy-verified breast cancer diagnoses, histological origin, tumor size, lymph node status, Elston grade, and receptor status. One thousand eight hundred ninety-one images of 898 women had tumors pixel level annotated including any tumor signs in the prior negative screening mammogram. Our dataset has already been used for evaluation by several research groups. We have defined a high-volume platform for training and evaluation of deep neural networks in the domain of mammographic imaging.

Comparison of a Deep Learning Risk Score and Standard Mammographic Density Score for Breast Cancer Risk Prediction.

Background Most risk prediction models for breast cancer are based on questionnaires and mammographic density assessments. By training a deep neural network, further information in the mammographic images can be considered. Purpose To develop a risk score that is associated with future breast cancer and compare it with density-based models. Materials and Methods In this retrospective study, all women aged 40-74 years within the Karolinska University Hospital uptake area in whom breast cancer was diagnosed in 2013-2014 were included along with healthy control subjects. Network development was based on cases diagnosed from 2008 to 2012. The deep learning (DL) risk score, dense area, and percentage density were calculated for the earliest available digital mammographic examination for each woman. Logistic regression models were fitted to determine the association with subsequent breast cancer. False-negative rates were obtained for the DL risk score, age-adjusted dense area, and age-adjusted percentage density. Results A total of 2283 women, 278 of whom were later diagnosed with breast cancer, were evaluated. The age at mammography (mean, 55.7 years vs 54.6 years; P < .001), the dense area (mean, 38.2 cm2 vs 34.2 cm2; P < .001), and the percentage density (mean, 25.6% vs 24.0%; P < .001) were higher among women diagnosed with breast cancer than in those without a breast cancer diagnosis. The odds ratios and areas under the receiver operating characteristic curve (AUCs) were higher for age-adjusted DL risk score than for dense area and percentage density: 1.56 (95% confidence interval [CI]: 1.48, 1.64; AUC, 0.65), 1.31 (95% CI: 1.24, 1.38; AUC, 0.60), and 1.18 (95% CI: 1.11, 1.25; AUC, 0.57), respectively (P < .001 for AUC). The false-negative rate was lower: 31% (95% CI: 29%, 34%), 36% (95% CI: 33%, 39%; P = .006), and 39% (95% CI: 37%, 42%; P < .001); this difference was most pronounced for more aggressive cancers. Conclusion Compared with density-based models, a deep neural network can more accurately predict which women are at risk for future breast cancer, with a lower false-negative rate for more aggressive cancers. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Bahl in this issue.

Clopidogrel Resistance after Minor Ischemic Stroke or Transient Ischemic Attack is Associated with Radiological Cerebral Small-Vessel Disease.

BACKGROUND: The objective of this study was to compare nonresponders (NR) and responders (R) to clopidogrel with respect to presence of microvascular and macrovascular pathology in a cohort of patients with recent minor ischemic stroke (IS) or transient ischemic attack (TIA). METHODS: Seventy-two patients treated with clopidogrel after IS or TIA were evaluated 1 month after onset. Platelet aggregation was measured by multiple electrode aggregometry (Multiplate). Nonresponse was defined according to recent consensus. The degree of cerebral small-vessel disease (cSVD) was evaluated on computed tomography scans of the brain using Fazekas scale for white matter changes. Carotid atherosclerosis was evaluated by ultrasound or computed tomography/magnetic resonance angiography. RESULTS: Twenty-two percent of patients were NR. Moderate to extensive cSVD was more common for NR than R, 56% versus 25%, odds ratio 3.9 (1.2-12), P = .03. Correspondingly, 39% of patients with cSVD were NR versus 14% of patients with no or mild cSVD. No differences were found between NR and R in prevalence or severity of carotid atherosclerosis. NR had higher platelet aggregation response than R after stimulation with arachidonic acid or thrombin receptor-activating peptide, indicating a general platelet hyperreactivity. In a univariate analysis, hypertension, previous IS, glucose intolerance, pulse pressure above median, and presence of moderate to extensive cSVD were associated with the NR phenotype. CONCLUSIONS: Nonresponsiveness to clopidogrel after minor IS or TIA is associated with radiological cSVD but not with carotid atherosclerosis. PRACTICE/IMPLICATIONS: Measurement of platelet function is warranted in patients with cSVD. Larger studies on alternative or tailored antiplatelet treatment for these patients should be initiated.