International evaluation of an AI system for breast cancer screening.

Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful1. Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives2. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.

Mammography Breast Cancer Screening Triage Using Deep Learning: A UK Retrospective Study.

Background Breast screening enables early detection of cancers; however, most women have normal mammograms, resulting in repetitive and resource-intensive reading tasks. Purpose To investigate if deep learning (DL) algorithms can be used to triage mammograms by identifying normal results to reduce workload or flag cancers that may be overlooked. Materials and Methods In this retrospective study, three commercial DL algorithms were investigated using consecutive mammograms from two UK Breast Screening Program sites from January 2015 to December 2017 and January 2017 to December 2018 on devices from two mammography vendors. Normal mammograms with a 3-year follow-up and histopathologically proven cancer detected at screening, the subsequent round, or in the 3-year interval were included. Two algorithm thresholds were set: in scenario A, 99.0% sensitivity for rule-out triage to a lone reader, and in scenario B, approximately 1.0% additional recall providing a rule-in triage for further assessment. Both thresholds were then applied to the screening workflow in scenario C. The sensitivity and specificity were used to assess the overall predictive performance of each DL algorithm. Results The data set comprised 78 849 patients (median age, 59 years [IQR, 53-63 years]) and 887 screening-detected, 439 interval, and 688 subsequent screening round-detected cancers. In scenario A (rule-out triage), models DL-1, DL-2, and DL-3 triaged 35.0% (27 565 of 78 849), 53.2% (41 937 of 78 849), and 55.6% (43 869 of 78 849) of mammograms, respectively, with 0.0% (0 of 887) to 0.1% (one of 887) of screening-detected cancers undetected. In scenario B, DL algorithms triaged in 4.6% (20 of 439) to 8.2% (36 of 439) of interval and 5.2% (36 of 688) to 6.1% (42 of 688) of subsequent-round cancers when applied after the routine double-reading workflow. Combining both approaches in scenario C resulted in an overall noninferior specificity (difference, -0.9%; P < .001) and superior sensitivity (difference, 2.7%; P < .001) for the adaptive workflow compared with routine double reading for all three algorithms. Conclusion Rule-out and rule-in DL-adapted triage workflows can improve the efficiency and efficacy of mammography breast cancer screening. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Nishikawa and Lu in this issue.

Standalone AI for Breast Cancer Detection at Screening Digital Mammography and Digital Breast Tomosynthesis: A Systematic Review and Meta-Analysis.

Background There is considerable interest in the potential use of artificial intelligence (AI) systems in mammographic screening. However, it is essential to critically evaluate the performance of AI before it can become a modality used for independent mammographic interpretation. Purpose To evaluate the reported standalone performances of AI for interpretation of digital mammography and digital breast tomosynthesis (DBT). Materials and Methods A systematic search was conducted in PubMed, Google Scholar, Embase (Ovid), and Web of Science databases for studies published from January 2017 to June 2022. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) values were reviewed. Study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 and Comparative (QUADAS-2 and QUADAS-C, respectively). A random effects meta-analysis and meta-regression analysis were performed for overall studies and for different study types (reader studies vs historic cohort studies) and imaging techniques (digital mammography vs DBT). Results In total, 16 studies that include 1 108 328 examinations in 497 091 women were analyzed (six reader studies, seven historic cohort studies on digital mammography, and four studies on DBT). Pooled AUCs were significantly higher for standalone AI than radiologists in the six reader studies on digital mammography (0.87 vs 0.81, P = .002), but not for historic cohort studies (0.89 vs 0.96, P = .152). Four studies on DBT showed significantly higher AUCs in AI compared with radiologists (0.90 vs 0.79, P < .001). Higher sensitivity and lower specificity were seen for standalone AI compared with radiologists. Conclusion Standalone AI for screening digital mammography performed as well as or better than radiologists. Compared with digital mammography, there is an insufficient number of studies to assess the performance of AI systems in the interpretation of DBT screening examinations. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Scaranelo in this issue.

A survey by the European Society of Breast Imaging on radiologists' preferences regarding quality assurance measures of image interpretation in screening and diagnostic mammography.

OBJECTIVES: Quality assurance (QA) of image interpretation plays a key role in screening and diagnostic mammography, maintaining minimum standards and supporting continuous improvement in interpreting images. However, the QA structure across Europe shows considerable variation. The European Society of Breast Imaging (EUSOBI) conducted a survey among the members to collect information on radiologists' preferences regarding QA measures in mammography. MATERIALS AND METHODS: An anonymous online survey consisting of 25 questions was distributed to all EUSOBI members and national breast radiology bodies in Europe. The questions were designed to collect demographic characteristics, information on responders' mammography workload and data about QA measures currently used in their country. Data was analysed using descriptive statistical analysis, the χ2 test, linear regression, and Durbin-Watson statistic test. RESULTS: In total, 251 breast radiologists from 34 countries completed the survey. Most respondents were providing both screening and symptomatic services (137/251, 54.6%), working in an academic hospital (85/251, 33.9%) and reading 1000-4999 cases per year (109/251, 43.4%). More than half of them (133/251, 53%) had established QA measures in their workplace. Although less than one-third (71/251, 28.3%) had to participate in regular performance testing, the vast majority (190/251, 75.7%) agreed that a mandatory test would be helpful to improve their skills. CONCLUSION: QA measures were in place for more than half of the respondents working in screening and diagnostic mammography to evaluate their breast imaging performance. Although there were substantial differences between countries, the importance of having QA in the workplace and implemented was widely acknowledged by radiologists. CLINICAL RELEVANCE STATEMENT: Although several quality assurance (QA) measures of image interpretation are recommended by European bodies or national organisations, the QA in mammography is quite heterogenous between countries and reporting settings, and not always actively implemented across Europe. KEY POINTS: The first survey that presents radiologists' preferences regarding QA measures of image interpretation in mammography. Quality assurance measures in the workplace are better-established for breast screening compared to diagnostic mammography. Radiologists consider that performance tests would help to improve their mammography interpretation skills.

PET/MRI of hypoxia and vascular function in ER-positive breast cancer: correlations with immunohistochemistry.

OBJECTIVES: To explore the relationship between indices of hypoxia and vascular function from 18F-fluoromisonidazole ([18F]-FMISO)-PET/MRI with immunohistochemical markers of hypoxia and vascularity in oestrogen receptor-positive (ER +) breast cancer. METHODS: Women aged > 18 years with biopsy-confirmed, treatment-naïve primary ER + breast cancer underwent [18F]-FMISO-PET/MRI prior to surgery. Parameters of vascular function were derived from DCE-MRI using the extended Tofts model, whilst hypoxia was assessed using the [18F]-FMISO influx rate constant, Ki. Histological tumour sections were stained with CD31, hypoxia-inducible factor (HIF)-1α, and carbonic anhydrase IX (CAIX). The number of tumour microvessels, median vessel diameter, and microvessel density (MVD) were obtained from CD31 immunohistochemistry. HIF-1α and CAIX expression were assessed using histoscores obtained by multiplying the percentage of positive cells stained by the staining intensity. Regression analysis was used to study associations between imaging and immunohistochemistry variables. RESULTS: Of the lesions examined, 14/22 (64%) were ductal cancers, grade 2 or 3 (19/22; 86%), with 17/22 (77%) HER2-negative. [18F]-FMISO Ki associated negatively with vessel diameter (p = 0.03), MVD (p = 0.02), and CAIX expression (p = 0.002), whilst no significant relationships were found between DCE-MRI pharmacokinetic parameters and immunohistochemical variables. HIF-1α did not significantly associate with any PET/MR imaging indices. CONCLUSION: Hypoxia measured by [18F]-FMISO-PET was associated with increased CAIX expression, low MVD, and smaller vessel diameters in ER + breast cancer, further corroborating the link between inadequate vascularity and hypoxia in ER + breast cancer. KEY POINTS: • Hypoxia, measured by [18F]-FMISO-PET, was associated with low microvessel density and small vessel diameters, corroborating the link between inadequate vascularity and hypoxia in ER + breast cancer. • Increased CAIX expression was associated with higher levels of hypoxia measured by [18F]-FMISO-PET. • Morphologic and functional abnormalities of the tumour microvasculature are the major determinants of hypoxia in cancers and support the previously reported perfusion-driven character of hypoxia in breast carcinomas.

Screening and diagnostic breast MRI: how do they impact surgical treatment? Insights from the MIPA study.

OBJECTIVES: To report mastectomy and reoperation rates in women who had breast MRI for screening (S-MRI subgroup) or diagnostic (D-MRI subgroup) purposes, using multivariable analysis for investigating the role of MRI referral/nonreferral and other covariates in driving surgical outcomes. METHODS: The MIPA observational study enrolled women aged 18-80 years with newly diagnosed breast cancer destined to have surgery as the primary treatment, in 27 centres worldwide. Mastectomy and reoperation rates were compared using non-parametric tests and multivariable analysis. RESULTS: A total of 5828 patients entered analysis, 2763 (47.4%) did not undergo MRI (noMRI subgroup) and 3065 underwent MRI (52.6%); of the latter, 2441/3065 (79.7%) underwent MRI with preoperative intent (P-MRI subgroup), 510/3065 (16.6%) D-MRI, and 114/3065 S-MRI (3.7%). The reoperation rate was 10.5% for S-MRI, 8.2% for D-MRI, and 8.5% for P-MRI, while it was 11.7% for noMRI (p ≤ 0.023 for comparisons with D-MRI and P-MRI). The overall mastectomy rate (first-line mastectomy plus conversions from conserving surgery to mastectomy) was 39.5% for S-MRI, 36.2% for P-MRI, 24.1% for D-MRI, and 18.0% for noMRI. At multivariable analysis, using noMRI as reference, the odds ratios for overall mastectomy were 2.4 (p < 0.001) for S-MRI, 1.0 (p = 0.957) for D-MRI, and 1.9 (p < 0.001) for P-MRI. CONCLUSIONS: Patients from the D-MRI subgroup had the lowest overall mastectomy rate (24.1%) among MRI subgroups and the lowest reoperation rate (8.2%) together with P-MRI (8.5%). This analysis offers an insight into how the initial indication for MRI affects the subsequent surgical treatment of breast cancer. KEY POINTS: • Of 3065 breast MRI examinations, 79.7% were performed with preoperative intent (P-MRI), 16.6% were diagnostic (D-MRI), and 3.7% were screening (S-MRI) examinations. • The D-MRI subgroup had the lowest mastectomy rate (24.1%) among MRI subgroups and the lowest reoperation rate (8.2%) together with P-MRI (8.5%). • The S-MRI subgroup had the highest mastectomy rate (39.5%) which aligns with higher-than-average risk in this subgroup, with a reoperation rate (10.5%) not significantly different to that of all other subgroups.

Preoperative breast MRI positively impacts surgical outcomes of needle biopsy-diagnosed pure DCIS: a patient-matched analysis from the MIPA study.

OBJECTIVES: To investigate the influence of preoperative breast MRI on mastectomy and reoperation rates in patients with pure ductal carcinoma in situ (DCIS). METHODS: The MIPA observational study database (7245 patients) was searched for patients aged 18-80 years with pure unilateral DCIS diagnosed at core needle or vacuum-assisted biopsy (CNB/VAB) and planned for primary surgery. Patients who underwent preoperative MRI (MRI group) were matched (1:1) to those who did not receive MRI (noMRI group) according to 8 confounding covariates that drive referral to MRI (age; hormonal status; familial risk; posterior-to-nipple diameter; BI-RADS category; lesion diameter; lesion presentation; surgical planning at conventional imaging). Surgical outcomes were compared between the matched groups with nonparametric statistics after calculating odds ratios (ORs). RESULTS: Of 1005 women with pure unilateral DCIS at CNB/VAB (507 MRI group, 498 noMRI group), 309 remained in each group after matching. First-line mastectomy rate in the MRI group was 20.1% (62/309 patients, OR 2.03) compared to 11.0% in the noMRI group (34/309 patients, p = 0.003). The reoperation rate was 10.0% in the MRI group (31/309, OR for reoperation 0.40) and 22.0% in the noMRI group (68/309, p < 0.001), with a 2.53 OR of avoiding reoperation in the MRI group. The overall mastectomy rate was 23.3% in the MRI group (72/309, OR 1.40) and 17.8% in the noMRI group (55/309, p = 0.111). CONCLUSIONS: Compared to those going directly to surgery, patients with pure DCIS at CNB/VAB who underwent preoperative MRI had a higher OR for first-line mastectomy but a substantially lower OR for reoperation. CLINICAL RELEVANCE STATEMENT: When confounding factors behind MRI referral are accounted for in the comparison of patients with CNB/VAB-diagnosed pure unilateral DCIS, preoperative MRI yields a reduction of reoperations that is more than twice as high as the increase in overall mastectomies. KEY POINTS: • Confounding factors cause imbalance when investigating the influence of preoperative MRI on surgical outcomes of pure DCIS. • When patient matching is applied to women with pure unilateral DCIS, reoperation rates are significantly reduced in women who underwent preoperative MRI. • The reduction of reoperations brought about by preoperative MRI is more than double the increase in overall mastectomies.

Imaging breast cancer using hyperpolarized carbon-13 MRI.

Our purpose is to investigate the feasibility of imaging tumor metabolism in breast cancer patients using 13C magnetic resonance spectroscopic imaging (MRSI) of hyperpolarized 13C label exchange between injected [1-13C]pyruvate and the endogenous tumor lactate pool. Treatment-naïve breast cancer patients were recruited: four triple-negative grade 3 cancers; two invasive ductal carcinomas that were estrogen and progesterone receptor-positive (ER/PR+) and HER2/neu-negative (HER2-), one grade 2 and one grade 3; and one grade 2 ER/PR+ HER2- invasive lobular carcinoma (ILC). Dynamic 13C MRSI was performed following injection of hyperpolarized [1-13C]pyruvate. Expression of lactate dehydrogenase A (LDHA), which catalyzes 13C label exchange between pyruvate and lactate, hypoxia-inducible factor-1 (HIF1α), and the monocarboxylate transporters MCT1 and MCT4 were quantified using immunohistochemistry and RNA sequencing. We have demonstrated the feasibility and safety of hyperpolarized 13C MRI in early breast cancer. Both intertumoral and intratumoral heterogeneity of the hyperpolarized pyruvate and lactate signals were observed. The lactate-to-pyruvate signal ratio (LAC/PYR) ranged from 0.021 to 0.473 across the tumor subtypes (mean ± SD: 0.145 ± 0.164), and a lactate signal was observed in all of the grade 3 tumors. The LAC/PYR was significantly correlated with tumor volume (R = 0.903, P = 0.005) and MCT 1 (R = 0.85, P = 0.032) and HIF1α expression (R = 0.83, P = 0.043). Imaging of hyperpolarized [1-13C]pyruvate metabolism in breast cancer is feasible and demonstrated significant intertumoral and intratumoral metabolic heterogeneity, where lactate labeling correlated with MCT1 expression and hypoxia.

Sodium accumulation in breast cancer predicts malignancy and treatment response.

BACKGROUND: Breast cancer remains a leading cause of death in women and novel imaging biomarkers are urgently required. Here, we demonstrate the diagnostic and treatment-monitoring potential of non-invasive sodium (23Na) MRI in preclinical models of breast cancer. METHODS: Female Rag2-/- Il2rg-/- and Balb/c mice bearing orthotopic breast tumours (MDA-MB-231, EMT6 and 4T1) underwent MRI as part of a randomised, controlled, interventional study. Tumour biology was probed using ex vivo fluorescence microscopy and electrophysiology. RESULTS: 23Na MRI revealed elevated sodium concentration ([Na+]) in tumours vs non-tumour regions. Complementary proton-based diffusion-weighted imaging (DWI) linked elevated tumour [Na+] to increased cellularity. Combining 23Na MRI and DWI measurements enabled superior classification accuracy of tumour vs non-tumour regions compared with either parameter alone. Ex vivo assessment of isolated tumour slices confirmed elevated intracellular [Na+] ([Na+]i); extracellular [Na+] ([Na+]e) remained unchanged. Treatment with specific inward Na+ conductance inhibitors (cariporide, eslicarbazepine acetate) did not affect tumour [Na+]. Nonetheless, effective treatment with docetaxel reduced tumour [Na+], whereas DWI measures were unchanged. CONCLUSIONS: Orthotopic breast cancer models exhibit elevated tumour [Na+] that is driven by aberrantly elevated [Na+]i. Moreover, 23Na MRI enhances the diagnostic capability of DWI and represents a novel, non-invasive biomarker of treatment response with superior sensitivity compared to DWI alone.

Comparative accuracy and cost-effectiveness of dynamic contrast-enhanced CT and positron emission tomography in the characterisation of solitary pulmonary nodules.

INTRODUCTION: Dynamic contrast-enhanced CT (DCE-CT) and positron emission tomography/CT (PET/CT) have a high reported accuracy for the diagnosis of malignancy in solitary pulmonary nodules (SPNs). The aim of this study was to compare the accuracy and cost-effectiveness of these. METHODS: In this prospective multicentre trial, 380 participants with an SPN (8-30 mm) and no recent history of malignancy underwent DCE-CT and PET/CT. All patients underwent either biopsy with histological diagnosis or completed CT follow-up. Primary outcome measures were sensitivity, specificity and overall diagnostic accuracy for PET/CT and DCE-CT. Costs and cost-effectiveness were estimated from a healthcare provider perspective using a decision-model. RESULTS: 312 participants (47% female, 68.1±9.0 years) completed the study, with 61% rate of malignancy at 2 years. The sensitivity, specificity, positive predictive value and negative predictive values for DCE-CT were 95.3% (95% CI 91.3 to 97.5), 29.8% (95% CI 22.3 to 38.4), 68.2% (95% CI 62.4% to 73.5%) and 80.0% (95% CI 66.2 to 89.1), respectively, and for PET/CT were 79.1% (95% CI 72.7 to 84.2), 81.8% (95% CI 74.0 to 87.7), 87.3% (95% CI 81.5 to 91.5) and 71.2% (95% CI 63.2 to 78.1). The area under the receiver operator characteristic curve (AUROC) for DCE-CT and PET/CT was 0.62 (95% CI 0.58 to 0.67) and 0.80 (95% CI 0.76 to 0.85), respectively (p<0.001). Combined results significantly increased diagnostic accuracy over PET/CT alone (AUROC=0.90 (95% CI 0.86 to 0.93), p<0.001). DCE-CT was preferred when the willingness to pay per incremental cost per correctly treated malignancy was below £9000. Above £15 500 a combined approach was preferred. CONCLUSIONS: PET/CT has a superior diagnostic accuracy to DCE-CT for the diagnosis of SPNs. Combining both techniques improves the diagnostic accuracy over either test alone and could be cost-effective. TRIAL REGISTRATION NUMBER: NCT02013063.

Machine Learning for Workflow Applications in Screening Mammography: Systematic Review and Meta-Analysis.

Background Advances in computer processing and improvements in data availability have led to the development of machine learning (ML) techniques for mammographic imaging. Purpose To evaluate the reported performance of stand-alone ML applications for screening mammography workflow. Materials and Methods Ovid Embase, Ovid Medline, Cochrane Central Register of Controlled Trials, Scopus, and Web of Science literature databases were searched for relevant studies published from January 2012 to September 2020. The study was registered with the PROSPERO International Prospective Register of Systematic Reviews (protocol no. CRD42019156016). Stand-alone technology was defined as a ML algorithm that can be used independently of a human reader. Studies were quality assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 and the Prediction Model Risk of Bias Assessment Tool, and reporting was evaluated using the Checklist for Artificial Intelligence in Medical Imaging. A primary meta-analysis included the top-performing algorithm and corresponding reader performance from which pooled summary estimates for the area under the receiver operating characteristic curve (AUC) were calculated using a bivariate model. Results Fourteen articles were included, which detailed 15 studies for stand-alone detection (n = 8) and triage (n = 7). Triage studies reported that 17%-91% of normal mammograms identified could be read by adapted screening, while "missing" an estimated 0%-7% of cancers. In total, an estimated 185 252 cases from three countries with more than 39 readers were included in the primary meta-analysis. The pooled sensitivity, specificity, and AUC was 75.4% (95% CI: 65.6, 83.2; P = .11), 90.6% (95% CI: 82.9, 95.0; P = .40), and 0.89 (95% CI: 0.84, 0.98), respectively, for algorithms, and 73.0% (95% CI: 60.7, 82.6), 88.6% (95% CI: 72.4, 95.8), and 0.85 (95% CI: 0.78, 0.97), respectively, for readers. Conclusion Machine learning (ML) algorithms that demonstrate a stand-alone application in mammographic screening workflows achieve or even exceed human reader detection performance and improve efficiency. However, this evidence is from a small number of retrospective studies. Therefore, further rigorous independent external prospective testing of ML algorithms to assess performance at preassigned thresholds is required to support these claims. ©RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Whitman and Moseley in this issue.

Study protocol comparing the ethical, psychological and socio-economic impact of personalised breast cancer screening to that of standard screening in the "My Personal Breast Screening" (MyPeBS) randomised clinical trial.

BACKGROUND: The MyPeBS study is an ongoing randomised controlled trial testing whether a risk-stratified breast cancer screening strategy is non-inferior, or eventually superior, to standard age-based screening at reducing incidence of stage 2 or more cancers. This large European Commission-funded initiative aims to include 85,000 women aged 40 to 70 years, without prior breast cancer and not previously identified at high risk in six countries (Belgium, France, Italy, Israel, Spain, UK). A specific work package within MyPeBS examines psychological, socio-economic and ethical aspects of this new screening strategy. It compares women's reported data and outcomes in both trial arms on the following issues: general anxiety, cancer-related worry, understanding of breast cancer screening strategy and information-seeking behaviour, socio-demographic and economic characteristics, quality of life, risk perception, intention to change health-related behaviours, satisfaction with the trial. METHODS: At inclusion, 3-months, 1-year and 4-years, each woman participating in MyPeBS is asked to fill online questionnaires. Descriptive statistics, bivariate analyses, subgroup comparisons and analysis of variations over time will be performed with appropriate tests to assess differences between arms. Multivariate regression models will allow modelling of different patient reported data and outcomes such as comprehension of the information provided, general anxiety or cancer worry, and information seeking behaviour. In addition, a qualitative study (48 semi-structured interviews conducted in France and in the UK with women randomised in the risk-stratified arm), will help further understand participants' acceptability and comprehension of the trial, and their experience of risk assessment. DISCUSSION: Beyond the scientific and medical objectives of this clinical study, it is critical to acknowledge the consequences of such a paradigm shift for women. Indeed, introducing a risk-based screening relying on individual biological differences also implies addressing non-biological differences (e.g. social status or health literacy) from an ethical perspective, to ensure equal access to healthcare. The results of the present study will facilitate making recommendations on implementation at the end of the trial to accompany any potential change in screening strategy. TRIAL REGISTRATION: Study sponsor: UNICANCER. My personalised breast screening (MyPeBS). CLINICALTRIALS: gov (2018) available at: https://clinicaltrials.gov/ct2/show/NCT03672331 Contact: Cécile VISSAC SABATIER, PhD, + 33 (0)1 73 79 77 58 ext + 330,142,114,293, contact@mypebs.eu.

A survey by the European Society of Breast Imaging on the implementation of breast diffusion-weighted imaging in clinical practice.

OBJECTIVES: To perform a survey among all European Society of Breast Imaging (EUSOBI) radiologist members to gather representative data regarding the clinical use of breast DWI. METHODS: An online questionnaire was developed by two board-certified radiologists, reviewed by the EUSOBI board and committees, and finally distributed among EUSOBI active and associated (not based in Europe) radiologist members. The questionnaire included 20 questions pertaining to technical preferences (acquisition time, magnet strength, breast coils, number of b values), clinical indications, imaging evaluation, and reporting. Data were analyzed using descriptive statistics, the Chi-square test of independence, and Fisher's exact test. RESULTS: Of 1411 EUSOBI radiologist members, 275/1411 (19.5%) responded. Most (222/275, 81%) reported using DWI as part of their routine protocol. Common indications for DWI include lesion characterization (using an ADC threshold of 1.2-1.3 × 10-3 mm2/s) and prediction of response to chemotherapy. Members most commonly acquire two separate b values (114/217, 53%), with b value = 800 s/mm2 being the preferred value for appraisal among those acquiring more than two b values (71/171, 42%). Most did not use synthetic b values (169/217, 78%). While most mention hindered diffusion in the MRI report (161/213, 76%), only 142/217 (57%) report ADC values. CONCLUSION: The utilization of DWI in clinical practice among EUSOBI radiologists who responded to the survey is generally in line with international recommendations, with the main application being the differentiation of benign and malignant enhancing lesions, treatment response assessment, and prediction of response to chemotherapy. Report integration of qualitative and quantitative DWI data is not uniform. KEY POINTS: • Clinical performance of breast DWI is in good agreement with the current recommendations of the EUSOBI International Breast DWI working group. • Breast DWI applications in clinical practice include the differentiation of benign and malignant enhancing, treatment response assessment, and prediction of response to chemotherapy. • Report integration of DWI results is not uniform.

Breast cancer screening in women with extremely dense breasts recommendations of the European Society of Breast Imaging (EUSOBI).

Breast density is an independent risk factor for the development of breast cancer and also decreases the sensitivity of mammography for screening. Consequently, women with extremely dense breasts face an increased risk of late diagnosis of breast cancer. These women are, therefore, underserved with current mammographic screening programs. The results of recent studies reporting on contrast-enhanced breast MRI as a screening method in women with extremely dense breasts provide compelling evidence that this approach can enable an important reduction in breast cancer mortality for these women and is cost-effective. Because there is now a valid option to improve breast cancer screening, the European Society of Breast Imaging (EUSOBI) recommends that women should be informed about their breast density. EUSOBI thus calls on all providers of mammography screening to share density information with the women being screened. In light of the available evidence, in women aged 50 to 70 years with extremely dense breasts, the EUSOBI now recommends offering screening breast MRI every 2 to 4 years. The EUSOBI acknowledges that it may currently not be possible to offer breast MRI immediately and everywhere and underscores that quality assurance procedures need to be established, but urges radiological societies and policymakers to act on this now. Since the wishes and values of individual women differ, in screening the principles of shared decision-making should be embraced. In particular, women should be counselled on the benefits and risks of mammography and MRI-based screening, so that they are capable of making an informed choice about their preferred screening method. KEY POINTS: • The recommendations in Figure 1 summarize the key points of the manuscript.

Magnetic resonance imaging before breast cancer surgery: results of an observational multicenter international prospective analysis (MIPA).

OBJECTIVES: Preoperative breast magnetic resonance imaging (MRI) can inform surgical planning but might cause overtreatment by increasing the mastectomy rate. The Multicenter International Prospective Analysis (MIPA) study investigated this controversial issue. METHODS: This observational study enrolled women aged 18-80 years with biopsy-proven breast cancer, who underwent MRI in addition to conventional imaging (mammography and/or breast ultrasonography) or conventional imaging alone before surgery as routine practice at 27 centers. Exclusion criteria included planned neoadjuvant therapy, pregnancy, personal history of any cancer, and distant metastases. RESULTS: Of 5896 analyzed patients, 2763 (46.9%) had conventional imaging only (noMRI group), and 3133 (53.1%) underwent MRI that was performed for diagnosis, screening, or unknown purposes in 692/3133 women (22.1%), with preoperative intent in 2441/3133 women (77.9%, MRI group). Patients in the MRI group were younger, had denser breasts, more cancers ≥ 20 mm, and a higher rate of invasive lobular histology than patients who underwent conventional imaging alone (p < 0.001 for all comparisons). Mastectomy was planned based on conventional imaging in 22.4% (MRI group) versus 14.4% (noMRI group) (p < 0.001). The additional planned mastectomy rate in the MRI group was 11.3%. The overall performed first- plus second-line mastectomy rate was 36.3% (MRI group) versus 18.0% (noMRI group) (p < 0.001). In women receiving conserving surgery, MRI group had a significantly lower reoperation rate (8.5% versus 11.7%, p < 0.001). CONCLUSIONS: Clinicians requested breast MRI for women with a higher a priori probability of receiving mastectomy. MRI was associated with 11.3% more mastectomies, and with 3.2% fewer reoperations in the breast conservation subgroup. KEY POINTS: • In 19% of patients of the MIPA study, breast MRI was performed for screening or diagnostic purposes. • The current patient selection to preoperative breast MRI implies an 11% increase in mastectomies, counterbalanced by a 3% reduction of the reoperation rate. • Data from the MIPA study can support discussion in tumor boards when preoperative MRI is under consideration and should be shared with patients to achieve informed decision-making.

Adoption of artificial intelligence in breast imaging: evaluation, ethical constraints and limitations.

Retrospective studies have shown artificial intelligence (AI) algorithms can match as well as enhance radiologist's performance in breast screening. These tools can facilitate tasks not feasible by humans such as the automatic triage of patients and prediction of treatment outcomes. Breast imaging faces growing pressure with the exponential growth in imaging requests and a predicted reduced workforce to provide reports. Solutions to alleviate these pressures are being sought with an increasing interest in the adoption of AI to improve workflow efficiency as well as patient outcomes. Vast quantities of data are needed to test and monitor AI algorithms before and after their incorporation into healthcare systems. Availability of data is currently limited, although strategies are being devised to harness the data that already exists within healthcare institutions. Challenges that underpin the realisation of AI into everyday breast imaging cannot be underestimated and the provision of guidance from national agencies to tackle these challenges, taking into account views from a societal, industrial and healthcare prospective is essential. This review provides background on the evaluation and use of AI in breast imaging in addition to exploring key ethical, technical, legal and regulatory challenges that have been identified so far.

Combined 23 Na and 13 C imaging at 3.0 Tesla using a single-tuned large FOV birdcage coil.

PURPOSE: An unmet need in carbon-13 (13 C)-MRI is a transmit system that provides uniform excitation across a large FOV and can accommodate patients of wide-ranging body habitus. Due to the small difference between the resonant frequencies, sodium-23 (23 Na) coil developments can inform 13 C coil design while being simpler to assess due to the higher naturally abundant 23 Na signal. Here we present a removable 23 Na birdcage, which also allows operation as a 13 C abdominal coil. METHODS: We demonstrate a quadrature-driven 4-rung 23 Na birdcage coil of 50 cm in length for both 23 Na and 13 C abdominal imaging. The coil transmit efficiencies and B1+ maps were compared to a linearly driven 13 C Helmholtz-based (clamshell) coil. SNR was investigated with 23 Na and 13 C data using an 8-channel 13 C receive array within the 23 Na birdcage. RESULTS: The 23 Na birdcage longitudinal FOV was > 40 cm, whereas the 13 C clamshell was < 32 cm. The transmit efficiency of the birdcage at the 23 Na frequency was 0.65 µT/sqrt(W), similar to the clamshell for 13 C. However, the coefficient of variation of 23 Na- B1+ was 16%, nearly half that with the 13 C clamshell. The 8-channel 13 C receive array combined with the 23 Na birdcage coil generated a greater than twofold increase in 23 Na-SNR from the central abdomen compared with the birdcage alone. DISCUSSION: This 23 Na birdcage coil has a larger FOV and improved B1+ uniformity when compared to the widely used clamshell coil design while also providing similar transmit efficiency. The coil has the potential to be used for both 23 Na and 13 C imaging.

Impact of solitary pulmonary nodule size on qualitative and quantitative assessment using 18F-fluorodeoxyglucose PET/CT: the SPUTNIK trial.

PURPOSE: To compare qualitative and semi-quantitative PET/CT criteria, and the impact of nodule size on the diagnosis of solitary pulmonary nodules in a prospective multicentre trial. METHODS: Patients with an SPN on CT ≥ 8 and ≤ 30 mm were recruited to the SPUTNIK trial at 16 sites accredited by the UK PET Core Lab. Qualitative assessment used a five-point ordinal PET-grade compared to the mediastinal blood pool, and a combined PET/CT grade using the CT features. Semi-quantitative measures included SUVmax of the nodule, and as an uptake ratio to the mediastinal blood pool (SURBLOOD) or liver (SURLIVER). The endpoints were diagnosis of lung cancer via biopsy/histology or completion of 2-year follow-up. Impact of nodule size was analysed by comparison between nodule size tertiles. RESULTS: Three hundred fifty-five participants completed PET/CT and 2-year follow-up, with 59% (209/355) malignant nodules. The AUCs of the three techniques were SUVmax 0.87 (95% CI 0.83;0.91); SURBLOOD 0.87 (95% CI 0.83; 0.91, p = 0.30 versus SUVmax); and SURLIVER 0.87 (95% CI 0.83; 0.91, p = 0.09 vs. SUVmax). The AUCs for all techniques remained stable across size tertiles (p > 0.1 for difference), although the optimal diagnostic threshold varied by size. For nodules < 12 mm, an SUVmax of 1.75 or visual uptake equal to the mediastinum yielded the highest accuracy. For nodules > 16 mm, an SUVmax ≥ 3.6 or visual PET uptake greater than the mediastinum was the most accurate. CONCLUSION: In this multicentre trial, SUVmax was the most accurate technique for the diagnosis of solitary pulmonary nodules. Diagnostic thresholds should be altered according to nodule size. TRIAL REGISTRATION: ISRCTN - ISRCTN30784948. ClinicalTrials.gov - NCT02013063.

Hypoxia and perfusion in breast cancer: simultaneous assessment using PET/MR imaging.

OBJECTIVES: Hypoxia is associated with poor prognosis and treatment resistance in breast cancer. However, the temporally variant nature of hypoxia can complicate interpretation of imaging findings. We explored the relationship between hypoxia and vascular function in breast tumours through combined 18F-fluoromisonidazole (18 F-FMISO) PET/MRI, with simultaneous assessment circumventing the effect of temporal variation in hypoxia and perfusion. METHODS: Women with histologically confirmed, primary breast cancer underwent a simultaneous 18F-FMISO-PET/MR examination. Tumour hypoxia was assessed using influx rate constant Ki and hypoxic fractions (%HF), while parameters of vascular function (Ktrans, kep, ve, vp) and cellularity (ADC) were derived from dynamic contrast-enhanced (DCE) and diffusion-weighted (DW)-MRI, respectively. Additional correlates included histological subtype, grade and size. Relationships between imaging variables were assessed using Pearson correlation (r). RESULTS: Twenty-nine women with 32 lesions were assessed. Hypoxic fractions > 1% were observed in 6/32 (19%) cancers, while 18/32 (56%) tumours showed a %HF of zero. The presence of hypoxia in lesions was independent of histological subtype or grade. Mean tumour Ktrans correlated negatively with Ki (r = - 0.38, p = 0.04) and %HF (r = - 0.33, p = 0.04), though parametric maps exhibited intratumoural heterogeneity with hypoxic regions colocalising with both hypo- and hyperperfused areas. No correlation was observed between ADC and DCE-MRI or PET parameters. %HF correlated positively with lesion size (r = 0.63, p = 0.001). CONCLUSION: Hypoxia measured by 18F-FMISO-PET correlated negatively with Ktrans from DCE-MRI, supporting the hypothesis of perfusion-driven hypoxia in breast cancer. Intratumoural hypoxia-perfusion relationships were heterogeneous, suggesting that combined assessment may be needed for disease characterisation, which could be achieved using simultaneous multimodality imaging. KEY POINTS: • At the tumour level, hypoxia measured by 18F-FMISO-PET was negatively correlated with perfusion measured by DCE-MRI, which supports the hypothesis of perfusion-driven hypoxia in breast cancer. • No associations were observed between 18F-FMISO-PET parameters and tumour histology or grade, but tumour hypoxic fractions increased with lesion size. • Intratumoural hypoxia-perfusion relationships were heterogeneous, suggesting that the combined hypoxia-perfusion status of tumours may need to be considered for disease characterisation, which can be achieved via simultaneous multimodality imaging as reported here.

Dynamic contrast-enhanced MRI of synovitis in knee osteoarthritis: repeatability, discrimination and sensitivity to change in a prospective experimental study.

OBJECTIVES: Evaluate test-retest repeatability, ability to discriminate between osteoarthritic and healthy participants, and sensitivity to change over 6 months, of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) biomarkers in knee OA. METHODS: Fourteen individuals aged 40-60 with mild-moderate knee OA and 6 age-matched healthy volunteers (HV) underwent DCE-MRI at 3 T at baseline, 1 month and 6 months. Voxelwise pharmacokinetic modelling of dynamic data was used to calculate DCE-MRI biomarkers including Ktrans and IAUC60. Median DCE-MRI biomarker values were extracted for each participant at each study visit. Synovial segmentation was performed using both manual and semiautomatic methods with calculation of an additional biomarker, the volume of enhancing pannus (VEP). Test-retest repeatability was assessed using intraclass correlation coefficients (ICC). Smallest detectable differences (SDDs) were calculated from test-retest data. Discrimination between OA and HV was assessed via calculation of between-group standardised mean differences (SMD). Responsiveness was assessed via the number of OA participants with changes greater than the SDD at 6 months. RESULTS: Ktrans demonstrated the best test-retest repeatability (Ktrans/IAUC60/VEP ICCs 0.90/0.84/0.40, SDDs as % of OA mean 33/71/76%), discrimination between OA and HV (SMDs 0.94/0.54/0.50) and responsiveness (5/1/1 out of 12 OA participants with 6-month change > SDD) when compared to IAUC60 and VEP. Biomarkers derived from semiautomatic segmentation outperformed those derived from manual segmentation across all domains. CONCLUSIONS: Ktrans demonstrated the best repeatability, discrimination and sensitivity to change suggesting that it is the optimal DCE-MRI biomarker for use in experimental medicine studies. KEY POINTS: • Dynamic contrast-enhanced MRI (DCE-MRI) provides quantitative measures of synovitis in knee osteoarthritis which may permit early assessment of efficacy in experimental medicine studies. • This prospective observational study compared DCE-MRI biomarkers across domains relevant to experimental medicine: test-retest repeatability, discriminative validity and sensitivity to change. • The DCE-MRI biomarker Ktrans demonstrated the best performance across all three domains, suggesting that it is the optimal biomarker for use in future interventional studies.