Contrast-enhanced mammography versus conventional imaging in women recalled from breast cancer screening (RACER trial): a multicentre, open-label, randomised controlled clinical trial.

Background: Women recalled from breast cancer screening receive post-screening work-up in the hospital with conventional breast imaging. The RACER trial aimed to study whether contrast-enhanced mammography (CEM) as primary imaging instead of conventional imaging resulted in more accurate and efficient diagnostic work-up in recalled women. Methods: In this randomised, controlled trial (registered under NL6413/NTR6589) participants were allocated using deterministic minimisation to CEM or conventional imaging as a primary work-up tool in two general and two academic hospitals. Predefined patients' factors were reason for recall, BI-RADS score, and study centre. Primary outcomes were sensitivity and specificity. Secondary outcomes were the proportion of women needing supplemental examinations, and number of days until diagnosis. Findings: Between April, 2018, and September, 2021, 529 patients recalled from the Dutch screening program were randomised, 265 to conventional imaging and 264 to CEM. Three patients in the control arm had to be excluded from analysis due to a protocol breach. After the entire work-up, sensitivity was 98.0% (95% CI; 92.2-99.7%) in the intervention arm and 97.7% (91.8-99.6%) in the control arm (p = 1.0), and specificity was 75.6% (72.5-76.6%) and 75.4% (72.5-76.4%, p = 1.0), respectively. Based on only primary full-field digital mammography/digital breast tomosynthesis or CEM, final diagnosis was reached in 27.7% (73/264) in the intervention arm and 1.1% (3/262) in the control arm. The frequency of supplemental imaging was significantly higher in the control arm (p < 0.0001). Median time needed to reach final diagnosis was comparable: 1 day (control arm: IQR 0-4; intervention arm: IQR 0-3). Thirteen malignant occult lesions were detected using CEM, versus three using conventional imaging. No serious adverse events occurred. Interpretation: Diagnostic accuracy of CEM in the work-up of recalled women is comparable with conventional imaging. However, work-up with CEM as primary imaging is a more efficient pathway. Funding: ZonMw (grant number 843001801) and GE Healthcare.

Deferring diagnostic evaluation of suspected deep vein thrombosis using direct oral anticoagulant or low-molecular-weight heparin as a single dose anticoagulant: A prospective real-world study in a regionwide care pathway.

BACKGROUND: Patients with suspected deep vein thrombosis (DVT) are typically referred to the emergency department for immediate evaluation. To enhance efficiency, our hospital implemented a regional, general practitioner (GP)-driven DVT care pathway, deferring diagnostic evaluation to a scheduled outpatient DVT clinic appointment the following day. Patients receive a single dose anticoagulant from their GP to prevent thrombosis progression while awaiting diagnostic workup. This prospective study aimed to evaluate the safety and patient preferences regarding the DVT care pathway and the type of single dose anticoagulant (low-molecular-weight heparin (LMWH) vs. direct oral anticoagulant (DOAC)). METHODS: Patients enrolled in the DVT care pathway between June 2021 and July 2023 were eligible. Until July 2022, LMWH was administered, and thereafter, the protocol recommended DOAC as the single dose anticoagulant. Patients completed questionnaires, incorporating patient-reported outcome and experience measures (PROMs/PREMs), during their DVT clinic visit and after five days. The primary endpoint was bleeding events within 72 h of receiving the single dose anticoagulant. RESULTS: Of 460 included patients, 229 received LMWH and 231 received DOAC as the single dose anticoagulant. DVT was confirmed in 24.8 % of patients. No major or clinically relevant non-major bleeding were reported. LMWH was associated with more minor bleedings (22.3 % vs. DOAC 13.4 %), primarily attributed to injection site hematomas. Patients reported high satisfaction with the DVT care pathway (96.5 %) and generally preferred DOAC over LMWH. CONCLUSION: Deferring diagnostic evaluation for DVT using a single dose of either LMWH or DOAC in a real-world population is deemed safe. Considering practical advantages, patient preferences, and fewer skin hematomas, we favor DOACs as the single dose anticoagulant in this care pathway.

Re-attendance in supplemental breast MRI screening rounds of the DENSE trial for women with extremely dense breasts.

OBJECTIVES: Supplemental MRI screening improves early breast cancer detection and reduces interval cancers in women with extremely dense breasts in a cost-effective way. Recently, the European Society of Breast Imaging recommended offering MRI screening to women with extremely dense breasts, but the debate on whether to implement it in breast cancer screening programs is ongoing. Insight into the participant experience and willingness to re-attend is important for this discussion. METHODS: We calculated the re-attendance rates of the second and third MRI screening rounds of the DENSE trial. Moreover, we calculated age-adjusted odds ratios (ORs) to study the association between characteristics and re-attendance. Women who discontinued MRI screening were asked to provide one or more reasons for this. RESULTS: The re-attendance rates were 81.3% (3458/4252) and 85.2% (2693/3160) in the second and third MRI screening round, respectively. A high age (> 65 years), a very low BMI, lower education, not being employed, smoking, and no alcohol consumption were correlated with lower re-attendance rates. Moderate or high levels of pain, discomfort, or anxiety experienced during the previous MRI screening round were correlated with lower re-attendance rates. Finally, a plurality of women mentioned an examination-related inconvenience as a reason to discontinue screening (39.1% and 34.8% in the second and third screening round, respectively). CONCLUSIONS: The willingness of women with dense breasts to re-attend an ongoing MRI screening study is high. However, emphasis should be placed on improving the MRI experience to increase the re-attendance rate if widespread supplemental MRI screening is implemented. CLINICAL RELEVANCE STATEMENT: For many women, MRI is an acceptable screening method, as re-attendance rates were high - even for screening in a clinical trial setting. To further enhance the (re-)attendance rate, one possible approach could be improving the overall MRI experience. KEY POINTS: • The willingness to re-attend in an ongoing MRI screening study is high. • Pain, discomfort, and anxiety in the previous MRI screening round were related to lower re-attendance rates. • Emphasis should be placed on improving MRI experience to increase the re-attendance rate in supplemental MRI screening.

Association of breast cancer with quantitative mammographic density measures for women receiving contrast-enhanced mammography.

Women with high mammographic density have an increased risk of breast cancer. They may be offered contrast-enhanced mammography to improve breast cancer screening performance. Using a cohort of women receiving contrast-enhanced mammography, we evaluated whether conventional and modified mammographic density measures were associated with breast cancer. Sixty-six patients with newly diagnosed unilateral breast cancer were frequency matched on the basis of age to 133 cancer-free control individuals. On low-energy craniocaudal contrast-enhanced mammograms (equivalent to standard mammograms), we measured quantitative mammographic density using CUMULUS software at the conventional intensity threshold ("Cumulus") and higher-than-conventional thresholds ("Altocumulus," "Cirrocumulus"). The measures were standardized to enable estimation of odds ratio per adjusted standard deviation (OPERA). In multivariable logistic regression of case-control status, only the highest-intensity measure (Cirrocumulus) was statistically significantly associated with breast cancer (OPERA = 1.40, 95% confidence interval = 1.04 to 1.89). Conventional Cumulus did not contribute to model fit. For women receiving contrast-enhanced mammography, Cirrocumulus mammographic density may better predict breast cancer than conventional quantitative mammographic density.

De-escalation of axillary treatment in the event of a positive sentinel lymph node biopsy in cT1-2 N0 breast cancer treated with mastectomy: nationwide registry study (BOOG 2013-07).

BACKGROUND: Trials have demonstrated the safety of omitting completion axillary lymph node dissection in patients with cT1-2 N0 breast cancer operated with breast-conserving surgery who have limited metastatic burden in the sentinel lymph node. The aim of this registry study was to provide insight into the oncological safety of omitting completion axillary treatment in patients operated with mastectomy who have limited-volume sentinel lymph node metastasis. METHODS: Women diagnosed in 2013-2014 with unilateral cT1-2 N0 breast cancer treated with mastectomy, with one to three sentinel lymph node metastases (pN1mi-pN1a), were identified from the Netherlands Cancer Registry, and classified by axillary treatment: no completion axillary treatment, completion axillary lymph node dissection, regional radiotherapy, or completion axillary lymph node dissection followed by regional radiotherapy. The primary endpoint was 5-year regional recurrence rate. Secondary endpoints included recurrence-free interval and overall survival, among others. RESULTS: In total, 1090 patients were included (no completion axillary treatment, 219 (20.1%); completion axillary lymph node dissection, 437 (40.1%); regional radiotherapy, 327 (30.0%); completion axillary lymph node dissection and regional radiotherapy, 107 (9.8%)). Patients in the group without completion axillary treatment had more favourable tumour characteristics and were older. The overall 5-year regional recurrence rate was 1.3%, and did not differ significantly between the groups. The recurrence-free interval was also comparable among groups. The group of patients who did not undergo completion axillary treatment had statistically significantly worse 5-year overall survival, owing to a higher percentage of non-cancer deaths. CONCLUSION: In this registry study of patients with cT1-2 N0 breast cancer treated with mastectomy, with low-volume sentinel lymph node metastasis, the 5-year regional recurrence rate was low and comparable between patients with and without completion axillary treatment.

Impact of low dose superparamagnetic iron oxide tracer for sentinel node biopsy in breast conserving treatment on susceptibility artefacts on magnetic resonance imaging and contrast enhanced mammography.

BACKGROUND: Residual particles of superparamagnetic iron oxide (SPIO) tracer, used for sentinel node biopsy, cause susceptibility artefacts on breast Magnetic Resonance Imaging (MRI). We investigated the impact of these artefacts on the imaging quality of MRI and explored whether contrast-enhanced mammography (CEM) could be an alternative in the follow-up of breast cancer patients. MATERIALS AND METHODS: Data on patients' characteristics, injection site, presence, size (mm) of artefacts on full-field digital mammography (FFDM)/CEM, MRI after 1 ml SPIO was recorded. Image quality scored by two breast radiologists using a 4-point Likert system: 0: no artefacts 1: good diagnostic quality 2: impaired but still readable 3: hampered clinical assessment. Continuous variables reported as means and standard deviations (SD), categorical variables as count and percentage. RESULTS: On FFDM/CEM, performed 13 months postoperatively, no iron SPIO particles were detected, with a Likert score of 0. In all MRI (100%) images, executed at 16.6 months after SPIO injection, susceptibility artefacts at the injection sites i.e., retroareolair and lateral quadrant were observed with a mean size of 41.9 ± 9.8 mm (SD) by observer 1, and 44.8 ± 12.5 mm (SD) by observer 2, independent of the injection site. Both observers scored a Likert score of 2: locally impaired on all MRI images and sequences. CONCLUSIONS: Even 1 ml SPIO tracer used for sentinel node procedure impairs the evaluation of breast MRI at the tracer injection site beyond one year of follow-up. No impairment was observed on FFDM/CEM, suggesting that CEM might be a reliable alternative to breast MRI if required.

Natural Language Processing Algorithm Used for Staging Pulmonary Oncology from Free-Text Radiological Reports: "Including PET-CT and Validation Towards Clinical Use".

Natural language processing (NLP) can be used to process and structure free text, such as (free text) radiological reports. In radiology, it is important that reports are complete and accurate for clinical staging of, for instance, pulmonary oncology. A computed tomography (CT) or positron emission tomography (PET)-CT scan is of great importance in tumor staging, and NLP may be of additional value to the radiological report when used in the staging process as it may be able to extract the T and N stage of the 8th tumor-node-metastasis (TNM) classification system. The purpose of this study is to evaluate a new TN algorithm (TN-PET-CT) by adding a layer of metabolic activity to an already existing rule-based NLP algorithm (TN-CT). This new TN-PET-CT algorithm is capable of staging chest CT examinations as well as PET-CT scans. The study design made it possible to perform a subgroup analysis to test the external validation of the prior TN-CT algorithm. For information extraction and matching, pyContextNLP, SpaCy, and regular expressions were used. Overall TN accuracy score of the TN-PET-CT algorithm was 0.73 and 0.62 in the training and validation set (N = 63, N = 100). The external validation of the TN-CT classifier (N = 65) was 0.72. Overall, it is possible to adjust the TN-CT algorithm into a TN-PET-CT algorithm. However, outcomes highly depend on the accuracy of the report, the used vocabulary, and its context to express, for example, uncertainty. This is true for both the adjusted PET-CT algorithm and for the CT algorithm when applied in another hospital.

Current use and future perspectives of contrast-enhanced mammography (CEM): a survey by the European Society of Breast Imaging (EUSOBI).

OBJECTIVES: To perform a survey among members of the European Society of Breast Imaging (EUSOBI) regarding the use of contrast-enhanced mammography (CEM). METHODS: A panel of nine board-certified radiologists developed a 29-item online questionnaire, distributed to all EUSOBI members (inside and outside Europe) from January 25 to March 10, 2023. CEM implementation, examination protocols, reporting strategies, and current and future CEM indications were investigated. Replies were exploratively analyzed with descriptive and non-parametric statistics. RESULTS: Among 434 respondents (74.9% from Europe), 50% (217/434) declared to use CEM, 155/217 (71.4%) seeing less than 200 CEMs per year. CEM use was associated with academic settings and high breast imaging workload (p < 0.001). The lack of CEM adoption was most commonly due to the perceived absence of a clinical need (65.0%) and the lack of resources to acquire CEM-capable systems (37.3%). CEM protocols varied widely, but most respondents (61.3%) had already adopted the 2022 ACR CEM BI-RADS® lexicon. CEM use in patients with contraindications to MRI was the most common current indication (80.6%), followed by preoperative staging (68.7%). Patients with MRI contraindications also represented the most commonly foreseen CEM indication (88.0%), followed by the work-up of inconclusive findings at non-contrast examinations (61.5%) and supplemental imaging in dense breasts (53.0%). Respondents declaring CEM use and higher CEM experience gave significantly more current (p = 0.004) and future indications (p < 0.001). CONCLUSIONS: Despite a trend towards academic high-workload settings and its prevalent use in patients with MRI contraindications, CEM use and progressive experience were associated with increased confidence in the technique. CLINICAL RELEVANCE STATEMENT: In this first survey on contrast-enhanced mammography (CEM) use and perspectives among the European Society of Breast Imaging (EUSOBI) members, the perceived absence of a clinical need chiefly drove the 50% CEM adoption rate. CEM adoption and progressive experience were associated with more extended current and future indications. KEY POINTS: • Among the 434 members of the European Society of Breast Imaging who completed this survey, 50% declared to use contrast-enhanced mammography in clinical practice. • Due to the perceived absence of a clinical need, contrast-enhanced mammography (CEM) is still prevalently used as a replacement for MRI in patients with MRI contraindications. • The number of current and future CEM indications marked by respondents was associated with their degree of CEM experience.

Deferring diagnostic evaluation for suspected deep venous thrombosis using a single dose of anticoagulant: Real-world data from a regionwide care pathway.

BACKGROUND: Patients with suspected deep venous thrombosis (DVT) are typically referred to the emergency department (ED) for immediate evaluation. However, this often contributes to ED overcrowding and necessitates round-the-clock sonographic examinations. Therefore, we implemented a regionwide care pathway for deferring diagnostic workup of suspected DVT until the following day. Patients receive a single anticoagulant dose from their general practitioner (GP) to prevent progression of DVT in the interval between referral and diagnostic evaluation. The next day, patients undergo comprehensive evaluation at our outpatient DVT clinic, including venous ultrasound. This retrospective study aims to provide real-world data on the safety of this care pathway regarding the occurrence of bleeding complications and pulmonary embolism (PE). METHODS: We included all GP-referred patients with suspected DVT in 2018 and 2019. Patients with absolute contraindications to deferred evaluation or anticoagulation were excluded. The primary endpoint was the occurrence of bleeding complications. Secondary endpoints included PE events and all-cause mortality within seven days following DVT evaluation. RESULTS: Among 1,024 included patients, DVT was confirmed in 238 patients (23.2%) and superficial thrombophlebitis in 98 patients (9.6%). No bleeding events were recorded in patients in whom DVT was ruled out. PE was confirmed in eight patients on the same day as DVT evaluation (0.8%, 95%CI 0.4-1.6) and in six patients within seven days following DVT evaluation (0.6%, 0.2-1.3%). No deaths occurred during this timeframe. CONCLUSION: This real-world study observed a very low incidence of bleeding complications and PE events, indicating that this care pathway of deferred DVT workup is safe and may offer a more streamlined diagnostic approach for patients with suspected DVT.

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.

Impact of the COVID-19 pandemic on breast cancer incidence and tumor stage in the Netherlands and Norway: A population-based study.

BACKGROUND: Comparing the impact of the COVID-19 pandemic on the incidence of newly diagnosed breast tumors and their tumor stage between the Netherlands and Norway will help us understand the effect of differences in governmental and social reactions towards the pandemic. METHODS: Women newly diagnosed with breast cancer in 2017-2021 were selected from the Netherlands Cancer Registry and the Cancer Registry of Norway. The crude breast cancer incidence rate (tumors per 100,000 women) during the first (March-September 2020), second (October 2020-April 2021), and Delta COVID-19 wave (May-December 2021) was compared with the incidence rate in the corresponding periods in 2017, 2018, and 2019. Incidence rates were stratified by age group, method of detection, and clinical tumor stage. RESULTS: During the first wave breast cancer incidence declined to a larger extent in the Netherlands than in Norway (27.7% vs. 17.2% decrease, respectively). In both countries, incidence decreased in women eligible for screening. In the Netherlands, incidence also decreased in women not eligible for screening. During the second wave an increase in the incidence of stage IV tumors in women aged 50-69 years was seen in the Netherlands. During the Delta wave an increase in overall incidence and incidence of stage I tumors was seen in Norway. CONCLUSION: Alterations in breast cancer incidence and tumor stage seem related to a combined effect of the suspension of the screening program, health care avoidance due to the severity of the pandemic, and other unknown factors.

Association of Breast Cancer Odds with Background Parenchymal Enhancement Quantified Using a Fully Automated Method at MRI: The IMAGINE Study.

Background Background parenchymal enhancement (BPE) at breast MRI has been associated with increased breast cancer risk in several independent studies. However, variability of subjective BPE assessments have precluded its use in clinical practice. Purpose To examine the association between fully objective measures of BPE at MRI and odds of breast cancer. Materials and Methods This prospective case-control study included patients who underwent a bilateral breast MRI examination and were receiving care at one of three centers in the United States from November 2010 to July 2017. Breast volume, fibroglandular tissue (FGT) volume, and BPE were quantified using fully automated software. Fat volume was defined as breast volume minus FGT volume. BPE extent was defined as the proportion of FGT voxels with enhancement of 20% or more. Spearman rank correlation between quantitative BPE extent and Breast Imaging Reporting and Data System (BI-RADS) BPE categories assigned by an experienced board-certified breast radiologist was estimated. With use of multivariable logistic regression, breast cancer case-control status was regressed on tertiles (low, moderate, and high) of BPE, FGT volume, and fat volume, with adjustment for covariates. Results In total, 536 case participants with breast cancer (median age, 48 years [IQR, 43-55 years]) and 940 cancer-free controls (median age, 46 years [IQR, 38-55 years]) were included. BPE extent was positively associated with BI-RADS BPE (rs = 0.54; P < .001). Compared with low BPE extent (range, 2.9%-34.2%), high BPE extent (range, 50.7%-97.3%) was associated with increased odds of breast cancer (odds ratio [OR], 1.74 [95% CI: 1.23, 2.46]; P for trend = .002) in a multivariable model also including FGT volume (OR, 1.39 [95% CI: 0.97, 1.98]) and fat volume (OR, 1.46 [95% CI: 1.04, 2.06]). The association of high BPE extent with increased odds of breast cancer was similar for premenopausal and postmenopausal women (ORs, 1.75 and 1.83, respectively; interaction P = .73). Conclusion Objectively measured BPE at breast MRI is associated with increased breast cancer odds for both premenopausal and postmenopausal women. Clinical trial registration no. NCT02301767 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Bokacheva in this issue.

Impact of analysis of the sentinel lymph node by one-step nucleic acid amplification (OSNA) compared to conventional histopathology on axillary and systemic treatment: data from the Dutch nationwide cohort of breast cancer patients.

PURPOSE: The outcome of the sentinel lymph node in breast cancer patients affects adjuvant treatment. Compared to conventional histopathology, analysis by one-step nucleic acid amplification (OSNA) harvests more micrometastasis, potentially inducing overtreatment. In this study we investigated the impact of OSNA analysis on adjuvant treatment, compared to histopathological analysis. METHODS: Data from T1-3 breast cancer patients with sentinel nodes analysed between January 2016 and December 2019 by OSNA (OSNA group, n = 1086) from Zuyderland Medical Centre, the Netherlands, were compared to concurrent data from the Netherlands Cancer Registry (NKR) where sentinel nodes were examined by histology (histology group, n = 35,143). Primary outcomes were micro- or macrometastasis, axillary treatments (axillary lymph node dissection (ALND) or axillary radiotherapy (ART)), chemotherapy, and endocrine therapy. Statistics with Pearson Chi-square. RESULTS: In the OSNA group more micrometastasis (14.9%) were detected compared to the histology group (7.9%, p < 0.001). No difference in axillary treatment between groups was detected (14.3 vs. 14.4%). In case of mastectomy and macrometastasis, ALND was preferred over ART in the OSNA group (14.9%) compared to the histology group (4.4%, p < 0.001). In cases of micrometastasis, no difference was seen. There was no difference in administration of adjuvant chemotherapy between groups. Endocrine treatment was administrated less often in the OSNA group compared to the histology group (45.8% vs. 50.8%, p < 0.002). CONCLUSION: More micrometastasis were detected by OSNA compared to histopathology, but no subsequent increase in adjuvant axillary and systematic treatment was noticed. When performing mastectomy and OSNA, there was a preference for ALND compared to ART.

MSCDA: Multi-level semantic-guided contrast improves unsupervised domain adaptation for breast MRI segmentation in small datasets.

Deep learning (DL) applied to breast tissue segmentation in magnetic resonance imaging (MRI) has received increased attention in the last decade, however, the domain shift which arises from different vendors, acquisition protocols, and biological heterogeneity, remains an important but challenging obstacle on the path towards clinical implementation. In this paper, we propose a novel Multi-level Semantic-guided Contrastive Domain Adaptation (MSCDA) framework to address this issue in an unsupervised manner. Our approach incorporates self-training with contrastive learning to align feature representations between domains. In particular, we extend the contrastive loss by incorporating pixel-to-pixel, pixel-to-centroid, and centroid-to-centroid contrasts to better exploit the underlying semantic information of the image at different levels. To resolve the data imbalance problem, we utilize a category-wise cross-domain sampling strategy to sample anchors from target images and build a hybrid memory bank to store samples from source images. We have validated MSCDA with a challenging task of cross-domain breast MRI segmentation between datasets of healthy volunteers and invasive breast cancer patients. Extensive experiments show that MSCDA effectively improves the model's feature alignment capabilities between domains, outperforming state-of-the-art methods. Furthermore, the framework is shown to be label-efficient, achieving good performance with a smaller source dataset. The code is publicly available at https://github.com/ShengKuangCN/MSCDA.

Combining Deep Learning and Handcrafted Radiomics for Classification of Suspicious Lesions on Contrast-enhanced Mammograms.

Background Handcrafted radiomics and deep learning (DL) models individually achieve good performance in lesion classification (benign vs malignant) on contrast-enhanced mammography (CEM) images. Purpose To develop a comprehensive machine learning tool able to fully automatically identify, segment, and classify breast lesions on the basis of CEM images in recall patients. Materials and Methods CEM images and clinical data were retrospectively collected between 2013 and 2018 for 1601 recall patients at Maastricht UMC+ and 283 patients at Gustave Roussy Institute for external validation. Lesions with a known status (malignant or benign) were delineated by a research assistant overseen by an expert breast radiologist. Preprocessed low-energy and recombined images were used to train a DL model for automatic lesion identification, segmentation, and classification. A handcrafted radiomics model was also trained to classify both human- and DL-segmented lesions. Sensitivity for identification and the area under the receiver operating characteristic curve (AUC) for classification were compared between individual and combined models at the image and patient levels. Results After the exclusion of patients without suspicious lesions, the total number of patients included in the training, test, and validation data sets were 850 (mean age, 63 years ± 8 [SD]), 212 (62 years ± 8), and 279 (55 years ± 12), respectively. In the external data set, lesion identification sensitivity was 90% and 99% at the image and patient level, respectively, and the mean Dice coefficient was 0.71 and 0.80 at the image and patient level, respectively. Using manual segmentations, the combined DL and handcrafted radiomics classification model achieved the highest AUC (0.88 [95% CI: 0.86, 0.91]) (P < .05 except compared with DL, handcrafted radiomics, and clinical features model, where P = .90). Using DL-generated segmentations, the combined DL and handcrafted radiomics model showed the highest AUC (0.95 [95% CI: 0.94, 0.96]) (P < .05). Conclusion The DL model accurately identified and delineated suspicious lesions on CEM images, and the combined output of the DL and handcrafted radiomics models achieved good diagnostic performance. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Bahl and Do in this issue.

Comparing quality of breast cancer care in the Netherlands and Norway by federated propensity score analytics.

PURPOSE: The aim of the study was to benchmark and compare breast cancer care quality indicators (QIs) between Norway and the Netherlands using federated analytics preventing transfer of patient-level data. METHODS: Breast cancer patients (2017-2018) were retrieved from the Netherlands Cancer Registry and the Cancer Registry of Norway. Five European Society of Breast Cancer Specialists (EUSOMA) QIs were assessed: two on magnetic resonance imaging (MRI), two on surgical approaches, and one on postoperative radiotherapy. The QI outcomes were calculated using 'Vantage 6' federated Propensity Score Stratification (PSS). Likelihood of receiving a treatment was expressed in odds ratios (OR). RESULTS: In total, 39,163 patients were included (32,786 from the Netherlands and 6377 from Norway). PSS scores were comparable to the crude outcomes of the QIs. The Netherlands scored higher on the QI 'proportions of patients preoperatively examined with breast MRI' [37% vs.17.5%; OR 2.8 (95% CI 2.7-2.9)], the 'proportions of patients receiving primary systemic therapy examined with breast MRI' [83.3% vs. 70.8%; OR 2.3 (95% CI 1.3-3.3)], and 'proportion of patients receiving a single breast operation' [95.2% vs. 91.5%; OR 1.8 (95% CI 1.4-2.2)]. Country scores for 'immediate breast reconstruction' and 'postoperative radiotherapy after breast-conserving surgery' were comparable. The EUSOMA standard was achieved in both countries for 4/5 indicators. CONCLUSION: Both countries achieved high scores on the QIs. Differences were observed in the use of MRI and proportion of patients receiving single surgery. The federated approach supports future possibilities on benchmark QIs without transfer of privacy-sensitive data.