Contrast-enhanced MRI for breast cancer screening

BIRADS 4 - Is it possible to downgrade lesions that do not enhance on recombinant contrast-enhanced mammography images?

PURPOSE

Analysis of the morphology of lesions classified into the BI-RADS 4 category and assessment of the possibility of downgrade the BI-RADS category in those that did not show enhancement on recombinant contrast-enhanced mammography (CEM) images.

METHOD

The retrospective, single-center study included 528 patients who underwent a core needle biopsy performed from January 2017 to November 2022 due to a breast lesion classified as BI-RADS 4 on CEM. Patients' electronic records and imaging examinations were reviewed. Individual lesions were classified into the morphological categories of mass, non-mass, and microcalcifications. Sensitivity, specificity, positive as well as negative predictive values were calculated for the whole group and individual morphological categories. The influence of the lesions' diameter on the results was analyzed.

RESULTS

CEM NPV for the whole group was 93.9% (±95% CI: 90.0-96.4), for mass lesions 100% (±95% CI: 94.5-100), for non-mass lesions 97.8% (±95% CI: 87.0-99.9) and 87.9% (±95% CI: 80.3-93.0) for microcalcifications. Given that 230 out of 383 benign lesions were not contrast-enhancing, 60.1% of unnecessary CNBs would have been correctly avoided. CEM sensitivity for lesions < 20 mm was lower than for lesions ≥ 20 mm and was respectively 86.6% (±95% CI: 76.8-92.8) vs 94.6% (±95% CI: 86.0-98.2), respectively.

CONCLUSION

CEM is characterized by high sensitivity in the detection of malignant lesions in the case of lesions with mass and non-mass morphology. The high NPV for recombinant images suggests that in the case of these lesions, the lack of enhancement supports the benign nature of the lesion and may lead to a downgrade of the BI-RADS category.

Phantom-based assessment of motion and needle targeting accuracy of robotic devices for magnetic resonance imaging-guided needle biopsy

BACKGROUND

The current study proposes simple methods for assessing the performance of robotic devices intended for Magnetic Resonance Imaging (MRI)-guided needle biopsy.

METHODS

In-house made agar-based breast phantoms containing biopsy targets served as the main tool in the evaluation process of an MRI compatible positioning device comprising a needle navigator. The motion accuracy of mechanical stages was assessed by calliper measurements. Laboratory evaluation of needle targeting included a repeatability phantom test and a laser-based method. The accuracy and repeatability of needle targeting was also assessed by MRI.

RESULTS

The maximum error of linear motion for steps up to 10 mm was 0.1 mm. Needle navigation relative to the phantom and alignment with the various biopsy targets were performed successfully in both the laboratory and MRI settings. The proposed biopsy phantoms offered tissue-like signal in MRI and good haptic feedback during needle insertion.

CONCLUSIONS

The proposed methods could be valuable in the process of validating the accuracy of MRI-guided biopsy robotic devices in both laboratory and real environments.

New Approaches and Recommendations for Risk-Adapted Breast Cancer Screening

Population-based breast cancer screening using mammography as the gold standard imaging modality has been in clinical practice for over 40 years. However, the limitations of mammography in terms of sensitivity and high false-positive rates, particularly in high-risk women, challenge the indiscriminate nature of population-based screening. Additionally, in light of expanding research on new breast cancer risk factors, there is a growing consensus that breast cancer screening should move toward a risk-adapted approach. Recent advancements in breast imaging technology, including contrast material-enhanced mammography (CEM), ultrasound (US) (automated-breast US, Doppler, elastography US), and especially magnetic resonance imaging (MRI) (abbreviated, ultrafast, and contrast-agent free), may provide new opportunities for risk-adapted personalized screening strategies. Moreover, the integration of artificial intelligence and radiomics techniques has the potential to enhance the performance of risk-adapted screening. This review article summarizes the current evidence and challenges in breast cancer screening and highlights potential future perspectives for various imaging techniques in a risk-adapted breast cancer screening approach. EVIDENCE LEVEL: 1. TECHNICAL EFFICACY: Stage 5.

A robust and efficient AI assistant for breast tumor segmentation from DCE-MRI via a spatial-temporal framework

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) allows screening, follow up, and diagnosis for breast tumor with high sensitivity. Accurate tumor segmentation from DCE-MRI can provide crucial information of tumor location and shape, which significantly influences the downstream clinical decisions. In this paper, we aim to develop an artificial intelligence (AI) assistant to automatically segment breast tumors by capturing dynamic changes in multi-phase DCE-MRI with a spatial-temporal framework. The main advantages of our AI assistant include (1) robustness, i.e., our model can handle MR data with different phase numbers and imaging intervals, as demonstrated on a large-scale dataset from seven medical centers, and (2) efficiency, i.e., our AI assistant significantly reduces the time required for manual annotation by a factor of 20, while maintaining accuracy comparable to that of physicians. More importantly, as the fundamental step to build an AI-assisted breast cancer diagnosis system, our AI assistant will promote the application of AI in more clinical diagnostic practices regarding breast cancer.

Diffusion-weighted Breast MRI at 3 Tesla: Improved Lesion Visibility and Image Quality with a Combination of Water-excitation and Spectral Fat Saturation

RATIONALE AND OBJECTIVES

In breast MRI with diffusion-weighted imaging (DWI), fat suppression is essential for eliminating the dominant lipid signal. This investigation evaluates a combined water-excitation-spectral-fatsat method (WEXfs) versus standard spectral attenuated inversion recovery (SPAIR) in high-resolution 3-Tesla breast MRI.

MATERIALS AND METHODS

Multiparametric breast MRI with 2 echo-planar DWI sequences was performed in 83 patients (50.1 ± 12.6 years) employing either WEXfs or SPAIR for fat signal suppression. Three radiologists assessed overall DWI quality and delineability of 88 focal lesions (28 malignant, 60 benign) on images with b values of 800 and 1600 s/mm2, as well as apparent diffusion coefficient (ADC) maps. For each fat suppression method and b value, the longest lesion diameter was determined in addition to measuring the signal intensity in DWI and ADC value in standardized regions of interest.

RESULTS

Regardless of b values, image quality (all p < 0.001) and lesion delineability (all p ≤ 0.003) with WEXfs-DWI were deemed superior compared to SPAIR-DWI in benign and malignant lesions. Irrespective of lesion characterization, WEXfs-DWI provided superior signal-to-noise, contrast-to-noise and signal-intensity ratios with 1600 s/mm2 (all p ≤ 0.05). The lesion size difference between contrast-enhanced T1 subtraction images and DWI was smaller for WEXfs compared to SPAIR fat suppression (all p ≤ 0.007). The mean ADC value in malignant lesions was lower for WEXfs-DWI (p < 0.001), while no significant ADC difference was ascertained between both techniques in benign lesions (p = 0.947).

CONCLUSION

WEXfs-DWI provides better subjective and objective image quality than standard SPAIR-DWI, resulting in a more accurate estimation of benign and malignant lesion size.

Deep Learning-based Automatic Diagnosis of Breast Cancer on MRI Using Mask R-CNN for Detection Followed by ResNet50 for Classification

RATIONALE AND OBJECTIVES

Diagnosis of breast cancer on MRI requires, first, the identification of suspicious lesions; second, the characterization to give a diagnostic impression. We implemented Mask Reginal-Convolutional Neural Network (R-CNN) to detect abnormal lesions, followed by ResNet50 to estimate the malignancy probability.

MATERIALS AND METHODS

Two datasets were used. The first set had 176 cases, 103 cancer, and 73 benign. The second set had 84 cases, 53 cancer, and 31 benign. For detection, the pre-contrast image and the subtraction images of left and right breasts were used as inputs, so the symmetry could be considered. The detected suspicious area was characterized by ResNet50, using three DCE parametric maps as inputs. The results obtained using slice-based analyses were combined to give a lesion-based diagnosis.

RESULTS

In the first dataset, 101 of 103 cancers were detected by Mask R-CNN as suspicious, and 99 of 101 were correctly classified by ResNet50 as cancer, with a sensitivity of 99/103 = 96%. 48 of 73 benign lesions and 131 normal areas were identified as suspicious. Following classification by ResNet50, only 16 benign and 16 normal areas remained as malignant. The second dataset was used for independent testing. The sensitivity was 43/53 = 81%. Of the total of 121 identified non-cancerous lesions, only 6 of 31 benign lesions and 22 normal tissues were classified as malignant.

CONCLUSION

ResNet50 could eliminate approximately 80% of false positives detected by Mask R-CNN. Combining Mask R-CNN and ResNet50 has the potential to develop a fully-automatic computer-aided diagnostic system for breast cancer on MRI.

Influence of mammographic density and compressed breast thickness on true mammographic sensitivity: a cohort study

Understanding the detectability of breast cancer using mammography is important when considering nation-wide screening programmes. Although the role of imaging settings on image quality has been studied extensively, their role in detectability of cancer at a population level is less well studied. We wish to quantify the association between mammographic screening sensitivity and various imaging parameters. Using a novel approach applied to a population-based breast cancer screening cohort, we specifically focus on sensitivity as defined in the classical diagnostic testing literature, as opposed to the screen-detected cancer rate, which is often used as a measure of sensitivity for monitoring and evaluating breast cancer screening. We use a natural history approach to model the presence and size of latent tumors at risk of detection at mammography screening, and the screening sensitivity is modeled as a logistic function of tumor size. With this approach we study the influence of compressed breast thickness, x-ray exposure, and compression pressure, in addition to (percent) breast density, on the screening test sensitivity. When adjusting for all screening parameters in addition to latent tumor size, we find that percent breast density and compressed breast thickness are statistically significant factors for the detectability of breast cancer. A change in breast density from 6.6 to 33.5% (the inter-quartile range) reduced the odds of detection by 61% (95% CI 48-71). Similarly, a change in compressed breast thickness from 46 to 66 mm reduced the odds by 42% (95% CI 21-57). The true sensitivity of mammography, defined as the probability that an examination leads to a positive result if a tumour is present in the breast, is associated with compressed breast thickness after accounting for mammographic density and tumour size. This can be used to guide studies of setups aimed at improving lesion detection. Compressed breast thickness-in addition to breast density-should be considered when assigning complementary screening modalities and personalized screening intervals.

Iopromide for Contrast-Enhanced Mammography: A Systemic Review and Meta-Analysis of Pertinent Literature

Background

Contrast-enhanced mammography (CEM) is an emerging breast imaging modality. Clinical data is scarce.

Objectives

To summarize clinical evidence on the use of iopromide in CEM for the detection or by systematically analyzing the available literature on efficacy and safety.

Design

Systematic review and meta-analysis.

Data sources and methods

Iopromide-specific publications reporting its use in CEM were identified by a systematic search within Bayer's Product Literature Information (PLI) database and by levering a recent review publication. The literature search in PLI was performed up to January 2023. The confirmatory-supporting review publication was based on a MEDLINE/EMBASE + full text search for publications issued between September 2003 and January 2019. Relevant literature was selected based on pre-defined criteria by 2 reviewers. The comparison of CEM vs traditional mammography (XRM) was performed on published results of sensitivity and specificity. Differences in diagnostic parameters were assessed within a meta-analysis.

Results

Literature search: A total of 31 studies were identified reporting data on 5194 patients. Thereof, 19 studies on efficacy and 3 studies on safety. Efficacy: in 11 studies comparing iopromide CEM vs XRM, sensitivity was up to 43% higher (range 1%-43%) for CEM. Differences in specificity were found to be in a range of -4% to 46% for CEM compared with XRM. The overall gain in sensitivity for CEM vs XRM was 7% (95% CI [4%, 11%]) with no statistically significant loss in specificity in any study assessed. In most studies, accuracy, positive predictive value, and negative predictive value were found to be in favor of CEM. In 2 studies comparing CEM with breast magnetic resonance imaging (bMRI), both imaging modalities performed either equally well or CEM tended to show better results with respect to sensitivity and specificity. Safety: eight cases of iopromide-related adverse drug reactions were reported in 1022 patients (0.8%).

Conclusions

Pertinent literature provides evidence for clinical utility of iopromide in CEM for the detection or confirmation of breast cancer. The overall gain in sensitivity for iopromide CEM vs XRM was 7% with no statistically significant loss in specificity.

The Role of Diffusion-Weighted Imaging Based on Maximum-Intensity Projection in Young Patients with Marked Background Parenchymal Enhancement on Contrast-Enhanced Breast MRI

Diffusion-weighted imaging (DWI) utilizing maximum-intensity projection (MIP) was suggested as a cost-effective alternative tool without the risk of gadolinium-based contrast agents. The purpose of this study was to investigate whether DWI MIPs played a supportive role in young (≤60) patients with marked background parenchymal enhancement (BPE) on contrast-enhanced MRI (CE-MRI). The research included 1303 patients with varying degrees of BPE, and correlations between BPE on CE-MRI, the background diffusion signal (BDS) on DWI, and clinical parameters were analyzed. Lesion detection scores were compared between CE-MRI and DWI, with DWI showing higher scores. Among the 186 lesions in 181 patients with marked BPE on CE-MRI, the main lesion on MIPs of CE-MRI was partially or completely seen in 88.7% of cases, while it was not seen in 11.3% of cases. On the other hand, the main lesion on MIPs of DWI was seen in 91.4% of cases, with only 8.6% of cases showing no visibility. DWI achieved higher scores for lesion detection compared to CE-MRI. The presence of a marked BDS was significantly associated with a lower likelihood of a higher DWI score (p < 0.001), and non-mass lesions were associated with a decreased likelihood of a higher DWI score compared with mass lesions (p = 0.196). In conclusion, the inclusion of MIPs of DWI in the preoperative evaluation of breast cancer patients, particularly young women with marked BPE, proved highly beneficial in improving the overall diagnostic process.

Deep learning applications to breast cancer detection by magnetic resonance imaging: a literature review

Deep learning analysis of radiological images has the potential to improve diagnostic accuracy of breast cancer, ultimately leading to better patient outcomes. This paper systematically reviewed the current literature on deep learning detection of breast cancer based on magnetic resonance imaging (MRI). The literature search was performed from 2015 to Dec 31, 2022, using Pubmed. Other database included Semantic Scholar, ACM Digital Library, Google search, Google Scholar, and pre-print depositories (such as Research Square). Articles that were not deep learning (such as texture analysis) were excluded. PRISMA guidelines for reporting were used. We analyzed different deep learning algorithms, methods of analysis, experimental design, MRI image types, types of ground truths, sample sizes, numbers of benign and malignant lesions, and performance in the literature. We discussed lessons learned, challenges to broad deployment in clinical practice and suggested future research directions.

Preoperative Breast Magnetic Resonance Imaging: An Ontario Health (Cancer Care Ontario) Clinical Practice Guideline

BACKGROUND

The use of preoperative breast magnetic resonance imaging (MRI) after the diagnosis of breast cancer by mammography and/or ultrasound is inconsistent.

METHODS

After conducting a systematic review and meta-analysis comparing preoperative breast MRI versus no MRI, we reconvened to prepare a clinical practice guideline on this topic.

RESULTS

Based on the evidence that MRI improved recurrence, decreased the rates of reoperations (re-excisions or conversion mastectomy), and increased detection of synchronous contralateral breast cancer, we recommend that preoperative breast MRI should be considered on a case-by-case basis in patients diagnosed with breast cancer for whom additional information about disease extent could influence treatment. Based on stronger evidence, preoperative breast MRI is recommended in patients diagnosed with invasive lobular carcinoma for whom additional information about disease extent could influence treatment. For both recommendations, the decision to proceed with MRI would be conditional on shared decision-making between care providers and the patient, taking into account the benefits and risks of MRI as well as patient preferences. Based on the opinion of the Working Group, preoperative breast MRI is also recommended in the following more specific situations: (a) to aid in surgical planning of breast conserving surgery in patients with suspected or known multicentric or multifocal disease; (b) to identify additional lesions in patients with dense breasts; (c) to determine the presence of pectoralis major muscle/chest wall invasion in patients with posteriorly located tumours or when invasion of the pectoralis major muscle or chest wall is suspected; (d) to aid in surgical planning for skin/nipple-sparing mastectomies, autologous reconstruction, oncoplastic surgery, and breast conserving surgery with suspected nipple/areolar involvement; and (e) in patients with familial/hereditary breast cancer but who have not had recent breast MRI as part of screening or diagnosis.

Image quality assessment using deep learning in high b-value diffusion-weighted breast MRI

The objective of this IRB approved retrospective study was to apply deep learning to identify magnetic resonance imaging (MRI) artifacts on maximum intensity projections (MIP) of the breast, which were derived from diffusion weighted imaging (DWI) protocols. The dataset consisted of 1309 clinically indicated breast MRI examinations of 1158 individuals (median age [IQR]: 50 years [16.75 years]) acquired between March 2017 and June 2020, in which a DWI sequence with a high b-value equal to 1500 s/mm2 was acquired. From these, 2D MIP images were computed and the left and right breast were cropped out as regions of interest (ROI). The presence of MRI image artifacts on the ROIs was rated by three independent observers. Artifact prevalence in the dataset was 37% (961 out of 2618 images). A DenseNet was trained with a fivefold cross-validation to identify artifacts on these images. In an independent holdout test dataset (n = 350 images) artifacts were detected by the neural network with an area under the precision-recall curve of 0.921 and a positive predictive value of 0.981. Our results show that a deep learning algorithm is capable to identify MRI artifacts in breast DWI-derived MIPs, which could help to improve quality assurance approaches for DWI sequences of breast examinations in the future.

The Future of Breast Cancer Research in the Survivorship Field

Prevalence of survivors of breast cancer has been steadily increasing in the last 20 years. Currently, more than 90% of women diagnosed with early-stage breast cancer are expected to be alive at 5 years from diagnosis thanks to early detection and breakthrough innovations in multimodal treatment strategies. Alongside this advancement in clinical outcomes, survivors of breast cancer might experience several specific challenges and present with unique needs. Survivorship trajectories after diagnosis and treatment of breast cancer can be significantly impacted by long-lasting and severe treatment-related side effects, including physical problems, psychological distress, fertility issues in young women, and impaired social and work reintegration, which add up to patients' individual risk of cancer recurrence and second primary malignancies. Alongside cancer-specific sequelae, survivors still present with general health needs, including management of chronic preexisting or ensuing conditions. Survivorship care should implement high-quality, evidence-based strategies to promptly screen, identify, and address survivors' needs in a comprehensive way and minimize the impact of severe treatment sequelae, preexisting comorbidities, unhealthy lifestyles, and risk of recurrence on quality of life. This narrative review focuses on core areas of survivorship care and discuss the state of the art and future research perspectives in key domains including selected long-term side effects, surveillance for recurrences and second cancers, well-being promotion, and specific survivors' needs.

Abbreviated Breast MRI: Our Two-Year Initial Experience

OBJECTIVE

The aim of this study was to retrospectively evaluate and present our two-year experience with abbreviated breast MRI at our academic institution as a screening tool to identify primary breast cancers.

METHODS

Employing eight specialty trained breast radiologists, studies were interpreted using the BI-RADS MRI lexicon in this IRB-approved retrospective study. The protocol utilized T1-weighted, fat-saturated, pre- and post-contrast, short  T1 inversion recovery images, and was completed within 10 minutes. Abbreviated breast MRI was offered to asymptomatic women of all breast densities, whose ages ranged from 24 to 90 years. Statistical analysis was performed for comparative data utilizing estimated odds ratios.

RESULTS

Of 1338 patients that met inclusion criteria, 83% (1111/1338) were BI-RADS 1 or 2, 9.0% (121/1338) were BI-RADS 3, and 8% (106/1338) were categorized as either BI-RADS 4 or 5 with recommended biopsy. Biopsy of BI-RADS 4 and 5 categorized patients yielded 15 cancers for a positive predictive value (PPV) 2 of 14.2% and a PPV3 of 18.5%, with 76% (81/106) of patients undergoing the recommended biopsy. An additional cancer was detected in a BI-RADS 3 finding. All cancers detected were in women with heterogeneously dense or extremely dense breasts. Therefore, 16 cancers were detected, yielding a cancer detection rate of 12.0 per 1000. Over the next 12 to 24 months, no interval cancers were detected.

CONCLUSION

Abbreviated breast MRI demonstrates a higher cancer detection rate compared with mammography only and may provide a supplemental screening method to detect breast cancers in patients with varying risk factors.

Evaluation of breast lesions based on modified BI-RADS using high-resolution readout-segmented diffusion-weighted echo-planar imaging and T2/T1-weighted image

PURPOSE

To evaluate the diagnostic performance of a non-contrast magnetic resonance imaging (MRI) protocol combining high-resolution diffusion-weighted images (HR-DWI) using readout-segmented echo planar imaging, T1-weighted imaging (T1WI), and T2-weighted imaging (T2WI), using our modified Breast Imaging-Reporting and Data System (modified BI-RADS).

METHODS

Two experienced radiologists, blinded to the final pathological diagnosis, categorized a total of 108 breast lesions (61 malignant and 47 benign) acquired with the above protocol using the modified BI-RADS with a diagnostic decision tree. The decision tree included subcategories of category 4, as in mammography (categories 2, 3, 4A, 4B, 4C, and 5). These results were compared with the pathological diagnoses.

RESULTS

The area under the ROC curve (AUC) was 0.89 (95% confidence interval [CI]: 0.83-0.95) for reader 1, and 0.89 (95% CI: 0.82-0.96) for reader 2. When categories 4C and above were classified as malignant, the sensitivity, specificity, and accuracy were 73.8%, 93.6%, and 82.4%, for reader 1; and 82.0%, 89.4%, and 85.2% for reader 2, respectively.

CONCLUSION

Our results suggest that using HR-DWI, T1WI/T2WI analyzed with a modified BI-RADS and a decision tree showed promising diagnostic performance in breast lesions, and is worthy of further study.

Improvement of semantic segmentation through transfer learning of multi-class regions with convolutional neural networks on supine and prone breast MRI images

Semantic segmentation of breast and surrounding tissues in supine and prone breast magnetic resonance imaging (MRI) is required for various kinds of computer-assisted diagnoses for surgical applications. Variability of breast shape in supine and prone poses along with various MRI artifacts makes it difficult to determine robust breast and surrounding tissue segmentation. Therefore, we evaluated semantic segmentation with transfer learning of convolutional neural networks to create robust breast segmentation in supine breast MRI without considering supine or prone positions. Total 29 patients with T1-weighted contrast-enhanced images were collected at Asan Medical Center and two types of breast MRI were performed in the prone position and the supine position. The four classes, including lungs and heart, muscles and bones, parenchyma with cancer, and skin and fat, were manually drawn by an expert. Semantic segmentation on breast MRI scans with supine, prone, transferred from prone to supine, and pooled supine and prone MRI were trained and compared using 2D U-Net, 3D U-Net, 2D nnU-Net and 3D nnU-Net. The best performance was 2D models with transfer learning. Our results showed excellent performance and could be used for clinical purposes such as breast registration and computer-aided diagnosis.

Disparities in the use of screening breast magnetic resonance imaging persist in Louisiana after the Affordable Care Act: A question of access, policy, institutional support, or something else?

BACKGROUND

Louisiana continues to have one of the highest breast cancer mortality rates in the nation, and Black women are disproportionally affected. Louisiana has made advances in improving access to breast cancer screening through the expansion of Medicaid. There remains, however, broad underuse of advanced imaging technology such as screening breast magnetic resonance imaging (MRI), particularly for Black women.

METHODS

Breast MRI has been proven to be very sensitive for the early detection of breast cancer in women at high risk. MRI is more sensitive than mammography for aggressive, invasive breast cancer types, which disproportionally affect Black women. Here the authors identify potential barriers to breast MRI screening in Black women, propose strategies to address disparities in access, and advocate for specific recommendations for change.

RESULTS

Cost was identified as one of the greatest barriers to screening breast MRI. The authors propose implementation of cost-saving, abbreviated protocols to address cost along with lobbying for further expansion of the Affordable Care Act (ACA) to include coverage for screening breast MRI. In addition, addressing gaps in communication and knowledge and facilitating providers' ability to readily identify women who might benefit from MRI could be particularly impactful for high-risk Black women in Louisiana communities.

CONCLUSIONS

Since the adoption of the ACA in Louisiana, Black women have continued to have disproportionally high breast cancer mortality rates. This persistent disparity provides evidence that additional change is needed. This change should include exploring innovative ways to make advanced imaging technology such as breast MRI more accessible and expanding research to specifically address community and culturally specific barriers.

Comprehensive Care of Women With Genetic Predisposition to Breast and Ovarian Cancer

Women at risk for hereditary breast and ovarian cancer syndromes are frequently seen in primary care and gynecology clinics. They present with a distinctive set of clinical and emotional needs that revolve around complex risk management discussions and decision making. The care of these women calls for the creation of individualized care plans that facilitate adjustment to the mental and physical changes associated with their choices. This article provides an update on comprehensive evidence-driven care of women with hereditary breast and ovarian cancer. The aim of this review is to aid clinicians in identifying those at risk for hereditary cancer syndromes and provide practical advice on patient-centered medical and surgical risk management. Topics of discussion include enhanced surveillance, preventive medications, risk-reducing mastectomy and reconstruction, risk-reducing bilateral salpingo-oophorectomy, fertility, sexuality, and menopausal management, with attention to the importance of psychological support. High-risk patients may benefit from a multidisciplinary team that provides realistic expectations with consistent messaging. The primary care provider must be aware of the special needs of these patients and the consequences of their risk management interventions.

Clinical utility of abbreviated breast MRI based on diffusion tensor imaging in patients underwent breast conservative therapy

PURPOSE

To evaluate the added value of the diffusion tensor imaging (DTI) parameters to abbreviated breast MRI protocol in differentiating recurrent breast cancer from post-operative changes in cases of breast conservative surgery (BCS).

METHODS

This prospective study was approved by our institutional review board. Written informed consent was obtained in all patients. 47 female patients (mean age, 49 years; range, 32-66 years) that previously underwent breast conservative surgery with a palpable mass were included in this study (62 breast lesions). Two abbreviated MRI protocols were compared using 1.5 Tesla MRI, AB-MRI 1 (axial T1, T2, pre-contrast T1, 1st post-contrast and subtracted images) and AB-MRI 2 (same sequences plus adding DTI). In both protocols, the wash-in rate was calculated. Histopathology was used as the standard of reference. Appropriate statistical tests were used to assess sensitivity, specificity, and diagnostic accuracy for each protocol.

RESULTS

The mean total acquisition time was of 6 min for AB-MRI 1 and 10 min for AB-MRI 2 protocols while the mean interpretation time was of 57.5 and 75 s, respectively. Among analyzed DTI parameters, MD (mean diffusivity) showed the highest sensitivity (96.43%) and specificity (91.18%) (P value =  < 0.001). FA (fractional anisotropy), AD (axial diffusivity) and RD (radial diffusivity) showed sensitivity = (78.57%, 82.14% and 85.71%), specificity = (88.24, 85.29% and 79.41%), respectively, P value (< 0.001).

CONCLUSION

DTI may be included in abbreviated MRI protocols without a significant increase in acquisition time and with the advantage of increasing specificity and clinical utility in the characterization of post-conservative breast lesions.

Evaluating potential overuse of surveillance care in cancer survivors

BACKGROUND

Survivorship care plans (SCPs) communicate cancer-related information from oncology providers to patients and primary care providers. SCPs may limit overuse testing by specifying necessary follow-up care. From a randomized, controlled trial of SCP delivery, we examined whether cancer-related tests not specified in SCPs, but conducted after SCP receipt, were appropriate or consistent with overuse.

METHODS

Survivors of breast, colorectal, or prostate cancer treated at urban-academic or rural-community health systems were randomized to one of three SCP delivery arms. Tests during 18 months after SCP receipt were classified as consistent with overuse if they were (1) not included in SCPs and (2) on a guideline-based predetermined list of "not recommended surveillance." After chart abstraction, physicians performed review and adjudication of potential overuse. Descriptive analyses were conducted of tests consistent with overuse. Negative binomial regression models determined if testing consistent with overuse differed across study arms.

RESULTS

Among 316 patients (137 breast, 67 colorectal, 112 prostate), 140 individual tests were identified as potential overuse. Upon review, 98 were deemed to be consistent with overuse: 78 tumor markers and 20 imaging tests. The majority of overuse testing was breast cancer-related (95%). Across sites, 27 patients (9%) received ≥1 test consistent with overuse; most were breast cancer patients (22/27). Exploratory analyses of overuse test frequency by study arm showed no significant difference.

CONCLUSIONS

This analysis identified practice patterns consistent with overuse of surveillance testing and can inform efforts to improve guideline-concordant care. Future interventions may include individual practice patterns and provider education.

Implementation of abbreviated breast MRI in diagnostic and screening settings

BACKGROUND

Abbreviated magnetic resonance imaging (MRI) includes fewer sequences than standard MRI, which could be utilized for breast cancer detection.

PURPOSE

To evaluate the diagnostic accuracy of abbreviated MRI protocol in screening and diagnostic settings.

MATERIAL AND METHODS

All women with screening and diagnostic (problem-solving and preoperative staging) MRI examination were recruited from 2017 to 2020. Two expert radiologists assessed designed abbreviated protocol (fat-saturated T1-weighted [T1W] pre-contrast and two first fat-saturated T1W post-contrast series with reconstruction of their subtraction) including maximum intensity projection (MIP) and then evaluated standard protocol of breast MRI. Associated findings, including axillary lymphadenopathy and invasion to nipple, skin, or pectoralis muscle were also evaluated. The concordance rate of abbreviated with standard protocol in screening and diagnostic settings were also compared, based on BI-RADS classification. Diagnostic accuracy, sensitivity, specificity, and positive and negative predictive value were calculated.

RESULTS

A total of 108 (26.5%) of 408 patients (mean age = 43 ± 9 years) were classified as BI-RADS 4-5 and considered positive findings based on suspicious enhancement (mass or non-mass enhancement). Compared to standard protocol, abbreviated protocol revealed >98% accuracy in the diagnostic setting as well as 100% accuracy in the screening setting. Concordance rates in screening and diagnostic settings were 99.6% and 98.1%, respectively. There was no discordance between abbreviated and standard protocol in the evaluation of associated findings.

CONCLUSION

Abbreviated MRI protocol possesses substantial diagnostic accuracy in both screening and diagnostic settings. Additional information provided by standard protocol might not require for cancer detection.

Challenges and Changes of the Breast Cancer Screening Paradigm

Since four decades mammography is used for early breast cancer detection in asymptomatic women and still remains the gold standard imaging modality. However, population screening programs can be personalized and women can be divided into different groups based on risk factors and personal preferences. The availability of new and evolving imaging modalities, for example, digital breast tomosynthesis, dynamic-contrast-enhanced magnetic resonance imaging (MRI), abbreviated MRI protocols, diffusion-weighted MRI, and contrast-enhanced mammography leads to new challenges and perspectives regarding the feasibility and potential harms of breast cancer screening. The aim of this review is to discuss the current guidelines for different risk groups, to analyze the recent published studies about the diagnostic performance of the imaging modalities and to discuss new developments and future perspectives. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY: Stage 6.

Utility of MRI-Directed Contrast-Enhanced Mammography for Biopsy Planning for Suspicious MRI-Detected Breast Lesions

BACKGROUND. Suspicious lesions detected on contrast-enhanced breast MRI often undergo targeted ultrasound evaluation to determine whether they are amenable to ultrasound-guided biopsy. OBJECTIVE. The purpose of this study is to assess the utility of MRI-directed contrast-enhanced mammography (CEM) performed for biopsy planning for suspicious MRI-detected breast lesions and to compare its use with that of MRI-directed ultrasound. METHODS. This retrospective study included 120 patients (median age, 50.3 years) who underwent MRI-directed CEM from September 2014 to July 2020 for biopsy planning for a total of 140 suspicious breast MRI lesions; 109 lesions were also evaluated by MRI-directed ultrasound at the same visit. The reference standard was histopathology or at least 2 years of imaging follow-up for benign lesions. Rates of detecting a correlate for the MRI lesion, among all lesions and among malignant lesions, were compared between MRI-directed CEM, MRI-directed ultrasound, and combined MRI-directed CEM and ultrasound (i.e., with the correlate detected on either modality), by use of the McNemar test. The frequencies with which imaging modalities were used for biopsy guidance after MRI-directed imaging were determined. RESULTS. Twenty-three of 109 lesions were malignant. The lesion detection rate was higher for MRI-directed CEM than for MRI-directed ultrasound (69.7% [76/109] vs 45.9% [50/109]; p < .001) and higher for combined MRI-directed CEM and ultrasound (77.1% [84/109]) than for either MRI-directed CEM (p = .008) or MRI-directed ultrasound (p < .001). The rate of detection of malignant lesions was not significantly different between MRI-directed CEM and MRI-directed ultrasound (95.7% [22/23] vs 78.3% [18/23]; p = .13). A total of 31.2% (34/109) of lesions were seen on MRI-directed CEM only, and 7.3% (8/109) were seen on MRI-directed ultrasound only. A total of 17.4% (4/23) of malignant lesions were seen on MRI-directed CEM only, and none were seen on MRI-directed ultrasound only. Among lesions recommended for biopsy, stereotactic- or tomosynthesis-guided biopsy was recommended for 25.2% (26/103), ultrasound-guided biopsy for 35.9% (37/103), and MRI-guided biopsy for 38.8% (40/103). CONCLUSION. MRI-directed CEM detects a higher fraction of suspicious MRI lesions than does MRI-directed ultrasound. Combined MRI-directed CEM and ultrasound detects a higher fraction than either method does individually. CLINICAL IMPACT. MRI-directed CEM may be a useful alternate or complementary tool to MRI-directed ultrasound in biopsy planning for suspicious MRI lesions, facilitating the use of biopsy guidance methods other than MRI guidance.

Novel manganese and polyester dendrimer-based theranostic nanoparticles for MRI and breast cancer therapy

Therapeutic nanoplatforms are widely used in the diagnosis and treatment of breast cancer due to the merits of enabling high soft-tissue resolution and the availability of numerous therapeutic nanoparticles. It is thus vital to develop multifunctional theranostic nanoparticles for the visualization and dynamic monitoring of tumor therapy. In this study, we designed a manganese-based and hypericin-loaded polyester dendrimer nanoparticle (MHD) for magnetic resonance imaging (MRI) and hypericin-based photodynamic therapy (PDT) enhancement. We found that MHD could greatly enhance MRI contrast with a longitudinal relaxivity of 5.8 mM^-1 s^-1 due to the Mn-based paramagnetic dendrimer carrier. Meanwhile, the MRI-guided PDT inhibition of breast tumors could be achieved by the hypericin-carrying MHD and further improved by Mn²⁺-mediated alleviation of the hypoxic microenvironment and the enhancement of cellular ROS. Besides, MHD showed excellent biocompatibility and biosafety with liver and kidney clearance mechanisms. Thus, the high efficiency in MRI contrast enhancement and excellent tumor-inhibiting effects indicate MHD's potential as a novel, stable, and multifunctional nanotheranostic agent for breast cancer.

Background Parenchymal Enhancement at Postoperative Surveillance Breast MRI: Association with Future Second Breast Cancer Risk

Background Background parenchymal enhancement (BPE) is a known risk factor for breast cancer. However, studies on the association between BPE and second breast cancer risk are still lacking. Purpose To investigate whether BPE at surveillance breast MRI is associated with subsequent second breast cancer risk in women with a personal history of breast cancer. Materials and Methods A retrospective search of the imaging database of an academic medical center identified consecutive surveillance breast MRI examinations performed between January 2008 and December 2017 in women who underwent surgery for primary breast cancer and had no prior diagnosis of second breast cancer. BPE at surveillance breast MRI was qualitatively assessed using a four-category classification of minimal, mild, moderate, or marked. Future second breast cancer was defined as ipsilateral breast tumor recurrence or contralateral breast cancer diagnosed at least 1 year after each surveillance breast MRI examination. Factors associated with future second breast cancer risk were evaluated using the multivariable Fine-Gray subdistribution hazard model. Results Among the 2668 women (mean age at baseline surveillance breast MRI, 49 years ± 8 [SD]), 109 developed a second breast cancer (49 ipsilateral, 58 contralateral, and two ipsilateral and contralateral) at a median follow-up of 5.8 years. Mild, moderate, or marked BPE at surveillance breast MRI (hazard ratio [HR], 2.1 [95% CI: 1.4, 3.1]; P < .001), young age (<45 years) at initial breast cancer diagnosis (HR, 3.4 [95% CI: 1.7, 6.4]; P < .001), positive results from a BRCA1/2 genetic test (HR, 6.5 [95% CI: 3.5, 12.0]; P < .001), and negative hormone receptor expression in the initial breast cancer (HR, 1.6 [95% CI: 1.1, 2.6]; P = .02) were independently associated with an increased risk of future second breast cancer. Conclusion Background parenchymal enhancement at surveillance breast MRI was associated with future second breast cancer risk in women with a personal history of breast cancer. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Niell in this issue.

[The cancer epidemic : Global significance of cancer and the situation in oncological imaging]

A significant increase in the incidence of cancer is expected worldwide. In Europe, cancer will soon be the leading cause of death, ahead of cardiovascular disease. Concerted efforts at the scientific, medical, societal, and political levels are required to address this problem on a global scale. High-quality oncological imaging is of particular importance in this regard. Access to it has been shown to have a significant impact on quality of care and survival. Imaging is an essential component of screening and early detection. In clinical oncology, imaging is essential for multidisciplinary diagnostics and personalized therapy. Likewise, imaging is necessary in translational and clinical research. Imaging techniques are also themselves the subject of research and development and, associated with this, are also of great importance as an economic factor. This article aims to provide insights into the global problem of oncology and the contribution that oncological imaging can make to its management.

Computational Imaging to Compensate for Soft-Tissue Deformations in Image-Guided Breast Conserving Surgery

OBJECTIVE

During breast conserving surgery (BCS), magnetic resonance (MR) images aligned to accurately display intraoperative lesion locations can offer improved understanding of tumor extent and position relative to breast anatomy. Unfortunately, even under consistent supine conditions, soft tissue deformation compromises image-to-physical alignment and results in positional errors.

METHODS

A finite element inverse modeling technique has been developed to nonrigidly register preoperative supine MR imaging data to the surgical scene for improved localization accuracy during surgery. Registration is driven using sparse data compatible with acquisition during BCS, including corresponding surface fiducials, sparse chest wall contours, and the intra-fiducial skin surface. Deformation predictions were evaluated at surface fiducial locations and subsurface tissue features that were expertly identified and tracked. Among n = 7 different human subjects, an average of 22 ± 3 distributed subsurface targets were analyzed in each breast volume.

RESULTS

The average target registration error (TRE) decreased significantly when comparing rigid registration to this nonrigid approach (10.4 ± 2.3 mm vs 6.3 ± 1.4 mm TRE, respectively). When including a single subsurface feature as additional input data, the TRE significantly improved further (4.2 ± 1.0 mm TRE), and in a region of interest within 15 mm of a mock biopsy clip TRE was 3.9 ± 0.9 mm.

CONCLUSION

These results demonstrate accurate breast deformation estimates based on sparse-data-driven model predictions.

SIGNIFICANCE

The data suggest that a computational imaging approach can account for image-to-surgery shape changes to enhance surgical guidance during BCS.

Breast density is strongly associated with multiparametric magnetic resonance imaging biomarkers and pro-tumorigenic proteins in situ

BACKGROUND

High mammographic density is an independent risk factor for breast cancer by poorly understood molecular mechanisms. Women with dense breasts often undergo conventional magnetic resonance imaging (MRI) despite its limited specificity, which may be increased by diffusion-weighted imaging (DWI) with apparent diffusion coefficient (ADC) and contrast. How these modalities are affected by breast density per se and their association with the local microenvironment are undetermined.

METHODS

Healthy postmenopausal women attending mammography screen with extremely dense or entirely fatty breasts underwent multiparametric MRI for analyses of lean tissue fraction (LTF), ADC and perfusion dynamics. Microdialysis was used for extracellular proteomics in situ.

RESULTS

Significantly increased LTF and ADC and delayed perfusion were detected in dense breasts. In total, 270 proteins were quantified, whereof 124 related to inflammation, angiogenesis, and cellular growth were significantly upregulated in dense breasts. Most of these correlated significantly with LTF, ADC and the perfusion data.

CONCLUSIONS

ADC and perfusion characteristics depend on breast density, which should be considered during the implementation of thresholds for malignant lesions. Dense and nondense breasts are two essentially different biological entities, with a pro-tumorigenic microenvironment in dense breasts. Our data reveal several novel pathways that may be explored for breast cancer prevention strategies.

Ductal Carcinoma In Situ (DCIS) Diagnosed by MRI-Guided Biopsy among BRCA1/BRCA2 Mutation Carriers

Background

While BRCA1/BRCA2 pathogenic sequence variants (PSVs) clearly confer an increased risk for invasive breast cancer, the extent to which these mutant alleles increase DCIS risk is less clear.

Objective

To assess the rate of detection over a 5-year period, and MRI imaging features of pure noncalcified DCIS in a cohort of Israeli BRCA1/BRCA2 PSV carriers attending a high-risk clinic from 2015 to 2020.

Materials and Methods

All female BRCA1/BRCA2 PSV-carriers followed at the Meirav High-risk clinic from 2015 to 2020 were eligible if they underwent semiannual breast imaging (MRI/mammography) and MRI-guided biopsy-proven pure DCIS. Clinical data, pathology information, and imaging characteristics were retrieved from the computerized archiving system.

Results

18/121 (15.2%) participating BRCA1 PSV carriers and 8/81 (10.1%) BRCA2 PSV-carriers who underwent MRI-guided biopsy were diagnosed with DCIS. The median age of BRCA1 carriers and BRCA2 carriers was 49.8 years and 60.6 years, respectively (p = 0.55). Negative estrogen-receptor tumors were diagnosed in 13/18 (72%) BRCA1 and 2/8 (25%) BRCA2 PSV carriers (p < 0.05). Thirteen (13/18–72%) BRCA1 carriers had intermediate to high-grade or high-grade DCIS compared with 4/8 (50%) of BRCA2 carriers (p = 0.03). Over the 5-year study period, 29/1100 (2.6%) BRCA1/BRCA2 PSV carriers were diagnosed with DCIS seen on MRI only.

Conclusion

MRI-detected noncalcified DCIS is more frequent in BRCA1 PSV carriers compared with BRCA2 carriers, unlike the BRCA2 predominance in mammography-detected calcified DCIS. BRCA1-related DCIS is diagnosed earlier, more likely to be estrogen receptor-negative and of higher grade compared with BRCA2-related DCIS. Future prospective studies should validate these results and assess the actual impact they might have on clinical management of BRCA PSV carriers.

The Frequency and Causes of Not-Detected Breast Malignancy in Dynamic Contrast-Enhanced MRI

Breast MR is the most sensitive imaging modality, but there are cases of malignant tumors that are not detected in MR. This study evaluated the frequency and main causes of malignant breast lesions not detected in dynamic contrast-enhanced (DCE) MR. A total of 1707 cases of preoperative breast MR performed between 2020 and 2021 were included. Three radiologists individually reviewed the DCE MRs and found not-detected malignancy cases in the MRs. The final cases were decided through consensus. For the selected cases, images other than DCE MRIs, such as mammography, ultrasounds, diffusion-weighted MRs, and, if possible, contrast-enhanced chest CTs, were analyzed. In the final sample, 12 cases were not detected in DCE MR, and the frequency was 0.7% (12/1707). Six cases were not detected due to known non-enhancing histologic features. In four cases, tumors were located in the breast periphery and showed no enhancement in MR. In the remaining two cases, malignant lesions were not identified due to underlying marked levels of BPE. The frequency of not-detected malignancy in DCE MR is rare. Knowing the causes of each case and correlating it with other imaging modalities could be helpful in the diagnosis of breast malignancy in DCE MR.

From the patient to the population: Use of genomics for population screening

Genomic medicine is expanding from a focus on diagnosis at the patient level to prevention at the population level given the ongoing under-ascertainment of high-risk and actionable genetic conditions using current strategies, particularly hereditary breast and ovarian cancer (HBOC), Lynch Syndrome (LS) and familial hypercholesterolemia (FH). The availability of large-scale next-generation sequencing strategies and preventive options for these conditions makes it increasingly feasible to screen pre-symptomatic individuals through public health-based approaches, rather than restricting testing to high-risk groups. This raises anew, and with urgency, questions about the limits of screening as well as the moral authority and capacity to screen for genetic conditions at a population level. We aimed to answer some of these critical questions by using the WHO Wilson and Jungner criteria to guide a synthesis of current evidence on population genomic screening for HBOC, LS, and FH.

Assessment of breast lesions by the Kaiser score for differential diagnosis on MRI: the added value of ADC and machine learning modeling

OBJECTIVES

To evaluate the diagnostic performance of Kaiser score (KS) adjusted with the apparent diffusion coefficient (ADC) (KS+) and machine learning (ML) modeling.

METHODS

A dataset of 402 malignant and 257 benign lesions was identified. Two radiologists assigned the KS. If a lesion with KS > 4 had ADC > 1.4 × 10^-3 mm²/s, the KS was reduced by 4 to become KS+. In order to consider the full spectrum of ADC as a continuous variable, the KS and ADC values were used to train diagnostic models using 5 ML algorithms. The performance was evaluated using the ROC analysis, compared by the DeLong test. The sensitivity, specificity, and accuracy achieved using the threshold of KS > 4, KS+ > 4, and ADC ≤ 1.4 × 10^-3 mm²/s were obtained and compared by the McNemar test.

RESULTS

The ROC curves of KS, KS+, and all ML models had comparable AUC in the range of 0.883-0.921, significantly higher than that of ADC (0.837, p < 0.0001). The KS had sensitivity = 97.3% and specificity = 59.1%; and the KS+ had sensitivity = 95.5% with significantly improved specificity to 68.5% (p < 0.0001). However, when setting at the same sensitivity of 97.3%, KS+ could not improve specificity. In ML analysis, the logistic regression model had the best performance. At sensitivity = 97.3% and specificity = 65.3%, i.e., compared to KS, 16 false-positives may be avoided without affecting true cancer diagnosis (p = 0.0015).

CONCLUSION

Using dichotomized ADC to modify KS to KS+ can improve specificity, but at the price of lowered sensitivity. Machine learning algorithms may be applied to consider the ADC as a continuous variable to build more accurate diagnostic models.

KEY POINTS

• When using ADC to modify the Kaiser score to KS+, the diagnostic specificity according to the results of two independent readers was improved by 9.4-9.7%, at the price of slightly degraded sensitivity by 1.5-1.8%, and overall had improved accuracy by 2.6-2.9%. • When the KS and the continuous ADC values were combined to train models by machine learning algorithms, the diagnostic specificity achieved by the logistic regression model could be significantly improved from 59.1 to 65.3% (p = 0.0015), while maintaining at the high sensitivity of KS = 97.3%, and thus, the results demonstrated the potential of ML modeling to further evaluate the contribution of ADC. • When setting the sensitivity at the same levels, the modified KS+ and the original KS have comparable specificity; therefore, KS+ with consideration of ADC may not offer much practical help, and the original KS without ADC remains as an excellent robust diagnostic method.

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.

Improving breast cancer diagnostics with deep learning for MRI

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has a high sensitivity in detecting breast cancer but often leads to unnecessary biopsies and patient workup. We used a deep learning (DL) system to improve the overall accuracy of breast cancer diagnosis and personalize management of patients undergoing DCE-MRI. On the internal test set (n = 3936 exams), our system achieved an area under the receiver operating characteristic curve (AUROC) of 0.92 (95% CI: 0.92 to 0.93). In a retrospective reader study, there was no statistically significant difference (P = 0.19) between five board-certified breast radiologists and the DL system (mean ΔAUROC, +0.04 in favor of the DL system). Radiologists' performance improved when their predictions were averaged with DL's predictions [mean ΔAUPRC (area under the precision-recall curve), +0.07]. We demonstrated the generalizability of the DL system using multiple datasets from Poland and the United States. An additional reader study on a Polish dataset showed that the DL system was as robust to distribution shift as radiologists. In subgroup analysis, we observed consistent results across different cancer subtypes and patient demographics. Using decision curve analysis, we showed that the DL system can reduce unnecessary biopsies in the range of clinically relevant risk thresholds. This would lead to avoiding biopsies yielding benign results in up to 20% of all patients with BI-RADS category 4 lesions. Last, we performed an error analysis, investigating situations where DL predictions were mostly incorrect. This exploratory work creates a foundation for deployment and prospective analysis of DL-based models for breast MRI.

Diagnostic Approach to Developing Asymmetry in Opportunist Screening Mammography; Correlation of Ultrasound, Magnetic Resonance Imaging, and Histopathologic Findings with Developing Asymmetry: A Cross-sectional Study

Background: Developing asymmetries are uncommon mammographic findings with a chance of being associated with malignancy. Objectives: The current study aimed at correlating ultrasound, magnetic resonance imaging (MRI) findings, and histopathology of patients with developing focal asymmetry in opportunist screening mammograms setting, and presents a diagnostic approach to developing asymmetry. Methods: This was a cross-sectional study on a database of opportunist screening mammography at the Breast Clinic, Cancer Center, at Tehran University of Medical Sciences from January 2017 to December 2018. Mammogram screenings (n = 12,169) were evaluated for developing asymmetry. Findings of mammography, ultrasound, MRI findings, and histopathology of patients with developing asymmetry were collected and analyzed. Results: Fifty-four cases (0.44%) had developed asymmetry in screening mammograms. After excluding 18 patients with considering exclusion criteria, the data of 36 patients were analyzed. The summation artifact was the etiology of developing asymmetry in 11 (30.5%) patients. Ultrasound was performed in 28 patients, and 14 (38.8%) patients had no correlated findings. All 3 malignant cases had ultrasound correlates, and a significant association existed between sonography and the risk of malignancy in patients having developing asymmetry (P = 0.003). Three malignant cases of the study underwent MRI, 1 with segmental clumped non-mass enhancement, and 2 showed a mass with rim enhancement. A significant association was revealed between a family history of breast cancer (P = 0.04) and developing asymmetry. The positive predictive value of developing asymmetry for malignancy was 8.3%. Conclusions: Patients having developing asymmetry should be evaluated for malignancy, using supplementary techniques, such as additional mammographic views, ultrasound primarily, or MRI. A biopsy is required for indeterminate findings.

Assessment of MRI to estimate metastatic dissemination risk and prometastatic effects of chemotherapy

Metastatic dissemination in breast cancer is regulated by specialized intravasation sites called “tumor microenvironment of metastasis” (TMEM) doorways, composed of a tumor cell expressing the actin-regulatory protein Mena, a perivascular macrophage, and an endothelial cell, all in stable physical contact. High TMEM doorway number is associated with an increased risk of distant metastasis in human breast cancer and mouse models of breast carcinoma. Here, we developed a novel magnetic resonance imaging (MRI) methodology, called TMEM Activity-MRI, to detect TMEM-associated vascular openings that serve as the portal of entry for cancer cell intravasation and metastatic dissemination. We demonstrate that TMEM Activity-MRI correlates with primary tumor TMEM doorway counts in both breast cancer patients and mouse models, including MMTV-PyMT and patient-derived xenograft models. In addition, TMEM Activity-MRI is reduced in mouse models upon treatment with rebastinib, a specific and potent TMEM doorway inhibitor. TMEM Activity-MRI is an assay that specifically measures TMEM-associated vascular opening (TAVO) events in the tumor microenvironment, and as such, can be utilized in mechanistic studies investigating molecular pathways of cancer cell dissemination and metastasis. Finally, we demonstrate that TMEM Activity-MRI increases upon treatment with paclitaxel in mouse models, consistent with prior observations that chemotherapy enhances TMEM doorway assembly and activity in human breast cancer. Our findings suggest that TMEM Activity-MRI is a promising precision medicine tool for localized breast cancer that could be used as a non-invasive test to determine metastatic risk and serve as an intermediate pharmacodynamic biomarker to monitor therapeutic response to agents that block TMEM doorway-mediated dissemination.

Rational Approach to Finding Genes Encoding Molecular Biomarkers: Focus on Breast Cancer

Early detection of cancer facilitates treatment and improves patient survival. We hypothesized that molecular biomarkers of cancer could be rationally predicted based on even partial knowledge of transcriptional regulation, functional pathways and gene co-expression networks. To test our data mining approach, we focused on breast cancer, as one of the best-studied models of this disease. We were particularly interested to check whether such a ‘guilt by association’ approach would lead to pan-cancer markers generally known in the field or whether molecular subtype-specific ‘seed’ markers will yield subtype-specific extended sets of breast cancer markers. The key challenge of this investigation was to utilize a small number of well-characterized, largely intracellular, breast cancer-related proteins to uncover similarly regulated and functionally related genes and proteins with the view to predicting a much-expanded range of disease markers, especially that of extracellular molecular markers, potentially suitable for the early non-invasive detection of the disease. We selected 23 previously characterized proteins specific to three major molecular subtypes of breast cancer and analyzed their established transcription factor networks, their known metabolic and functional pathways and the existing experimentally derived protein co-expression data. Having started with largely intracellular and transmembrane marker ‘seeds’ we predicted the existence of as many as 150 novel biomarker genes to be associated with the selected three major molecular sub-types of breast cancer all coding for extracellularly targeted or secreted proteins and therefore being potentially most suitable for molecular diagnosis of the disease. Of the 150 such predicted protein markers, 114 were predicted to be linked through the combination of regulatory networks to basal breast cancer, 48 to luminal and 7 to Her2-positive breast cancer. The reported approach to mining molecular markers is not limited to breast cancer and therefore offers a widely applicable strategy of biomarker mining.

Evaluation of different imaging modalities for axillary lymph node staging in breast cancer patients to provide a personalized and optimized therapy algorithm

PURPOSE

The reliable detection of tumor-infiltrated axillary lymph nodes for breast cancer [BC] patients plays a decisive role in further therapy. We aimed to find out whether cross-sectional imaging techniques could improve sensitivity for pretherapeutic axillary staging in nodal-positive BC patients compared to conventional imaging such as mammography and sonography.

METHODS

Data for breast cancer patients with tumor-infiltrated axillary lymph nodes having received surgery between 2014 and 2020 were included in this study. All examinations (sonography, mammography, computed tomography [CT] and magnetic resonance imaging [MRI]) were interpreted by board-certified specialists in radiology. The sensitivity of different imaging modalities was calculated, and binary logistic regression analyses were performed to detect variables influencing the detection of positive lymph nodes.

RESULTS

All included 382 breast cancer patients had received conventional imaging, while 52.61% of the patients had received cross-sectional imaging. The sensitivity of the combination of all imaging modalities was 68.89%. The combination of MRI and CT showed 63.83% and the combination of sonography and mammography showed 36.11% sensitivity.

CONCLUSION

We could demonstrate that cross-sectional imaging can improve the sensitivity of the detection of tumor-infiltrated axillary lymph nodes in breast cancer patients. Only the safe detection of these lymph nodes at the time of diagnosis enables the evaluation of the response to neoadjuvant therapy, thereby allowing access to prognosis and improving new post-neoadjuvant therapies.

Contrast-Enhanced Mammography versus Breast Magnetic Resonance Imaging: A Systematic Review and Meta-Analysis

BACKGROUND

Contrast-enhanced mammography (CEM) and contrast-enhanced magnetic resonance imaging (CE-MRI) are commonly used in the screening of breast cancer. The present systematic review aimed to summarize, critically analyse, and meta-analyse the available evidence regarding the role of CE-MRI and CEM in the early detection, diagnosis, and preoperative assessment of breast cancer.

METHODS

The search was performed on PubMed, Google Scholar, and Web of Science on 28 July 2021 using the following terms "breast cancer", "preoperative staging", "contrast-enhanced mammography", "contrast-enhanced spectral mammography", "contrast enhanced digital mammography", "contrast-enhanced breast magnetic resonance imaging" "CEM", "CESM", "CEDM", and "CE-MRI". We selected only those papers comparing the clinical efficacy of CEM and CE-MRI. The study quality was assessed using the QUADAS-2 criteria. The pooled sensitivities and specificity of CEM and CE-MRI were computed using a random-effects model directly from the STATA "metaprop" command. The between-study statistical heterogeneity was tested (I2-statistics).

RESULTS

Nineteen studies were selected for this systematic review. Fifteen studies (1315 patients) were included in the metanalysis. Both CEM and CE-MRI detect breast lesions with a high sensitivity, without a significant difference in performance (97% and 96%, respectively).

CONCLUSIONS

Our findings confirm the potential of CEM as a supplemental screening imaging modality, even for intermediate-risk women, including females with dense breasts and a history of breast cancer.

Diagnostic Significance of 3D Automated Breast Volume Scanner in a Combination with Contrast-Enhanced Ultrasound for Breast Cancer

The incidence of cancer is increasing today, particularly lung and chest cancer. Employing novel methods to detect cancer in its earliest stages and discover painless, noninvasive treatments are urgently needed. The goal of the proposed study is to investigate the value of automated breast volume scanning (ABUS) in conjunction with contrast-enhanced ultrasonography (CEUS) in properly diagnosing breast cancer in its early stages and the effectiveness of neoadjuvant chemotherapy (NAC) in treating the disease. For the research study, information on 98 patients who had NAC and surgery in the breast surgery department of the Shaanxi Provincial Cancer Hospital has been gathered. All patients have received four cycles of NAC and underwent conventional ultrasound (HUSS), CEUS, ABUS, and pathological examination. At the same time, receiver operating characteristic (ROC) curve analysis, single factor, multiple linear regression, and other methods have also been used to analyze the diagnostic efficacy of breast cancer and NAC efficacy evaluation results. The study of this paper is totally based on the data collected from Shaanxi Provincial Cancer Hospital. The statistical and computational analyses are performed on the data collected for drawing inferences. When the findings are compared to the results of the pathological examination, HUSS has demonstrated a significant distinction between benign and malignant diagnoses with a statistical value of P < 0.05.ABUS combined with CEUS has shown no considerable differences in correlation study. Except for negative likelihood ratio, the diagnostic performance indexes of CEUS+ ABUS are substantially higher than HHUS with P < 0.05. ROC curve analysis is also performed which shows that CEUS and ABUS combination has higher precision in the analysis of breast cancer. ABUS pooled with CEUS shows great application value in the judgment of breast cancer as per the results obtained from the statistical analysis on data of 98 patients.

The value of noncontrast MRI in evaluating breast imaging reporting and data system category 0 lesions on digital mammograms

Background

Benign and malignant diagnosis of nonpalpable breast imaging reporting and data system (BI-RADS) category 0 lesions on digital mammograms (DMs) is very important. We compared the diagnostic performance of non-contrast-enhanced magnetic resonance imaging (MRI) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for them. We sought to evaluate BI-RADS category 0 lesions using 3 MRI sequences: short tau inversion recovery (STIR), STIR combined with high b value diffusion-weighted imaging (STIR-DWI), and DCE-MRI.

Methods

We retrospectively reviewed 114 breast DMs rated as nonpalpable BI-RADS category 0 lesions in 112 patients from January 2014 to June 2019. STIR, high b value DWI, and DCE-MRI were performed for all patients. Two breast radiologists read individual sequences (STIR, DWI, DCE-MRI) and pairs of sequences (STIR-DWI) to detect BI-RADS category 0 lesions in DMs. Receiver operating characteristic (ROC) curve analysis was used to assess diagnostic performance according to a best valuable comparator that combined MRI imaging, clinical, and pathological data.

Results

Among of 114 lesions (the median age of patients was 47 years; the median size of the lesion was 19 mm), 32 (48.5%) malignant lesions were missed by STIR, 9 (13.6%) malignant lesions were missed by STIR-DWI, and 3 (4.5%) malignant lesions were missed by DCE-MRI. The principal finding of our study was that STIR-DWI and DCE-MRI showed higher diagnostic accuracy than did STIR (P<0.01). STIR-DWI showed higher accuracy [area under the curve (AUC) =0.858; sensitivity =87.8%] for BI-RADS category 0 lesions in DMs than did STIR (AUC =0.754; sensitivity =51.5%), while the performance was comparable to that of DCE-MRI (AUC =0.884; sensitivity =95.5%).

Conclusions

Using pairs of sequences (STIR-DWI) is a non-contrast-enhanced MRI technique and had an equal diagnostic performance in distinguishing benign from malignant lesions among nonpalpable BI-RADS category 0 lesions to that of DCE-MRI. As a result, STIR-DWI as having the potential to improve the safety and efficacy in of breast cancer screening, especially in nonpalpable BI-RADS category 0 lesions at in DMs.

Semi-supervised vision transformer with adaptive token sampling for breast cancer classification

Various imaging techniques combined with machine learning (ML) models have been used to build computer-aided diagnosis (CAD) systems for breast cancer (BC) detection and classification. The rise of deep learning models in recent years, represented by convolutional neural network (CNN) models, has pushed the accuracy of ML-based CAD systems to a new level that is comparable to human experts. Existing studies have explored the usage of a wide spectrum of CNN models for BC detection, and supervised learning has been the mainstream. In this study, we propose a semi-supervised learning framework based on the Vision Transformer (ViT). The ViT is a model that has been validated to outperform CNN models on numerous classification benchmarks but its application in BC detection has been rare. The proposed method offers a custom semi-supervised learning procedure that unifies both supervised and consistency training to enhance the robustness of the model. In addition, the method uses an adaptive token sampling technique that can strategically sample the most significant tokens from the input image, leading to an effective performance gain. We validate our method on two datasets with ultrasound and histopathology images. Results demonstrate that our method can consistently outperform the CNN baselines for both learning tasks. The code repository of the project is available at https://github.com/FeiYee/Breast-area-TWO.

Signal-Intensity Informed Multi-Coil MRI Encoding Operator for Improved Physics-Guided Deep Learning Reconstruction of Dynamic Contrast-Enhanced MRI

Dynamic contrast enhanced (DCE) MRI acquires a series of images following the administration of a contrast agent, and plays an important clinical role in diagnosing various diseases. DCE MRI typically necessitates rapid imaging to provide sufficient spatio-temporal resolution and coverage. Conventional MRI acceleration techniques exhibit limited image quality at such high acceleration rates. Recently, deep learning (DL) methods have gained interest for improving highly-accelerated MRI. However, DCE MRI series show substantial variations in SNR and contrast across images. This hinders the quality and generalizability of DL methods, when applied across time frames. In this study, we propose signal intensity informed multi-coil MRI encoding operator for improved DL reconstruction of DCE MRI. The output of the corresponding inverse problem for this forward operator leads to more uniform contrast across time frames, since the proposed operator captures signal intensity variations across time frames while not altering the coil sensitivities. Our results in perfusion cardiac MRI show that high-quality images are reconstructed at very high acceleration rates, with substantial improvement over existing methods.

Breast Cancer—How Can Imaging Help?

Breast cancer is the most common malignant disease among women, causing death and suffering worldwide. It is known that, for the improvement of the survival rate and the psychological impact it has on patients, early detection is crucial. For this to happen, the imaging techniques should be used at their full potential. We selected and examined 44 articles that had as subject the use of a specific imaging method in breast cancer management (mammography, ultrasound, MRI, ultrasound-guided biopsy, PET-CT). After analyzing their data, we summarized and concluded which are the best ways to use each one of the mentioned techniques for a good outcome. We created a simplified algorithm with easy steps that can be followed by radiologists when facing this type of neoplasia.

Comparison of diagnostic values of two magnetic resonance imaging (MRI) protocols for diagnosis of breast lesions

BACKGROUND

Magnetic resonance imaging (MRI) has a pivotal role in diagnosing breast lesions. Here we aimed to compare the diagnostic values of Abbreviated and Full Breast MRI for breast lesions.

METHODS

This is a cross-sectional study performed in 2017-2021 on 80 women with breast lesions. Using the available MRI analysis software, the necessary sequences for the Abbreviated MRI were extracted from standard breast MRI protocol. First, a Full Breast MRI was examined by a radiologist giving Breast imaging-reporting and data system (BI-RADS). Then, from this Full Breast MRI, the necessary sequences for Abbreviated Breast MRI were prepared. The second expert radiologist read them in this field and BIRADS was reported. The data relating to each patient were recorded in the patient-specific profile and then the pathology results were followed for each patient.

RESULTS

Modified breast MRI had 84% sensitivity and 58.18% specificity, while full Breast MRI had 100% sensitivity and 38.18% specificity. Comparing the results of pathology (benign or malignant) for breast tumors and BIRADS reported by modified breast MRI indicated that these results were similar in 53 cases (66.3%) and different in 27 patients (33.8%). On the other hand, similar assessments for Full Breast MRI and pathology reports showed that the results were the same in 46 patients (57.5%) and different in 34 patients (42.5%).

CONCLUSION

Abbreviated breast MRI has lower sensitivity and higher specificity than full breast MRI.