Pilot study: A simple CAD-based tool to detect breast cancer on MRI of the breast

PURPOSE

This pilot-study aims to assess, whether quantitatively assessed enhancing breast tissue as a percentage of the entire breast volume can serve as an indicator of breast cancer at breast MRI and whether the contrast-agent employed affects diagnostic efficacy.

MATERIALS

This retrospective IRB-approved study, included 39 consecutive patients, that underwent two subsequent breast MRI exams for suspicious findings at conventional imaging with 0.1 mmol/kg gadobenic and gadoteric acid. Two independent readers, blinded to the histopathological outcome, assessed unenhanced and early post-contrast images using computer-assisted software (Brevis, Siemens Healthcare). Diagnostic performance was statistically determined for percentage of ipsilateral voxel volume enhancement and for percentage of contralateral enhancing voxel volume subtracted from ipsilateral enhancing voxel volume after crosstabulation with the dichotomized histological outcome (benign/malignant).

RESULTS

Ipsilateral enhancing voxel volume versus histopathological outcome resulted in an AUC of 0.707 and 0.687 for gadobenic acid, reader 1 and 2, respectively and in an AUC of 0.778 and 0.773 for gadoteric acid, reader 1 and 2, respectively. Accounting for background parenchymal enhancement by subtracting contralateral enhancing volume from ipsilateral enhancing voxel volume versus histolopathological outcome resulted in an AUC of 0.793 and 0.843 for gadobenic acid, reader 1 and 2, respectively and in an AUC of 0.692 and 0.662 for gadoteric acid, reader 1 and 2, respectively. Pairwise testing yielded no statistically significant difference both between readers and between contrast agents employed (p > 0.05).

CONCLUSION

Our proposed CAD algorithm, which quantitatively assesses enhancing breast tissue as a percentage of the entire breast volume, allows indicating the presence of breast cancer.

Assessment of Hypoxia in Breast Cancer: Emerging Functional MR Imaging and Spectroscopy Techniques and Clinical Applications

Breast cancer is one of the most prevalent forms of cancer affecting women worldwide. Hypoxia, a condition characterized by insufficient oxygen supply in tumor tissues, is closely associated with tumor aggressiveness, resistance to therapy, and poor clinical outcomes. Accurate assessment of tumor hypoxia can guide treatment decisions, predict therapy response, and contribute to the development of targeted therapeutic interventions. Over the years, functional magnetic resonance imaging (fMRI) and magnetic resonance spectroscopy (MRS) techniques have emerged as promising noninvasive imaging options for evaluating hypoxia in cancer. Such techniques include blood oxygen level-dependent (BOLD) MRI, oxygen-enhanced MRI (OE) MRI, chemical exchange saturation transfer (CEST) MRI, and proton MRS (1H-MRS). These may help overcome the limitations of the routinely used dynamic contrast-enhanced (DCE) MRI and diffusion-weighted imaging (DWI) techniques, contributing to better diagnosis and understanding of the biological features of breast cancer. This review aims to provide a comprehensive overview of the emerging functional MRI and MRS techniques for assessing hypoxia in breast cancer, along with their evolving clinical applications. The integration of these techniques in clinical practice holds promising implications for breast cancer management. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 1.

AI Applications to Breast MRI: Today and Tomorrow

In breast imaging, there is an unrelenting increase in the demand for breast imaging services, partly explained by continuous expanding imaging indications in breast diagnosis and treatment. As the human workforce providing these services is not growing at the same rate, the implementation of artificial intelligence (AI) in breast imaging has gained significant momentum to maximize workflow efficiency and increase productivity while concurrently improving diagnostic accuracy and patient outcomes. Thus far, the implementation of AI in breast imaging is at the most advanced stage with mammography and digital breast tomosynthesis techniques, followed by ultrasound, whereas the implementation of AI in breast magnetic resonance imaging (MRI) is not moving along as rapidly due to the complexity of MRI examinations and fewer available dataset. Nevertheless, there is persisting interest in AI-enhanced breast MRI applications, even as the use of and indications of breast MRI continue to expand. This review presents an overview of the basic concepts of AI imaging analysis and subsequently reviews the use cases for AI-enhanced MRI interpretation, that is, breast MRI triaging and lesion detection, lesion classification, prediction of treatment response, risk assessment, and image quality. Finally, it provides an outlook on the barriers and facilitators for the adoption of AI in breast MRI. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 6.

Contrast-Enhanced Mammography for Women with Palpable Breast Abnormalities

RATIONALE AND OBJECTIVES

To examine the role of contrast-enhanced mammography (CEM) in the work-up of palpable breast abnormalities.

MATERIALS AND METHODS

In this single-center combination prospective-retrospective study, women with palpable breast abnormalities underwent CEM evaluation prospectively, comprising the acquisition of low energy (LE) images and recombined images (RI) which depict enhancement, followed by targeted ultrasound (US). Two independent readers retrospectively reviewed the imaging and assigned BI-RADS assessment based on LE alone, LE plus US, RI with LE plus US (CEM plus US), and RI alone. Pathology results or 1-year follow-up imaging served as the reference standard.

RESULTS

237 women with 262 palpable abnormalities were included (mean age, 51 years). Of the 262 palpable abnormalities, 116/262 (44%) had no imaging correlate and 242/262 (92%) were benign. RI alone had better specificity compared to LE plus US (Reader 1, 94% versus 89% (p = 0.009); Reader 2, 93% versus 88% (p = 0.03)), better positive predictive value (Reader 1, 52% versus 42% (p = 0.04); Reader 2, 53% versus 42% (p = 0.04)), and better accuracy (Reader 1, 93% versus 89% (p = 0.05); Reader 2, 93% versus 90% (p = 0.06)). CEM plus US was not significantly different in performance metrics versus LE plus US.

CONCLUSION

RI had better specificity compared to LE in combination with US. There was no difference in performance between CEM plus US and LE plus US, likely reflecting the weight US carries in radiologist decision-making. However, the results indicate that the absence of enhancement on RI in the setting of palpable lesions may help avoid benign biopsies.

BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study

Background The performance of publicly available large language models (LLMs) remains unclear for complex clinical tasks. Purpose To evaluate the agreement between human readers and LLMs for Breast Imaging Reporting and Data System (BI-RADS) categories assigned based on breast imaging reports written in three languages and to assess the impact of discordant category assignments on clinical management. Materials and Methods This retrospective study included reports for women who underwent MRI, mammography, and/or US for breast cancer screening or diagnostic purposes at three referral centers. Reports with findings categorized as BI-RADS 1-5 and written in Italian, English, or Dutch were collected between January 2000 and October 2023. Board-certified breast radiologists and the LLMs GPT-3.5 and GPT-4 (OpenAI) and Bard, now called Gemini (Google), assigned BI-RADS categories using only the findings described by the original radiologists. Agreement between human readers and LLMs for BI-RADS categories was assessed using the Gwet agreement coefficient (AC1 value). Frequencies were calculated for changes in BI-RADS category assignments that would affect clinical management (ie, BI-RADS 0 vs BI-RADS 1 or 2 vs BI-RADS 3 vs BI-RADS 4 or 5) and compared using the McNemar test. Results Across 2400 reports, agreement between the original and reviewing radiologists was almost perfect (AC1 = 0.91), while agreement between the original radiologists and GPT-4, GPT-3.5, and Bard was moderate (AC1 = 0.52, 0.48, and 0.42, respectively). Across human readers and LLMs, differences were observed in the frequency of BI-RADS category upgrades or downgrades that would result in changed clinical management (118 of 2400 [4.9%] for human readers, 611 of 2400 [25.5%] for Bard, 573 of 2400 [23.9%] for GPT-3.5, and 435 of 2400 [18.1%] for GPT-4; P < .001) and that would negatively impact clinical management (37 of 2400 [1.5%] for human readers, 435 of 2400 [18.1%] for Bard, 344 of 2400 [14.3%] for GPT-3.5, and 255 of 2400 [10.6%] for GPT-4; P < .001). Conclusion LLMs achieved moderate agreement with human reader-assigned BI-RADS categories across reports written in three languages but also yielded a high percentage of discordant BI-RADS categories that would negatively impact clinical management. © RSNA, 2024 Supplemental material is available for this article.

Identification of impactful imaging biomarker: Clinical applications for breast and prostate carcinoma

BACKGROUND

 Imaging biomarkers are quantitative parameters from imaging modalities, which are collected noninvasively, allow conclusions about physiological and pathophysiological processes, and may consist of single (monoparametric) or multiple parameters (bi- or multiparametric).

METHOD

 This review aims to present the state of the art for the quantification of multimodal and multiparametric imaging biomarkers. Here, the use of biomarkers using artificial intelligence will be addressed and the clinical application of imaging biomarkers in breast and prostate cancers will be explained. For the preparation of the review article, an extensive literature search was performed based on Pubmed, Web of Science and Google Scholar. The results were evaluated and discussed for consistency and generality.

RESULTS AND CONCLUSION

 Different imaging biomarkers (multiparametric) are quantified based on the use of complementary imaging modalities (multimodal) from radiology, nuclear medicine, or hybrid imaging. From these techniques, parameters are determined at the morphological (e. g., size), functional (e. g., vascularization or diffusion), metabolic (e. g., glucose metabolism), or molecular (e. g., expression of prostate specific membrane antigen, PSMA) level. The integration and weighting of imaging biomarkers are increasingly being performed with artificial intelligence, using machine learning algorithms. In this way, the clinical application of imaging biomarkers is increasing, as illustrated by the diagnosis of breast and prostate cancers.

KEY POINTS

· Imaging biomarkers are quantitative parameters to detect physiological and pathophysiological processes.. · Imaging biomarkers from multimodality and multiparametric imaging are integrated using artificial intelligence algorithms.. · Quantitative imaging parameters are a fundamental component of diagnostics for all tumor entities, such as for mammary and prostate carcinomas..

CITATION FORMAT

· Bäuerle T, Dietzel M, Pinker K et al. Identification of impactful imaging biomarker: Clinical applications for breast and prostate carcinoma. Fortschr Röntgenstr 2024; 196: 354 - 362.

Comparison of Axillary Lymph Nodes on Breast MRI Before and After COVID-19 Booster Vaccination

RATIONALE AND OBJECTIVES

Vaccine-related lymphadenopathy is a frequent finding following initial coronavirus disease 2019 (COVID-19) vaccination, but the frequency after COVID-19 booster vaccination is still unknown. In this study we compare axillary lymph node morphology on breast MRI before and after COVID-19 booster vaccination.

MATERIALS AND METHODS

This retrospective, single-center, IRB-approved study included patients who underwent breast MRI between October 2021 and December 2021 after the COVID-19 booster vaccination. The axillary lymph node with the greatest cortical thickness ipsilateral to the side of vaccination was measured on MRI after booster vaccination and before initial COVID-19 vaccination. Comparisons were made between patients with and without increase in cortical thickness of ≥ 0.2 cm. Continuous covariates were compared using Wilcoxon rank-sum test and categorical covariates were compared using Fisher's exact test. Multiple comparison adjustment was made using the Benjamini-Hochberg procedure.

RESULTS

All 128 patients were included. Twenty-four of 128 (19%) displayed an increase in lymph node cortical thickness of ≥ 0.2 cm. Patients who received the booster more recently were more likely to present cortical thickening, with a median of 9 days (IQR 5, 20) vs. 36 days (IQR 18, 59) (p < 0.001). Age (p = 0.5) and type of vaccine (p = 0.7) were not associated with thickening. No ipsilateral breast cancer or malignant lymphadenopathy were diagnosed on follow-up.

CONCLUSION

Axillary lymphadenopathy on breast MRI following COVID-19 booster vaccination is a frequent finding, especially in the first 3 weeks after vaccination. Additional evaluation or follow-up may be omitted in patients with low concern for malignancy.

Artificial Intelligence-Enhanced Breast MRI: Applications in Breast Cancer Primary Treatment Response Assessment and Prediction

ABSTRACT

Primary systemic therapy (PST) is the treatment of choice in patients with locally advanced breast cancer and is nowadays also often used in patients with early-stage breast cancer. Although imaging remains pivotal to assess response to PST accurately, the use of imaging to predict response to PST has the potential to not only better prognostication but also allow the de-escalation or omission of potentially toxic treatment with undesirable adverse effects, the accelerated implementation of new targeted therapies, and the mitigation of surgical delays in selected patients. In response to the limited ability of radiologists to predict response to PST via qualitative, subjective assessments of tumors on magnetic resonance imaging (MRI), artificial intelligence-enhanced MRI with classical machine learning, and in more recent times, deep learning, have been used with promising results to predict response, both before the start of PST and in the early stages of treatment. This review provides an overview of the current applications of artificial intelligence to MRI in assessing and predicting response to PST, and discusses the challenges and limitations of their clinical implementation.

A Survey of Publicly Available MRI Datasets for Potential Use in Artificial Intelligence Research

Artificial intelligence (AI) has the potential to bring transformative improvements to the field of radiology; yet, there are barriers to widespread clinical adoption. One of the most important barriers has been access to large, well-annotated, widely representative medical image datasets, which can be used to accurately train AI programs. Creating such datasets requires time and expertise and runs into constraints around data security and interoperability, patient privacy, and appropriate data use. Recognizing these challenges, several institutions have started curating and providing publicly available, high-quality datasets that can be accessed by researchers to advance AI models. The purpose of this work was to review the publicly available MRI datasets that can be used for AI research in radiology. Despite being an emerging field, a simple internet search for open MRI datasets presents an overwhelming number of results. Therefore, we decided to create a survey of the major publicly accessible MRI datasets in different subfields of radiology (brain, body, and musculoskeletal), and list the most important features of value to the AI researcher. To complete this review, we searched for publicly available MRI datasets and assessed them based on several parameters (number of subjects, demographics, area of interest, technical features, and annotations). We reviewed 110 datasets across sub-fields with 1,686,245 subjects in 12 different areas of interest ranging from spine to cardiac. This review is meant to serve as a reference for researchers to help spur advancements in the field of AI for radiology. LEVEL OF EVIDENCE: Level 4 TECHNICAL EFFICACY: Stage 6.

[WITHDRAWN] Predicting breast cancer with AI for individual risk-adjusted MRI screening and early detection

This paper has been withdrawn by Lukas Hirsch. Major revisions and rewriting in progress.

Non-Contrast-Enhanced Multiparametric MRI of the Hypoxic Tumor Microenvironment Allows Molecular Subtyping of Breast Cancer: A Pilot Study

Tumor neoangiogenesis is an important hallmark of cancer progression, triggered by alternating selective pressures from the hypoxic tumor microenvironment. Non-invasive, non-contrast-enhanced multiparametric MRI combining blood-oxygen-level-dependent (BOLD) MRI, which depicts blood oxygen saturation, and intravoxel-incoherent-motion (IVIM) MRI, which captures intravascular and extravascular diffusion, can provide insights into tumor oxygenation and neovascularization simultaneously. Our objective was to identify imaging markers that can predict hypoxia-induced angiogenesis and to validate our findings using multiplexed immunohistochemical analyses. We present an in vivo study involving 36 female athymic nude mice inoculated with luminal A, Her2+, and triple-negative breast cancer cells. We used a high-field 9.4-tesla MRI system for imaging and subsequently analyzed the tumors using multiplex immunohistochemistry for CD-31, PDGFR-β, and Hif1-α. We found that the hyperoxic-BOLD-MRI-derived parameter ΔR2* discriminated luminal A from Her2+ and triple-negative breast cancers, while the IVIM-derived parameter fIVIM discriminated luminal A and Her2+ from triple-negative breast cancers. A comprehensive analysis using principal-component analysis of both multiparametric MRI- and mpIHC-derived data highlighted the differences between triple-negative and luminal A breast cancers. We conclude that multiparametric MRI combining hyperoxic BOLD MRI and IVIM MRI, without the need for contrast agents, offers promising non-invasive markers for evaluating hypoxia-induced angiogenesis.

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.

Breast MRI in patients with implantable loop recorder: initial experience

OBJECTIVES

To investigate the feasibility of breast MRI exams and guided biopsies in patients with an implantable loop recorder (ILR) as well as the impact ILRs may have on image interpretation.

MATERIALS AND METHODS

This retrospective study examined breast MRIs of patients with ILR, from April 2008 to September 2022. Radiological reports and electronic medical records were reviewed for demographic characteristics, safety concerns, and imaging findings. MR images were analyzed and compared statistically for artifact quantification on the various pulse sequences.

RESULTS

Overall, 40/82,778 (0.049%) MRIs during the study period included ILR. All MRIs were completed without early termination. No patient-related or device-related adverse events occurred. ILRs were most commonly located in the left lower-inner quadrant (64.6%). The main artifact was a signal intensity (SI) void in a dipole formation in the ILR bed with or without areas of peripheral high SI. Artifacts appeared greatest in the cranio-caudal axis (p < 0.001), followed by the anterior-posterior axis (p < 0.001), and then the right-left axis. High peripheral rim-like SI artifacts appeared on the post-contrast and subtracted T1-weighted images, mimicking suspicious enhancement. Artifacts were most prominent on diffusion-weighted (p < 0.001), followed by T2-weighted and T1-weighted images. In eight patients, suspicious findings were found on MRI, resulting in four additional malignant lesions. Of six patients with left breast cancer, the tumor was completely visible in five cases and partially obscured in one.

CONCLUSION

Breast MRI is feasible and safe among patients with ILR and may provide a significant diagnostic value, albeit with localized, characteristic artifacts.

CLINICAL RELEVANCE STATEMENT

Indicated breast MRI exams and guided biopsies can be safely performed in patients with implantable loop recorder. Nevertheless, radiologists should be aware of associated limitations including limited assessment of the inner left breast and pseudo-enhancement artifacts.

KEY POINTS

• Breast MRI in patients with an implantable loop recorder is an infrequent, feasible, and safe procedure. • Despite limited breast visualization of the implantable loop recorder bed and characteristic artifacts, MRI depicted additional lesions in 8/40 (20%) of cases, half of which were malignant. • Breast MRI in patients with an implantable loop recorder should be performed when indicated, taking into consideration typical associated artifacts.

Update on DWI for Breast Cancer Diagnosis and Treatment Monitoring

DWI is a noncontrast MRI technique that measures the diffusion of water molecules within biologic tissue. DWI is increasingly incorporated into routine breast MRI examinations. Currently, the main applications of DWI are breast cancer detection and characterization, prognostication, and prediction of treatment response to neoadjuvant chemotherapy. In addition, DWI is promising as a noncontrast MRI alternative for breast cancer screening. Problems with suboptimal resolution and image quality have restricted the mainstream use of DWI for breast imaging, but these shortcomings are being addressed through several technologic advancements. In this review, we present an up-to-date assessment of the use of DWI for breast cancer imaging, including a summary of the clinical literature and recommendations for future use.

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.

Current Status of Cancer Genomics and Imaging Phenotypes: What Radiologists Need to Know

Ongoing discoveries in cancer genomics and epigenomics have revolutionized clinical oncology and precision health care. This knowledge provides unprecedented insights into tumor biology and heterogeneity within a single tumor, among primary and metastatic lesions, and among patients with the same histologic type of cancer. Large-scale genomic sequencing studies also sparked the development of new tumor classifications, biomarkers, and targeted therapies. Because of the central role of imaging in cancer diagnosis and therapy, radiologists need to be familiar with the basic concepts of genomics, which are now becoming the new norm in oncologic clinical practice. By incorporating these concepts into clinical practice, radiologists can make their imaging interpretations more meaningful and specific, facilitate multidisciplinary clinical dialogue and interventions, and provide better patient-centric care. This review article highlights basic concepts of genomics and epigenomics, reviews the most common genetic alterations in cancer, and discusses the implications of these concepts on imaging by organ system in a case-based manner. This information will help stimulate new innovations in imaging research, accelerate the development and validation of new imaging biomarkers, and motivate efforts to bring new molecular and functional imaging methods to clinical radiology. Keywords: Oncology, Cancer Genomics, Epignomics, Radiogenomics, Imaging Markers Supplemental material is available for this article. © RSNA, 2023.

Simultaneous 18F-FDG PET/MRI Radiomics and Machine Learning Analysis of the Primary Breast Tumor for the Preoperative Prediction of Axillary Lymph Node Status in Breast Cancer

In this prospective study, 117 female patients (mean age = 53 years) with 127 histologically proven breast cancer lesions (lymph node (LN) positive = 85, LN negative = 42) underwent simultaneous 18F-FDG PET/MRI of the breast. Quantitative parameters were calculated from dynamic contrast-enhanced (DCE) imaging (tumor Mean Transit Time, Volume Distribution, Plasma Flow), diffusion-weighted imaging (DWI) (tumor ADCmean), and PET (tumor SUVmax, mean and minimum, SUVmean of ipsilateral breast parenchyma). Manual whole-lesion segmentation was also performed on DCE, T2-weighted, DWI, and PET images, and radiomic features were extracted. The dataset was divided into a training (70%) and a test set (30%). Multi-step feature selection was performed, and a support vector machine classifier was trained and tested for predicting axillary LN status. 13 radiomic features from DCE, DWI, T2-weighted, and PET images were selected for model building. The classifier obtained an accuracy of 79.8 (AUC = 0.798) in the training set and 78.6% (AUC = 0.839), with sensitivity and specificity of 67.9% and 100%, respectively, in the test set. A machine learning-based radiomics model comprising 18F-FDG PET/MRI radiomic features extracted from the primary breast cancer lesions allows high accuracy in non-invasive identification of axillary LN metastasis.

High-Temporal/High-Spatial Resolution Breast Magnetic Resonance Imaging Improves Diagnostic Accuracy Compared With Standard Breast Magnetic Resonance Imaging in Patients With High Background Parenchymal Enhancement

PURPOSE

To compare breast magnetic resonance imaging (MRI) diagnostic performance using a standard high-spatial resolution protocol versus a simultaneous high-temporal/high-spatial resolution (HTHS) protocol in women with high levels of background parenchymal enhancement (BPE).

MATERIALS AND METHODS

We conducted a retrospective study of contrast-enhanced breast MRIs performed at our institution before and after the introduction of the HTHS protocol. We compared diagnostic performance of the HTHS and standard protocol by comparing cancer detection rate (CDR) and positive predictive value of biopsy (PPV3) among women with high BPE (ie, marked or moderate).

RESULTS

Among women with high BPE, the HTHS protocol demonstrated increased CDR (23.6 per 1,000 patients v 7.9 per 1,000 patients; P = 0. 013) and increased PPV3 (16.0% v 6.3%; P = .021) compared with the standard protocol. This corresponded to a 9.8% (95% CI, 1.29 to 18.3) decrease in the proportion of unnecessary biopsies among high-BPE patients and an additional cancer yield of 15.7 per 1,000 patients (95% CI, 1.3 to 18.3).

CONCLUSION

Among women with high BPE, HTHS MRI improved diagnostic performance, leading to an additional cancer yield of 15.7 cancers per 1,000 women and concomitantly decreasing unnecessary biopsies by 9.8%. A multisite prospective trial is warranted to confirm these findings and to pave the way for more widespread clinical implementation.

A Review of the Estimation of Sensitivity and Specificity in the Context of Time-Dependent Outcomes

Time is an essential element in the field of survival analysis. Time to an event is essential in adjudicating diagnostic utility and determining the effectiveness of treatment. However, time-to-event outcomes-in a sense-are complicated to deal with, since they involve both a binary component, which is the outcome itself (death or recurrence) and a continuous component, which is the time for the occurrence of the outcome. In such scenarios, simpler metrics such as sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve are insufficient to establish the utility of a diagnostic marker. Given the above constraint, this review discusses established ways in which sensitivity and specificity can be determined and are therefore sufficient in establishing utility in the context of time-dependent outcomes. This review also discusses how studies investigating the sensitivity and specificity of a diagnostic marker in the context of time-dependent outcomes can be improved through the use of existing user-friendly statistical software. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 3.

From bedside to portable and wearable: development of a conformable ultrasound patch for deep breast tissue imaging

A breakthrough study from Du et al. has developed a wearable, ultrasound imaging patch for standardized and reproducible breast tissue imaging. The technology utilizes a honeycomb patch design to facilitate guided movement of the ultrasound array, enabling comprehensive, multiangle breast imaging. The system was validated in vitro and in vivo with a single human subject and has the potential for early-stage breast cancer detection. This study addressed the current limitations of wearable ultrasound technologies, including imaging over large, curvilinear organs and integration of superior piezoelectric materials for high-performance ultrasound arrays. The transition of ultrasound from the bedside to portable and wearable devices will pave the way for integration with big data collection, such as artificial intelligence (AI)-based diagnosis and personalized ultrasonographic profile generation, for rapid and objective measurements. This advancement is especially important in the context of breast cancer, where early diagnosis and assessment of medical therapy responses are paramount to patient care.

AI-Enhanced PET and MR Imaging for Patients with Breast Cancer

New challenges are currently faced by clinical and surgical oncologists in the management of patients with breast cancer, mainly related to the need for molecular and prognostic data. Recent technological advances in diagnostic imaging and informatics have led to the introduction of functional imaging modalities, such as hybrid PET/MR imaging, and artificial intelligence (AI) software, aimed at the extraction of quantitative radiomics data, which may reflect tumor biology and behavior. In this article, the most recent applications of radiomics and AI to PET/MR imaging are described to address the new needs of clinical and surgical oncology.

Automated Triage of Screening Breast MRI Examinations in High-Risk Women Using an Ensemble Deep Learning Model

OBJECTIVES

The aim of the study is to develop and evaluate the performance of a deep learning (DL) model to triage breast magnetic resonance imaging (MRI) findings in high-risk patients without missing any cancers.

MATERIALS AND METHODS

In this retrospective study, 16,535 consecutive contrast-enhanced MRIs performed in 8354 women from January 2013 to January 2019 were collected. From 3 New York imaging sites, 14,768 MRIs were used for the training and validation data set, and 80 randomly selected MRIs were used for a reader study test data set. From 3 New Jersey imaging sites, 1687 MRIs (1441 screening MRIs and 246 MRIs performed in recently diagnosed breast cancer patients) were used for an external validation data set. The DL model was trained to classify maximum intensity projection images as "extremely low suspicion" or "possibly suspicious." Deep learning model evaluation (workload reduction, sensitivity, specificity) was performed on the external validation data set, using a histopathology reference standard. A reader study was performed to compare DL model performance to fellowship-trained breast imaging radiologists.

RESULTS

In the external validation data set, the DL model triaged 159/1441 of screening MRIs as "extremely low suspicion" without missing a single cancer, yielding a workload reduction of 11%, a specificity of 11.5%, and a sensitivity of 100%. The model correctly triaged 246/246 (100% sensitivity) of MRIs in recently diagnosed patients as "possibly suspicious." In the reader study, 2 readers classified MRIs with a specificity of 93.62% and 91.49%, respectively, and missed 0 and 1 cancer, respectively. On the other hand, the DL model classified MRIs with a specificity of 19.15% and missed 0 cancers, highlighting its potential use not as an independent reader but as a triage tool.

CONCLUSIONS

Our automated DL model triages a subset of screening breast MRIs as "extremely low suspicion" without misclassifying any cancer cases. This tool may be used to reduce workload in standalone mode, to shunt low suspicion cases to designated radiologists or to the end of the workday, or to serve as base model for other downstream AI tools.

Hyperoxic BOLD-MRI-Based Characterization of Breast Cancer Molecular Subtypes Is Independent of the Supplied Amount of Oxygen: A Preclinical Study

Hyperoxic BOLD-MRI targeting tumor hypoxia may provide imaging biomarkers that represent breast cancer molecular subtypes without the use of injected contrast agents. However, the diagnostic performance of hyperoxic BOLD-MRI using different levels of oxygen remains unclear. We hypothesized that molecular subtype characterization with hyperoxic BOLD-MRI is feasible independently of the amount of oxygen. Twenty-three nude mice that were inoculated into the flank with luminal A (n = 9), Her2+ (n = 5), and triple-negative (n = 9) human breast cancer cells were imaged using a 9.4 T Bruker BioSpin system. During BOLD-MRI, anesthesia was supplemented with four different levels of oxygen (normoxic: 21%; hyperoxic: 41%, 71%, 100%). The change in the spin-spin relaxation rate in relation to the normoxic state, ΔR2*, dependent on the amount of erythrocyte-bound oxygen, was calculated using in-house MATLAB code. ΔR2* was significantly different between luminal A and Her2+ as well as between luminal A and triple-negative breast cancer, reflective of the less aggressive luminal A breast cancer's ability to better deliver oxygen-rich hemoglobin to its tissue. Differences in ΔR2* between subtypes were independent of the amount of oxygen, with robust distinction already achieved with 41% oxygen. In conclusion, hyperoxic BOLD-MRI may be used as a biomarker for luminal A breast cancer identification without the use of exogenous contrast agents.

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

OBJECTIVES

To report mastectomy and reoperation rates in women who had breast MRI for screening (S-MRI subgroup) or diagnostic (D-MRI subgroup) purposes, using multivariable analysis for investigating the role of MRI referral/nonreferral and other covariates in driving surgical outcomes.

METHODS

The MIPA observational study enrolled women aged 18-80 years with newly diagnosed breast cancer destined to have surgery as the primary treatment, in 27 centres worldwide. Mastectomy and reoperation rates were compared using non-parametric tests and multivariable analysis.

RESULTS

A total of 5828 patients entered analysis, 2763 (47.4%) did not undergo MRI (noMRI subgroup) and 3065 underwent MRI (52.6%); of the latter, 2441/3065 (79.7%) underwent MRI with preoperative intent (P-MRI subgroup), 510/3065 (16.6%) D-MRI, and 114/3065 S-MRI (3.7%). The reoperation rate was 10.5% for S-MRI, 8.2% for D-MRI, and 8.5% for P-MRI, while it was 11.7% for noMRI (p ≤ 0.023 for comparisons with D-MRI and P-MRI). The overall mastectomy rate (first-line mastectomy plus conversions from conserving surgery to mastectomy) was 39.5% for S-MRI, 36.2% for P-MRI, 24.1% for D-MRI, and 18.0% for noMRI. At multivariable analysis, using noMRI as reference, the odds ratios for overall mastectomy were 2.4 (p < 0.001) for S-MRI, 1.0 (p = 0.957) for D-MRI, and 1.9 (p < 0.001) for P-MRI.

CONCLUSIONS

Patients from the D-MRI subgroup had the lowest overall mastectomy rate (24.1%) among MRI subgroups and the lowest reoperation rate (8.2%) together with P-MRI (8.5%). This analysis offers an insight into how the initial indication for MRI affects the subsequent surgical treatment of breast cancer.

KEY POINTS

• Of 3065 breast MRI examinations, 79.7% were performed with preoperative intent (P-MRI), 16.6% were diagnostic (D-MRI), and 3.7% were screening (S-MRI) examinations. • The D-MRI subgroup had the lowest mastectomy rate (24.1%) among MRI subgroups and the lowest reoperation rate (8.2%) together with P-MRI (8.5%). • The S-MRI subgroup had the highest mastectomy rate (39.5%) which aligns with higher-than-average risk in this subgroup, with a reoperation rate (10.5%) not significantly different to that of all other subgroups.

Introduction of a breast apparent diffusion coefficient category system (ADC-B) derived from a large multicenter MRI database

OBJECTIVES

To develop an intuitive and generally applicable system for the reporting, assessment, and documentation of ADC to complement standard BI-RADS criteria.

METHODS

This was a multicentric, retrospective analysis of 11 independently conducted institutional review board-approved studies from seven institutions performed between 2007 and 2019. Breast Apparent Diffusion coefficient (ADC-B) categories comprised ADC-B0 (ADC non-diagnostic), ADC-B1 (no enhancing lesion), and ADC-B2-5. The latter was defined by plotting ADC versus cumulative malignancy rates. Statistics comprised ANOVA with post hoc testing and ROC analysis. p values ≤ 0.05 were considered statistically significant.

RESULTS

A total of 1625 patients (age: 55.9 years (± 13.8)) with 1736 pathologically verified breast lesions were included. The mean ADC (× 10-3 mm2/s) differed significantly between benign (1.45, SD .40) and malignant lesions (.95, SD .39), and between invasive (.92, SD .22) and in situ carcinomas (1.18, SD .30) (p < .001). The following ADC-B categories were identified: ADC-B0-ADC cannot be assessed; ADC-B1-no contrast-enhancing lesion; ADC-B2-ADC ≥ 1.9 (cumulative malignancy rate < 0.1%); ADC-B3-ADC 1.5 to < 1.9 (0.1-1.7%); ADC-B4-ADC 1.0 to < 1.5 (10-24.5%); and ADC-B5-ADC < 1.0 (> 24.5%). At the latter threshold, a positive predictive value of 95.8% (95% CI 0.94-0.97) for invasive versus non-invasive breast carcinomas was reached.

CONCLUSIONS

The breast apparent diffusion coefficient system (ADC-B) provides a simple and widely applicable categorization scheme for assessment, documentation, and reporting of apparent diffusion coefficient values in contrast-enhancing breast lesions on MRI.

CLINICAL RELEVANCE STATEMENT

The ADC-B system, based on diverse MRI examinations, is clinically relevant for stratifying breast cancer risk via apparent diffusion coefficient measurements, and complements BI-RADS for improved clinical decision-making and patient outcomes.

KEY POINTS

• The breast apparent diffusion coefficient category system (ADC-B) is a simple tool for the assessment, documentation, and reporting of ADC values in contrast-enhancing breast lesions on MRI. • The categories comprise ADC-B0 for non-diagnostic examinations, ADC-B1 for examinations without an enhancing lesion, and ADC-B2-5 for enhancing lesions with an increasing malignancy rate. • The breast apparent diffusion coefficient category system may be used to complement BI-RADS in clinical decision-making.

European Society of Breast Imaging (EUSOBI) guidelines on the management of axillary lymphadenopathy after COVID-19 vaccination: 2023 revision

Axillary lymphadenopathy is a common side effect of COVID-19 vaccination, leading to increased imaging-detected asymptomatic and symptomatic unilateral axillary lymphadenopathy. This has threatened to negatively impact the workflow of breast imaging services, leading to the release of ten recommendations by the European Society of Breast Imaging (EUSOBI) in August 2021. Considering the rapidly changing scenario and data scarcity, these initial recommendations kept a highly conservative approach. As of 2023, according to newly acquired evidence, EUSOBI proposes the following updates, in order to reduce unnecessary examinations and avoid delaying necessary examinations. First, recommendation n. 3 has been revised to state that breast examinations should not be delayed or rescheduled because of COVID-19 vaccination, as evidence from the first pandemic waves highlights how delayed or missed screening tests have a negative effect on breast cancer morbidity and mortality, and that there is a near-zero risk of subsequent malignant findings in asymptomatic patients who have unilateral lymphadenopathy and no suspicious breast findings. Second, recommendation n. 7 has been revised to simplify follow-up strategies: in patients without breast cancer history and no imaging findings suspicious for cancer, symptomatic and asymptomatic imaging-detected unilateral lymphadenopathy on the same side of recent COVID-19 vaccination (within 12 weeks) should be classified as a benign finding (BI-RADS 2) and no further work-up should be pursued. All other recommendations issued by EUSOBI in 2021 remain valid.

The Lucerne Toolbox 2 to optimise axillary management for early breast cancer: a multidisciplinary expert consensus

Clinical axillary lymph node management in early breast cancer has evolved from being merely an aspect of surgical management and now includes the entire multidisciplinary team. The second edition of the "Lucerne Toolbox", a multidisciplinary consortium of European cancer societies and patient representatives, addresses the challenges of clinical axillary lymph node management, from diagnosis to local therapy of the axilla. Five working packages were developed, following the patients' journey and addressing specific clinical scenarios. Panellists voted on 72 statements, reaching consensus (agreement of 75% or more) in 52.8%, majority (51%-74% agreement) in 43.1%, and no decision in 4.2%. Based on the votes, targeted imaging and standardized pathology of lymph nodes should be a prerequisite to planning local and systemic therapy, axillary lymph node dissection can be replaced by sentinel lymph node biopsy ( ± targeted approaches) in a majority of scenarios; and positive patient outcomes should be driven by both low recurrence risks and low rates of lymphoedema.

Breast PET/MRI Hybrid Imaging and Targeted Tracers

The recent introduction of hybrid positron emission tomography/magnetic resonance imaging (PET/MRI) as a promising imaging modality for breast cancer assessment has prompted fervent research activity on its clinical applications. The current knowledge regarding the possible clinical applications of hybrid PET/MRI is constantly evolving, thanks to the development and clinical availability of hybrid scanners, the development of new PET tracers and the rise of artificial intelligence (AI) techniques. In this state-of-the-art review on the use of hybrid breast PET/MRI, the most promising advanced MRI techniques (diffusion-weighted imaging, dynamic contrast-enhanced MRI, magnetic resonance spectroscopy, and chemical exchange saturation transfer) are discussed. Current and experimental PET tracers (¹⁸ F-FDG, ¹⁸ F-NaF, choline, ¹⁸ F-FES, ¹⁸ F-FES, ⁸⁹ Zr-trastuzumab, choline derivatives, ¹⁸ F-FLT, and ⁶⁸ Ga-FAPI-46) are described in order to provide an overview on their molecular mechanisms of action and corresponding clinical applications. New perspectives represented by the use of radiomics and AI techniques are discussed. Furthermore, the current strengths and limitations of hybrid PET/MRI in the real world are highlighted. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

Limited value of multiparametric MRI with dynamic contrast-enhanced and diffusion-weighted imaging in non-mass enhancing breast tumors

PURPOSE

To investigate the diagnostic value of multiparametric MRI (mpMRI) including dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion-weighted imaging (DWI) in non-mass enhancing breast tumors.

METHOD

Patients who underwent mpMRI, who were diagnosed with a suspicious non-mass enhancement (NME) on DCE-MRI (BI-RADS 4/5), and who subsequently underwent image-guided biopsy were retrospectively included. Two radiologists independently evaluated all NMEs, on both DCE-MR images and high-b-value DW images. Different mpMRI reading approaches were evaluated: 1) with a fixed apparent diffusion coefficient (ADC) threshold (<1.3 malignant, ≥1.3 benign) based on the recommendation by the European Society of Breast Imaging (EUSOBI); 2) with a fixed ADC threshold (<1.5 malignant, ≥1.5 benign) based on recently published trial data; 3) with an ADC threshold adapted to the assigned BI-RADS classification using a previously published reading method; and 4) with individually determined best thresholds for each reader.

RESULTS

The final study sample consisted of 66 lesions in 66 patients. DCE-MRI alone had the highest sensitivity for breast cancer detection (94.8-100 %), outperforming all mpMRI reading approaches (R1 74.4-87.1 %, R2 71.7-94.8 %) and DWI alone (R1 74.4 %, R2 79.4 %). The adapted approach achieved the best specificity for both readers (85.1 %), resulting in the best diagnostic accuracy for R1 (86.5 %) but a moderate diagnostic accuracy for R2 (77.2 %).

CONCLUSION

mpMRI has limited added diagnostic value to DCE-MRI in the assessment of NME.

Breast MRI Background Parenchymal Enhancement Categorization Using Deep Learning: Outperforming the Radiologist

BACKGROUND

Background parenchymal enhancement (BPE) is assessed on breast MRI reports as mandated by the Breast Imaging Reporting and Data System (BI-RADS) but is prone to inter and intrareader variation. Semiautomated and fully automated BPE assessment tools have been developed but none has surpassed radiologist BPE designations.

PURPOSE

To develop a deep learning model for automated BPE classification and to compare its performance with current standard-of-care radiology report BPE designations.

STUDY TYPE

Retrospective.

POPULATION

Consecutive high-risk patients (i.e. >20% lifetime risk of breast cancer) who underwent contrast-enhanced screening breast MRI from October 2013 to January 2019. The study included 5224 breast MRIs, divided into 3998 training, 444 validation, and 782 testing exams. On radiology reports, 1286 exams were categorized as high BPE (i.e., marked or moderate) and 3938 as low BPE (i.e., mild or minimal).

FIELD STRENGTH/SEQUENCE

A 1.5 T or 3 T system; one precontrast and three postcontrast phases of fat-saturated T1-weighted dynamic contrast-enhanced imaging.

ASSESSMENT

Breast MRIs were used to develop two deep learning models (Slab artificial intelligence (AI); maximum intensity projection [MIP] AI) for BPE categorization using radiology report BPE labels. Models were tested on a heldout test sets using radiology report BPE and three-reader averaged consensus as the reference standards.

STATISTICAL TESTS

Model performance was assessed using receiver operating characteristic curve analysis. Associations between high BPE and BI-RADS assessments were evaluated using McNemar's chi-square test (α* = 0.025).

RESULTS

The Slab AI model significantly outperformed the MIP AI model across the full test set (area under the curve of 0.84 vs. 0.79) using the radiology report reference standard. Using three-reader consensus BPE labels reference standard, our AI model significantly outperformed radiology report BPE labels. Finally, the AI model was significantly more likely than the radiologist to assign "high BPE" to suspicious breast MRIs and significantly less likely than the radiologist to assign "high BPE" to negative breast MRIs.

DATA CONCLUSION

Fully automated BPE assessments for breast MRIs could be more accurate than BPE assessments from radiology reports.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY STAGE: 3.

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

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

Breast Lesion Classification with Multiparametric Breast MRI Using Radiomics and Machine Learning: A Comparison with Radiologists' Performance

Simple Summary

Currently, breast contrast-enhanced MRI is the most sensitive imaging technique for breast cancer detection; however, its specificity is low given the common characteristics shared by benign breast lesions and some cancers. This leads to a high number of false-positive cases and, therefore, unnecessary biopsies. Multiparametric MRI including diffusion-weighted imaging assists in this task by increasing the specificity for breast lesion discrimination. Nevertheless, interpretation of breast MRI is still highly dependent on the reader’s level of experience. Our work combines radiomic features extracted from multiparametric MRI to generate predictive models for breast cancer differentiation. Additionally, decision support models were compared with the performance of two breast dedicated radiologists for lesion differentiation. Our work proves the potential of multiparametric radiomics coupled with machine learning to be implemented in clinical practice for lesion differentiation on breast MRI. AI algorithms show value to assist less experienced readers, improving the accuracy for breast lesion discrimination.

Abstract

This multicenter retrospective study compared the performance of radiomics analysis coupled with machine learning (ML) with that of radiologists for the classification of breast tumors. A total of 93 consecutive women (mean age: 49 ± 12 years) with 104 histopathologically verified enhancing lesions (mean size: 22.8 ± 15.1 mm), classified as suspicious on multiparametric breast MRIs were included. Two experienced breast radiologists assessed all of the lesions, assigning a Breast Imaging Reporting and Database System (BI-RADS) suspicion category, providing a diffusion-weighted imaging (DWI) score based on lesion signal intensity, and determining the apparent diffusion coefficient (ADC). Ten predictive models for breast lesion discrimination were generated using radiomic features extracted from the multiparametric MRI. The area under the receiver operating curve (AUC) and the accuracy were compared using McNemar’s test. Multiparametric radiomics with DWI score and BI-RADS (accuracy = 88.5%; AUC = 0.93) and multiparametric radiomics with ADC values and BI-RADS (accuracy= 88.5%; AUC = 0.96) models showed significant improvements in diagnostic accuracy compared to the multiparametric radiomics (DWI + DCE data) model (p = 0.01 and p = 0.02, respectively), but performed similarly compared to the multiparametric assessment by radiologists (accuracy = 85.6%; AUC = 0.03; p = 0.39). In conclusion, radiomics analysis coupled with the ML of multiparametric MRI could assist in breast lesion discrimination, especially for less experienced readers of breast MRIs.

Differentiation Between Benign and Metastatic Breast Lymph Nodes Using Apparent Diffusion Coefficients

The aim of this study was to determine the range of apparent diffusion coefficient (ADC) values for benign axillary lymph nodes in contrast to malignant axillary lymph nodes, and to define the optimal ADC thresholds for three different ADC parameters (minimum, maximum, and mean ADC) in differentiating between benign and malignant lymph nodes. This retrospective study included consecutive patients who underwent breast MRI from January 2017–December 2020. Two-year follow-up breast imaging or histopathology served as the reference standard for axillary lymph node status. Area under the receiver operating characteristic curve (AUC) values for minimum, maximum, and mean ADC (min ADC, max ADC, and mean ADC) for benign vs malignant axillary lymph nodes were determined using the Wilcoxon rank sum test, and optimal ADC thresholds were determined using Youden’s Index. The final study sample consisted of 217 patients (100% female, median age of 52 years (range, 22–81), 110 with benign axillary lymph nodes and 107 with malignant axillary lymph nodes. For benign axillary lymph nodes, ADC values (×10⁻³ mm²/s) ranged from 0.522–2.712 for mean ADC, 0.774–3.382 for max ADC, and 0.071–2.409 for min ADC; for malignant axillary lymph nodes, ADC values (×10⁻³ mm²/s) ranged from 0.796–1.080 for mean ADC, 1.168–1.592 for max ADC, and 0.351–0.688 for min ADC for malignant axillary lymph nodes. While there was a statistically difference in all ADC parameters (p<0.001) between benign and malignant axillary lymph nodes, boxplots illustrate overlaps in ADC values, with the least overlap occurring with mean ADC, suggesting that this is the most useful ADC parameter for differentiating between benign and malignant axillary lymph nodes. The mean ADC threshold that resulted in the highest diagnostic accuracy for differentiating between benign and malignant lymph nodes was 1.004×10⁻³ mm²/s, yielding an accuracy of 75%, sensitivity of 71%, specificity of 79%, positive predictive value of 77%, and negative predictive value of 74%. This mean ADC threshold is lower than the European Society of Breast Imaging (EUSOBI) mean ADC threshold of 1.300×10⁻³ mm²/s, therefore suggesting that the EUSOBI threshold which was recently recommended for breast tumors should not be extrapolated to evaluate the axillary lymph nodes.

Radiologist-Level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans

Purpose

To develop a deep network architecture that would achieve fully automated radiologist-level segmentation of cancers at breast MRI.

Materials and Methods

In this retrospective study, 38 229 examinations (composed of 64 063 individual breast scans from 14 475 patients) were performed in female patients (age range, 12–94 years; mean age, 52 years ± 10 [standard deviation]) who presented between 2002 and 2014 at a single clinical site. A total of 2555 breast cancers were selected that had been segmented on two-dimensional (2D) images by radiologists, as well as 60 108 benign breasts that served as examples of noncancerous tissue; all these were used for model training. For testing, an additional 250 breast cancers were segmented independently on 2D images by four radiologists. Authors selected among several three-dimensional (3D) deep convolutional neural network architectures, input modalities, and harmonization methods. The outcome measure was the Dice score for 2D segmentation, which was compared between the network and radiologists by using the Wilcoxon signed rank test and the two one-sided test procedure.

Results

The highest-performing network on the training set was a 3D U-Net with dynamic contrast-enhanced MRI as input and with intensity normalized for each examination. In the test set, the median Dice score of this network was 0.77 (interquartile range, 0.26). The performance of the network was equivalent to that of the radiologists (two one-sided test procedures with radiologist performance of 0.69–0.84 as equivalence bounds, P < .001 for both; n = 250).

Conclusion

When trained on a sufficiently large dataset, the developed 3D U-Net performed as well as fellowship-trained radiologists in detailed 2D segmentation of breast cancers at routine clinical MRI.

Keywords: MRI, Breast, Segmentation, Supervised Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms

Published under a CC BY 4.0 license.

Supplemental material is available for this article.

Assessing PD-L1 Expression Status Using Radiomic Features from Contrast-Enhanced Breast MRI in Breast Cancer Patients: Initial Results

Simple Summary

To our knowledge, this is the first study assessing radiomics coupled with machine learning from MRI-derived features to predict PD-L1 expression status in biopsy-proven triple negative breast cancers and comparing the performance of this approach with the performance of qualitative assessment by two radiologists. This pilot study shows that radiomics analysis coupled with machine learning of DCE-MRI is a promising approach to derive prognostic and predictive information and to select patients who could benefit from anti-PD-1/PD-L1 treatment. This technique could also be used to monitor PD-L1 expression, as it can vary over time and between different regions of the tumor, thus avoiding repeated biopsies.

Abstract

The purpose of this retrospective study was to assess whether radiomics analysis coupled with machine learning (ML) based on standard-of-care dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict PD-L1 expression status in patients with triple negative breast cancer, and to compare the performance of this approach with radiologist review. Patients with biopsy-proven triple negative breast cancer who underwent pre-treatment breast MRI and whose PD-L1 status was available were included. Following 3D tumor segmentation and extraction of radiomic features, radiomic features with significant differences between PD-L1+ and PD-L1− patients were determined, and a final predictive model to predict PD-L1 status was developed using a coarse decision tree and five-fold cross-validation. Separately, all lesions were qualitatively assessed by two radiologists independently according to the BI-RADS lexicon. Of 62 women (mean age 47, range 31–81), 27 had PD-L1− tumors and 35 had PD-L1+ tumors. The final radiomics model to predict PD-L1 status utilized three MRI parameters, i.e., variance (FO), run length variance (RLM), and large zone low grey level emphasis (LZLGLE), for a sensitivity of 90.7%, specificity of 85.1%, and diagnostic accuracy of 88.2%. There were no significant associations between qualitative assessed DCE-MRI imaging features and PD-L1 status. Thus, radiomics analysis coupled with ML based on standard-of-care DCE-MRI is a promising approach to derive prognostic and predictive information and to select patients who could benefit from anti-PD-1/PD-L1 treatment.

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

OBJECTIVES

Preoperative breast magnetic resonance imaging (MRI) can inform surgical planning but might cause overtreatment by increasing the mastectomy rate. The Multicenter International Prospective Analysis (MIPA) study investigated this controversial issue.

METHODS

This observational study enrolled women aged 18-80 years with biopsy-proven breast cancer, who underwent MRI in addition to conventional imaging (mammography and/or breast ultrasonography) or conventional imaging alone before surgery as routine practice at 27 centers. Exclusion criteria included planned neoadjuvant therapy, pregnancy, personal history of any cancer, and distant metastases.

RESULTS

Of 5896 analyzed patients, 2763 (46.9%) had conventional imaging only (noMRI group), and 3133 (53.1%) underwent MRI that was performed for diagnosis, screening, or unknown purposes in 692/3133 women (22.1%), with preoperative intent in 2441/3133 women (77.9%, MRI group). Patients in the MRI group were younger, had denser breasts, more cancers ≥ 20 mm, and a higher rate of invasive lobular histology than patients who underwent conventional imaging alone (p < 0.001 for all comparisons). Mastectomy was planned based on conventional imaging in 22.4% (MRI group) versus 14.4% (noMRI group) (p < 0.001). The additional planned mastectomy rate in the MRI group was 11.3%. The overall performed first- plus second-line mastectomy rate was 36.3% (MRI group) versus 18.0% (noMRI group) (p < 0.001). In women receiving conserving surgery, MRI group had a significantly lower reoperation rate (8.5% versus 11.7%, p < 0.001).

CONCLUSIONS

Clinicians requested breast MRI for women with a higher a priori probability of receiving mastectomy. MRI was associated with 11.3% more mastectomies, and with 3.2% fewer reoperations in the breast conservation subgroup.

KEY POINTS

• In 19% of patients of the MIPA study, breast MRI was performed for screening or diagnostic purposes. • The current patient selection to preoperative breast MRI implies an 11% increase in mastectomies, counterbalanced by a 3% reduction of the reoperation rate. • Data from the MIPA study can support discussion in tumor boards when preoperative MRI is under consideration and should be shared with patients to achieve informed decision-making.

AI-Enhanced Diagnosis of Challenging Lesions in Breast MRI: A Methodology and Application Primer

Computer-aided diagnosis (CAD) systems have become an important tool in the assessment of breast tumors with magnetic resonance imaging (MRI). CAD systems can be used for the detection and diagnosis of breast tumors as a "second opinion" review complementing the radiologist's review. CAD systems have many common parts, such as image preprocessing, tumor feature extraction, and data classification that are mostly based on machine-learning (ML) techniques. In this review article, we describe applications of ML-based CAD systems in MRI covering the detection of diagnostically challenging lesions of the breast such as nonmass enhancing (NME) lesions, and furthermore discuss how multiparametric MRI and radiomics can be applied to the study of NME, including prediction of response to neoadjuvant chemotherapy (NAC). Since ML has been widely used in the medical imaging community, we provide an overview about the state-of-the-art and novel techniques applied as classifiers to CAD systems. The differences in the CAD systems in MRI of the breast for several standard and novel applications for NME are explained in detail to provide important examples, illustrating: 1) CAD for detection and diagnosis, 2) CAD in multiparametric imaging, 3) CAD in NAC, and 4) breast cancer radiomics. We aim to provide a comparison between these CAD applications and to illustrate a global view on intelligent CAD systems based on machine and deep learning in MRI of the breast. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 2.

AI-enhanced breast imaging: Where are we and where are we heading?

Significant advances in imaging analysis and the development of high-throughput methods that can extract and correlate multiple imaging parameters with different clinical outcomes have led to a new direction in medical research. Radiomics and artificial intelligence (AI) studies are rapidly evolving and have many potential applications in breast imaging, such as breast cancer risk prediction, lesion detection and classification, radiogenomics, and prediction of treatment response and clinical outcomes. AI has been applied to different breast imaging modalities, including mammography, ultrasound, and magnetic resonance imaging, in different clinical scenarios. The application of AI tools in breast imaging has an unprecedented opportunity to better derive clinical value from imaging data and reshape the way we care for our patients. The aim of this study is to review the current knowledge and future applications of AI-enhanced breast imaging in clinical practice.

Axillary lymphadenopathy at the time of COVID-19 vaccination: ten recommendations from the European Society of Breast Imaging (EUSOBI)

Unilateral axillary lymphadenopathy is a frequent mild side effect of COVID-19 vaccination. European Society of Breast Imaging (EUSOBI) proposes ten recommendations to standardise its management and reduce unnecessary additional imaging and invasive procedures: (1) in patients with previous history of breast cancer, vaccination should be performed in the contralateral arm or in the thigh; (2) collect vaccination data for all patients referred to breast imaging services, including patients undergoing breast cancer staging and follow-up imaging examinations; (3) perform breast imaging examinations preferentially before vaccination or at least 12 weeks after the last vaccine dose; (4) in patients with newly diagnosed breast cancer, apply standard imaging protocols regardless of vaccination status; (5) in any case of symptomatic or imaging-detected axillary lymphadenopathy before vaccination or at least 12 weeks after, examine with appropriate imaging the contralateral axilla and both breasts to exclude malignancy; (6) in case of axillary lymphadenopathy contralateral to the vaccination side, perform standard work-up; (7) in patients without breast cancer history and no suspicious breast imaging findings, lymphadenopathy only ipsilateral to the vaccination side within 12 weeks after vaccination can be considered benign or probably-benign, depending on clinical context; (8) in patients without breast cancer history, post-vaccination lymphadenopathy coupled with suspicious breast finding requires standard work-up, including biopsy when appropriate; (9) in patients with breast cancer history, interpret and manage post-vaccination lymphadenopathy considering the timeframe from vaccination and overall nodal metastatic risk; (10) complex or unclear cases should be managed by the multidisciplinary team.

Radiomics and Machine Learning with Multiparametric Breast MRI for Improved Diagnostic Accuracy in Breast Cancer Diagnosis

The purpose of this multicenter retrospective study was to evaluate radiomics analysis coupled with machine learning (ML) of dynamic contrast-enhanced (DCE) and diffusion-weighted imaging (DWI) radiomics models separately and combined as multiparametric MRI for improved breast cancer detection. Consecutive patients (Memorial Sloan Kettering Cancer Center, January 2018-March 2020; Medical University Vienna, from January 2011-August 2014) with a suspicious enhancing breast tumor on breast MRI categorized as BI-RADS 4 and who subsequently underwent image-guided biopsy were included. In 93 patients (mean age: 49 years ± 12 years; 100% women), there were 104 lesions (mean size: 22.8 mm; range: 7-99 mm), 46 malignant and 58 benign. Radiomics features were calculated. Subsequently, the five most significant features were fitted into multivariable modeling to produce a robust ML model for discriminating between benign and malignant lesions. A medium Gaussian support vector machine (SVM) model with five-fold cross validation was developed for each modality. A model based on DWI-extracted features achieved an AUC of 0.79 (95% CI: 0.70-0.88), whereas a model based on DCE-extracted features yielded an AUC of 0.83 (95% CI: 0.75-0.91). A multiparametric radiomics model combining DCE- and DWI-extracted features showed the best AUC (0.85; 95% CI: 0.77-0.92) and diagnostic accuracy (81.7%; 95% CI: 73.0-88.6). In conclusion, radiomics analysis coupled with ML of multiparametric MRI allows an improved evaluation of suspicious enhancing breast tumors recommended for biopsy on clinical breast MRI, facilitating accurate breast cancer diagnosis while reducing unnecessary benign breast biopsies.

Diffusion-weighted Imaging Allows for Downgrading MR BI-RADS 4 Lesions in Contrast-enhanced MRI of the Breast to Avoid Unnecessary Biopsy

PURPOSE

Diffusion-weighted imaging with the calculation of an apparent diffusion coefficient (ADC) has been proposed as a quantitative biomarker on contrast-enhanced MRI (CE-MRI) of the breast. There is a need to approve a generalizable ADC cutoff. The purpose of this study was to evaluate whether a predefined ADC cutoff allows downgrading of BI-RADS 4 lesions on CE-MRI, avoiding unnecessary biopsies.

EXPERIMENTAL DESIGN

This was a retrospective, multicentric, cross-sectional study. Data from five centers were pooled on the individual lesion level. Eligible patients had a BI-RADS 4 rating on CE-MRI. For each center, two breast radiologists evaluated the images. Data on lesion morphology (mass, non-mass), size, and ADC were collected. Histology was the standard of reference. A previously suggested ADC cutoff (≥1.5 × 10-3 mm2/second) was applied. A negative likelihood ratio of 0.1 or lower was considered as a rule-out criterion for breast cancer. Diagnostic performance indices were calculated by ROC analysis.

RESULTS

There were 657 female patients (mean age, 42; SD, 14.1) with 696 BI-RADS 4 lesions included. Disease prevalence was 59.5% (414/696). The area under the ROC curve was 0.784. Applying the investigated ADC cutoff, sensitivity was 96.6% (400/414). The potential reduction of unnecessary biopsies was 32.6% (92/282).

CONCLUSIONS

An ADC cutoff of ≥1.5 × 10-3 mm2/second allows downgrading of lesions classified as BI-RADS 4 on breast CE-MRI. One-third of unnecessary biopsies could thus be avoided.

Multispectral Imaging for Metallic Biopsy Marker Detection During MRI-Guided Breast Biopsy: A Feasibility Study for Clinical Translation

Purpose

To assess the feasibility and diagnostic accuracy of multispectral MRI (MSI) in the detection and localization of biopsy markers during MRI-guided breast biopsy.

Methods

This prospective study included 20 patients undergoing MR-guided breast biopsy. In 10 patients (Group 1), MSI was acquired following tissue sampling and biopsy marker deployment. In the other 10 patients (Group 2), MSI was acquired following tissue sampling but before biopsy marker deployment (to simulate deployment failure). All patients received post-procedure mammograms. Group 1 and Group 2 designations, in combination with the post-procedure mammogram, served as the reference standard. The diagnostic performance of MSI for biopsy marker identification was independently evaluated by two readers using two-spectral-bin MR and one-spectral-bin MR. The κ statistic was used to assess inter-rater agreement for biopsy marker identification.

Results

The sensitivity, specificity, and accuracy of biopsy marker detection for readers 1 and 2 using 2-bin MSI were 90.0% (9/10) and 90.0% (9/10), 100.0% (10/10) and 100.0% (10/10), 95.0% (19/20) and 95.0% (19/20); and using 1-bin MSI were 70.0% (7/10) and 80.0% (8/10), 100.0% (8/8) and 100.0% (10/10), 85.0% (17/20) and 90.0% (18/20). Positive predictive value was 100% for both readers for all numbers of bins. Inter-rater agreement was excellent: κ was 1.0 for 2-bin MSI and 0.81 for 1-bin MSI.

Conclusion

MSI is a feasible, diagnostically accurate technique for identifying metallic biopsy markers during MRI-guided breast biopsy and may eliminate the need for a post-procedure mammogram.

Using Deep Learning to Improve Nonsystematic Viewing of Breast Cancer on MRI

OBJECTIVE

To investigate the feasibility of using deep learning to identify tumor-containing axial slices on breast MRI images.

METHODS

This IRB-approved retrospective study included consecutive patients with operable invasive breast cancer undergoing pretreatment breast MRI between January 1, 2014, and December 31, 2017. Axial tumor-containing slices from the first postcontrast phase were extracted. Each axial image was subdivided into two subimages: one of the ipsilateral cancer-containing breast and one of the contralateral healthy breast. Cases were randomly divided into training, validation, and testing sets. A convolutional neural network was trained to classify subimages into "cancer" and "no cancer" categories. Accuracy, sensitivity, and specificity of the classification system were determined using pathology as the reference standard. A two-reader study was performed to measure the time savings of the deep learning algorithm using descriptive statistics.

RESULTS

Two hundred and seventy-three patients with unilateral breast cancer met study criteria. On the held-out test set, accuracy of the deep learning system for tumor detection was 92.8% (648/706; 95% confidence interval: 89.7%-93.8%). Sensitivity and specificity were 89.5% and 94.3%, respectively. Readers spent 3 to 45 seconds to scroll to the tumor-containing slices without use of the deep learning algorithm.

CONCLUSION

In breast MR exams containing breast cancer, deep learning can be used to identify the tumor-containing slices. This technology may be integrated into the picture archiving and communication system to bypass scrolling when viewing stacked images, which can be helpful during nonsystematic image viewing, such as during interdisciplinary tumor board meetings.

Breast Tumor Characterization Using [18F]FDG-PET/CT Imaging Combined with Data Preprocessing and Radiomics

Simple Summary

Breast cancer is the second most common diagnosed malignancy in women worldwide. In this study, we examine the feasibility of breast tumor characterization based on [¹⁸F]FDG-PET/CT images using machine learning (ML) approaches in combination with data-preprocessing techniques. ML prediction models for breast cancer detection and the identification of breast cancer receptor status, proliferation rate, and molecular subtypes were established and evaluated. Furthermore, the importance of most repeatable features was investigated. Results displayed high performance of malignant/benign tumor differentiation and triple negative tumor subtype ML models. We observed high repeatability of radiomic features for both high performing predictive models.

Abstract

Background: This study investigated the performance of ensemble learning holomic models for the detection of breast cancer, receptor status, proliferation rate, and molecular subtypes from [¹⁸F]FDG-PET/CT images with and without incorporating data pre-processing algorithms. Additionally, machine learning (ML) models were compared with conventional data analysis using standard uptake value lesion classification. Methods: A cohort of 170 patients with 173 breast cancer tumors (132 malignant, 38 benign) was examined with [¹⁸F]FDG-PET/CT. Breast tumors were segmented and radiomic features were extracted following the imaging biomarker standardization initiative (IBSI) guidelines combined with optimized feature extraction. Ensemble learning including five supervised ML algorithms was utilized in a 100-fold Monte Carlo (MC) cross-validation scheme. Data pre-processing methods were incorporated prior to machine learning, including outlier and borderline noisy sample detection, feature selection, and class imbalance correction. Feature importance in each model was assessed by calculating feature occurrence by the R-squared method across MC folds. Results: Cross validation demonstrated high performance of the cancer detection model (80% sensitivity, 78% specificity, 80% accuracy, 0.81 area under the curve (AUC)), and of the triple negative tumor identification model (85% sensitivity, 78% specificity, 82% accuracy, 0.82 AUC). The individual receptor status and luminal A/B subtype models yielded low performance (0.46–0.68 AUC). SUV_max model yielded 0.76 AUC in cancer detection and 0.70 AUC in predicting triple negative subtype. Conclusions: Predictive models based on [¹⁸F]FDG-PET/CT images in combination with advanced data pre-processing steps aid in breast cancer diagnosis and in ML-based prediction of the aggressive triple negative breast cancer subtype.