Search

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 AlgorithmsPublished under a CC BY 4.0 license. Supplemental material is available for this article.

PURPOSE: To investigate whether radiomics features extracted from magnetic resonance imaging (MRI) of patients with biopsy-proven atypical ductal hyperplasia (ADH) coupled with machine learning can differentiate high-risk lesions that will upgrade to malignancy at surgery from those that will not, and to determine if qualitatively and semi-quantitatively assessed imaging features, clinical factors, and image-guided biopsy technical factors are associated with upgrade rate. METHODS: This retrospective study included 127 patients with 139 breast lesions yielding ADH at biopsy who were assessed with multiparametric MRI prior to biopsy. Two radiologists assessed all lesions independently and with a third reader in consensus according to the BI-RADS lexicon. Univariate analysis and multivariate modeling were performed to identify significant radiomic features to be included in a machine learning model to discriminate between lesions that upgraded to malignancy on surgery from those that did not. RESULTS: Of 139 lesions, 28 were upgraded to malignancy at surgery, while 111 were not upgraded. Diagnostic accuracy was 53.6%, specificity 79.2%, and sensitivity 15.3% for the model developed from pre-contrast features, and 60.7%, 86%, and 22.8% for the model developed from delta radiomics datasets. No significant associations were found between any radiologist-assessed lesion parameters and upgrade status. There was a significant correlation between the number of specimens sampled during biopsy and upgrade status (p = 0.003). CONCLUSION: Radiomics analysis coupled with machine learning did not predict upgrade status of ADH. The only significant result from this analysis is between the number of specimens sampled during biopsy procedure and upgrade status at surgery.

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.

OBJECTIVES: To assess DWI for tumor visibility and breast cancer detection by the addition of different synthetic b-values. METHODS: Eighty-four consecutive women who underwent a breast-multiparametric-MRI (mpMRI) with enhancing lesions on DCE-MRI (BI-RADS 2-5) were included in this IRB-approved retrospective study from September 2018 to March 2019. Three readers evaluated DW acquired b-800 and synthetic b-1000, b-1200, b-1500, and b-1800 s/mm2 images for lesion visibility and preferred b-value based on lesion conspicuity. Image quality (1-3 scores) and breast composition (BI-RADS) were also recorded. Diagnostic parameters for DWI were determined using a 1-5 malignancy score based on qualitative imaging parameters (acquired + preferred synthetic b-values) and ADC values. BI-RADS classification was used for DCE-MRI and quantitative ADC values + BI-RADS were used for mpMRI. RESULTS: Sixty-four malignant (average = 23 mm) and 39 benign (average = 8 mm) lesions were found in 80 women. Although b-800 achieved the best image quality score, synthetic b-values 1200-1500 s/mm2 were preferred for lesion conspicuity, especially in dense breast. b-800 and synthetic b-1000/b-1200 s/mm2 values allowed the visualization of 84-90% of cancers visible with DCE-MRI performing better than b-1500/b-1800 s/mm2. DWI was more specific (86.3% vs 65.7%, p < 0.001) but less sensitive (62.8% vs 90%, p < 0.001) and accurate (71% vs 80.7%, p = 0.003) than DCE-MRI for breast cancer detection, where mpMRI was the most accurate modality accounting for less false positive cases. CONCLUSION: The addition of synthetic b-values enhances tumor conspicuity and could potentially improve tumor visualization particularly in dense breast. However, its supportive role for DWI breast cancer detection is still not definite. KEY POINTS: • The addition of synthetic b-values (1200-1500 s/mm2) to acquired DWI afforded a better lesion conspicuity without increasing acquisition time and was particularly useful in dense breasts. • Despite the use of synthetic b-values, DWI was less sensitive and accurate than DCE-MRI for breast cancer detection. • A multiparametric MRI modality still remains the best approach having the highest accuracy for breast cancer detection and thus reducing the number of unnecessary biopsies.

OBJECTIVES: To investigate whether radiomics features extracted from MRI of BRCA-positive patients with sub-centimeter breast masses can be coupled with machine learning to differentiate benign from malignant lesions using model-free parameter maps. METHODS: In this retrospective study, BRCA-positive patients who had an MRI from November 2013 to February 2019 that led to a biopsy (BI-RADS 4) or imaging follow-up (BI-RADS 3) for sub-centimeter lesions were included. Two radiologists assessed all lesions independently and in consensus according to BI-RADS. Radiomics features were calculated using open-source CERR software. Univariate analysis and multivariate modeling were performed to identify significant radiomics features and clinical factors to be included in a machine learning model to differentiate malignant from benign lesions. RESULTS: Ninety-six BRCA mutation carriers (mean age at biopsy = 45.5 ± 13.5 years) were included. Consensus BI-RADS classification assessment achieved a diagnostic accuracy of 53.4%, sensitivity of 75% (30/40), specificity of 42.1% (32/76), PPV of 40.5% (30/74), and NPV of 76.2% (32/42). The machine learning model combining five parameters (age, lesion location, GLCM-based correlation from the pre-contrast phase, first-order coefficient of variation from the 1st post-contrast phase, and SZM-based gray level variance from the 1st post-contrast phase) achieved a diagnostic accuracy of 81.5%, sensitivity of 63.2% (24/38), specificity of 91.4% (64/70), PPV of 80.0% (24/30), and NPV of 82.1% (64/78). CONCLUSIONS: Radiomics analysis coupled with machine learning improves the diagnostic accuracy of MRI in characterizing sub-centimeter breast masses as benign or malignant compared with qualitative morphological assessment with BI-RADS classification alone in BRCA mutation carriers. KEY POINTS: • Radiomics and machine learning can help differentiate benign from malignant breast masses even if the masses are small and morphological features are benign. • Radiomics and machine learning analysis showed improved diagnostic accuracy, specificity, PPV, and NPV compared with qualitative morphological assessment alone.

BACKGROUND: To use clinical and MRI radiomic features coupled with machine learning to assess HER2 expression level and predict pathologic response (pCR) in HER2 overexpressing breast cancer patients receiving neoadjuvant chemotherapy (NAC). METHODS: This retrospective study included 311 patients. pCR was defined as no residual invasive carcinoma in the breast or axillary lymph nodes (ypT0/isN0). Radiomics/statistical analysis was performed using MATLAB and CERR software. After ROC and correlation analysis, selected radiomics parameters were advanced to machine learning modelling alongside clinical MRI-based parameters (lesion type, multifocality, size, nodal status). For predicting pCR, the data was split into a training and test set (80:20). FINDINGS: The overall pCR rate was 60.5% (188/311). The final model to predict HER2 heterogeneity utilised three MRI parameters (two clinical, one radiomic) for a sensitivity of 99.3% (277/279), specificity of 81.3% (26/32), and diagnostic accuracy of 97.4% (303/311). The final model to predict pCR included six MRI parameters (two clinical, four radiomic) for a sensitivity of 86.5% (32/37), specificity of 80.0% (20/25), and diagnostic accuracy of 83.9% (52/62) (test set); these results were independent of age and ER status, and outperformed the best model developed using clinical parameters only (p=0.029, comparison of proportion Chi-squared test). INTERPRETATION: The machine learning models, including both clinical and radiomics MRI features, can be used to assess HER2 expression level and can predict pCR after NAC in HER2 overexpressing breast cancer patients. FUNDING: NIH/NCI (P30CA008748), Susan G. Komen Foundation, Breast Cancer Research Foundation, Spanish Foundation Alfonso Martin Escudero, European School of Radiology.

BACKGROUND: To investigate if baseline and/or changes in contralateral background parenchymal enhancement (BPE) and fibroglandular tissue (FGT) measured on magnetic resonance imaging (MRI) and mammographic breast density (MD) can be used as imaging biomarkers for overall and recurrence-free survival in patients with invasive lobular carcinomas (ILCs) undergoing adjuvant endocrine treatment. METHODS: Women who fulfilled the following inclusion criteria were included in this retrospective HIPAA-compliant IRB-approved study: unilateral ILC, pre-treatment breast MRI and/or mammography from 2000 to 2010, adjuvant endocrine treatment, follow-up MRI, and/or mammography 1-2 years after treatment onset. BPE, FGT, and mammographic MD of the contralateral breast were independently graded by four dedicated breast radiologists according to BI-RADS. Associations between the baseline levels and change in levels of BPE, FGT, and MD with overall survival and recurrence-free survival were assessed using Kaplan-Meier survival curves and Cox regression analysis. RESULTS: Two hundred ninety-eight patients (average age = 54.1 years, range = 31-79) fulfilled the inclusion criteria. The average follow-up duration was 11.8 years (range = 2-19). Baseline and change in levels of BPE, FGT, and MD were not significantly associated with recurrence-free or overall survival. Recurrence-free and overall survival were affected by histological subtype (p

Multishot multiplexed sensitivity-encoding diffusion-weighted imaging is a feasible and easily implementable routine breast MRI protocol that yields high-quality diffusion-weighted breast images.Purpose: To compare multiplexed sensitivity-encoding (MUSE) diffusion-weighted imaging (DWI) and single-shot DWI for lesion visibility and differentiation of malignant and benign lesions within the breast.Materials and Methods: In this prospective institutional review board-approved study, both MUSE DWI and single-shot DWI sequences were first optimized in breast phantoms and then performed in a group of patients. Thirty women (mean age, 51.1 years ± 10.1 [standard deviation]; age range, 27-70 years) with 37 lesions were included in this study and underwent scanning using both techniques. Visual qualitative analysis of diffusion-weighted images was accomplished by two independent readers; images were assessed for lesion visibility, adequate fat suppression, and the presence of artifacts. Quantitative analysis was performed by calculating apparent diffusion coefficient (ADC) values and image quality parameters (signal-to-noise ratio [SNR] for lesions and fibroglandular tissue; contrast-to-noise ratio) by manually drawing regions of interest within the phantoms and breast tumor tissue. Interreader variability was determined using the Cohen κ coefficient, and quantitative differences between MUSE DWI and single-shot DWI were assessed using the Mann-Whitney U test; significance was defined at P < .05.Results: MUSE DWI yielded significantly improved image quality compared with single-shot DWI in phantoms (SNR, P = .001) and participants (lesion SNR, P = .009; fibroglandular tissue SNR, P = .05; contrast-to-noise ratio, P = .008). MUSE DWI ADC values showed a significant difference between malignant and benign lesions (P < .001). No significant differences were found between MUSE DWI and single-shot DWI in the mean, maximum, and minimum ADC values (P = .96, P = .28, and P = .49, respectively). Visual qualitative analysis resulted in better lesion visibility for MUSE DWI over single-shot DWI (κ = 0.70).Conclusion: MUSE DWI is a promising high-spatial-resolution technique that may enhance breast MRI protocols without the need for contrast material administration in breast screening.Keywords: Breast, MR-Diffusion Weighted Imaging, OncologySupplemental material is available for this article.© RSNA, 2020.

In patients with locally advanced breast cancer undergoing neoadjuvant chemotherapy (NAC), some patients achieve a complete pathologic response (pCR), some achieve a partial response, and some do not respond at all or even progress. Accurate prediction of treatment response has the potential to improve patient care by improving prognostication, enabling de-escalation of toxic treatment that has little benefit, facilitating upfront use of novel targeted therapies, and avoiding delays to surgery. Visual inspection of a patients tumor on multiparametric MRI is insufficient to predict that patients response to NAC. However, machine learning and deep learning approaches using a mix of qualitative and quantitative MRI features have recently been applied to predict treatment response early in the course of or even before the start of NAC. This is a novel field but the data published so far has shown promising results. We provide an overview of the machine learning and deep learning models developed to date, as well as discuss some of the challenges to clinical implementation.

BACKGROUND: Radiogenomics is the extension of radiomics through the combination of genetic and radiomic data. Because genetic testing remains expensive, invasive, and time-consuming, and thus unavailable for all patients, radiogenomics may play an important role in providing accurate imaging surrogates which are correlated with genetic expression, thereby serving as a substitute for genetic testing. MAIN BODY: In this article, we define the meaning of radiogenomics and the difference between radiomics and radiogenomics. We provide an up-to-date review of the radiomics and radiogenomics literature in oncology, focusing on breast, brain, gynecological, liver, kidney, prostate and lung malignancies. We also discuss the current challenges to radiogenomics analysis. CONCLUSION: Radiomics and radiogenomics are promising to increase precision in diagnosis, assessment of prognosis, and prediction of treatment response, providing valuable information for patient care throughout the course of the disease, given that this information is easily obtainable with imaging. Larger prospective studies and standardization will be needed to define relevant imaging biomarkers before they can be implemented into the clinical workflow.

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 [ABSTRACT FROM AUTHOR]

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 [ABSTRACT FROM AUTHOR]

Simple Summary: Triple-negative breast cancer is the most aggressive breast cancer subtype. However, women at risk for developing triple-negative breast cancer may not be identified by existing risk models. Thus, we present a study to determine if triple-negative breast cancer can be predicted based on a radiomic analysis and the machine-learning features of the fibroglandular tissue of the contralateral unaffected breast. Our initial results indicate that this approach can be used to predict triple-negative breast cancer. In the future, triple-negative breast-cancer-specific models may be implemented in the screening workflow to identify those women who are at elevated risk for triple-negative breast cancer specifically, for whom early detection and treatment are most essential. Aim: The purpose of this study was to develop a radiomic-based machine-learning model to predict triple-negative breast cancer (TNBC) based on the contralateral unaffected breast's fibroglandular tissue (FGT) in breast cancer patients. Materials and methods: This study retrospectively included 541 patients (mean age, 51 years; range, 26–82) who underwent a screening breast MRI between November 2016 and September 2018 and who were subsequently diagnosed with biopsy-confirmed, treatment-naïve breast cancer. Patients were divided into training (n = 250) and validation (n = 291) sets. In the training set, 132 radiomic features were extracted using the open-source CERR platform. Following feature selection, the final prediction model was created, based on a support vector machine with a polynomial kernel of order 2. Results: In the validation set, the final prediction model, which included four radiomic features, achieved an F1 score of 0.66, an area under the curve of 0.71, a sensitivity of 54% [47–60%], a specificity of 74% [65–84%], a positive predictive value of 84% [78–90%], and a negative predictive value of 39% [31–47%]. Conclusions: TNBC can be predicted based on radiomic features extracted from the FGT of the contralateral unaffected breast of patients, suggesting the potential for risk prediction specific to TNBC. [ABSTRACT FROM AUTHOR]