Maximum intensity breast diffusion MRI for BI-RADS 4 lesions detected on X-ray mammography

Computed diffusion-weighted imaging with a low-apparent diffusion coefficient-pixel cut-off technique for breast cancer detection

OBJECTIVE

This study aimed to compare the image quality and diagnostic performance of computed diffusion-weighted imaging (DWI) with low-apparent diffusion coefficient (ADC)-pixel cut-off technique (cDWI cut-off) and actual measured DWI (mDWI).

METHODS

Eighty-seven consecutive patients with malignant breast lesions and 72 with negative breast lesions who underwent breast MRI were retrospectively evaluated. Computed DWI with high b-values of 800, 1200, and 1500 s/mm2 and ADC cut-off thresholds of none, 0, 0.3, and 0.6 (×10-3 mm2/s) were generated from DWI with two b-values (0 and 800 s/mm2). To identify the optimal conditions, two radiologists evaluated the fat suppression and lesion reduction failure using a cut-off technique. The contrast between breast cancer and glandular tissue was evaluated using region of interest analysis. Three other board-certified radiologists independently assessed the optimised cDWI cut-off and mDWI data sets. Diagnostic performance was evaluated using receiver operating characteristic (ROC) analysis.

RESULTS

When an ADC cut-off threshold of 0.3 or 0.6 (× 10-3 mm2/s) was applied, fat suppression improved significantly (p < .05). The contrast of the cDWI cut-off with a b-value of 1200 or 1500 s/mm2 was better than the mDWI (p < .01). The ROC area under the curve for breast cancer detection was 0.837 for the mDWI and 0.909 for the cDWI cut-off (p < .01).

CONCLUSION

The cDWI cut-off provided better diagnostic performance than mDWI for breast cancer detection.

ADVANCES IN KNOWLEDGE

Using the low-ADC-pixel cut-off technique, computed DWI can improve diagnostic performance by increasing contrast and eliminating un-suppressed fat signals.

Prevalence and influencing factors for artifact development in breast MRI-derived maximum intensity projections

BACKGROUND

Magnetic resonance imaging (MRI) provides high diagnostic sensitivity for breast cancer. However, MRI artifacts may impede the diagnostic assessment. This is particularly important when evaluating maximum intensity projections (MIPs), such as in abbreviated MRI (AB-MRI) protocols, because high image quality is desired as a result of fewer sequences being available to compensate for problems.

PURPOSE

To describe the prevalence of artifacts on dynamic contrast enhanced (DCE) MRI-derived MIPs and to investigate potentially associated attributes.

MATERIAL AND METHODS

For this institutional review board approved retrospective analysis, MIPs were generated from subtraction series and cropped to represent the left and right breasts as regions of interest. These images were labeled by three independent raters regarding the presence of MRI artifacts. MRI artifact prevalence and associations with patient characteristics and technical attributes were analyzed using descriptive statistics and generalized linear models (GLMMs).

RESULTS

The study included 2524 examinations from 1794 patients (median age 50 years), performed on 1.5 and 3.0 Tesla MRI systems. Overall inter-rater agreement was kappa = 0.54. Prevalence of significant unilateral artifacts was 29.2% (736/2524), whereas bilateral artifacts were present in 37.8% (953/2524) of all examinations. According to the GLMM, artifacts were significantly positive associated with age (odds ratio [OR] = 1.52) and magnetic field strength (OR = 1.55), whereas a negative effect could be shown for body mass index (OR = 0.95).

CONCLUSION

MRI artifacts on DCE subtraction MIPs of the breast, as used in AB-MRI, are a relevant topic. Our results show that, besides the magnetic field strength, further associated attributes are patient age and body mass index, which can provide possible targets for artifact reduction.

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

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

The efficacy of abbreviated breast MRI protocols using 1.5 T MRI in the preoperative staging of newly diagnosed breast cancers

PURPOSE

To determine the efficacy of abbreviated breast magnetic resonance imaging (MRI) protocols using 1.5 T MRI in the preoperative staging of newly diagnosed breast cancers.

METHODS

Eighty patients who underwent 1.5 T MRI between August 2014 and January 2018 for the preoperative staging of breast cancer were evaluated retrospectively. Three separate abbreviated breast MRI protocols (AP) were created from a full protocol, and the images were evaluated independently by two radiologists. AP1 included axial fat-saturated T2 weighted and diffusion-weighted (DW) images, while subtracted axial fat-saturated T1 weighted images were obtained 2 min after contrast administration in AP2. Finally, AP2 and DW images were evaluated in AP3. Lesion location, number, and size, and presence of axillary lymphadenopathy were evaluated in each protocol. Pathological data (lesion quadrant, lesion size, and presence of axillary metastases) from the 80 patients were compared with the abbreviated protocols and full diagnostic protocol.

RESULTS

The best correlation with the full protocol for detecting the lesion quadrant, number of lesions, and presence of axillary lymphadenopathy was achieved with AP3 for both readers (κ = 0.954, 0.954 for the lesion quadrant, κ = 0.971, 0.910 for the number of lesions, and κ = 0.973, 0.865 for the axillary lymphadenopathy). The evaluation time in all abbreviated protocols was shorter than for the full protocol (p < 0.05). Comparing the abbreviated protocols with pathological data for both readers, the best correlation for detecting the lesion quadrant, number of lesions, and presence of axillary lymphadenopathy was achieved with AP3 (κ = 0.939, 0.954 for the lesion quadrant, κ = 0.941, 0.879 for the number of lesions, and κ = 0.842, 0.740 for axillary lymphadenopathy, respectively).

CONCLUSION

Abbreviated breast MRI protocols can provide sufficient diagnostic accuracy in the preoperative staging of breast cancer, with shorter imaging and evaluation times.

Can Ultrasound Elastography Help Better Manage Mammographic BI-RADS Category 4 Breast Lesions?

BACKGROUND

To assess the performance of conventional ultrasound (US) combined with strain elastography (SE) in the Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions on mammography.

MATERIALS AND METHODS

Women with breast lesions identified as having mammography BI-RADS 4 lesions and underwent US examination were included in China. US features and US BI-RADS assessment were recorded in real-time and prospectively reported. The pathological result was referred to as the gold standard. The performance of US in the mammographic BI-RADS category 4 lesions was evaluated. Diagnostic performances of US BI-RADS, SE and combined both were compared.

RESULTS

A total of 751 women with 751 breast lesions classified as mammographic BI-RADS category 4 were included. For mammographic findings, 530 (70.6%) were true positive and 221 (29.4%) were false positive. Conventional US achieved higher positive predictive value (PPV) than mammography (78.5% vs. 70.6%, P=.001). The specificity increased from 34.4% to 47.1% (P< .001) without any loss in sensitivity and the PPV increased to 81.9% (P = .122) when conventional US was used in combination with SE. For conventional US combined with SE, it led to a correct diagnosis of no breast cancer in 104 of the 221 false-positive findings (47.1%) and achieved higher PPV than mammography regardless of patient age and lesion size.

CONCLUSION

Conventional US combined with SE is a helpful tool for the noninvasive examination of breast lesions classified as BI-RADS category 4 on mammography. It helped increase the PPV and had the potential to avoid unnecessary biopsies of BI-RADS category 4 lesions detected on mammography.

Diffusion weighted imaging for evaluation of breast lesions: Comparison between high b-value single-shot and routine readout-segmented sequences at 3 T

PURPOSE

In this study, we compare readout-segmented echo-planar imaging (rs-EPI) Diffusion Weighted Imaging (DWI) to a work-in-progress single-shot EPI with modified Inversion Recovery Background Suppression (ss-EPI-mIRBS) sequence at 3 T using a b-value of 2000 s/mm² on image quality, lesion visibility and evaluation time.

METHOD

From September 2017 to December 2018, 23 women (one case used for training) with known breast cancer were included in this study, after providing signed informed consent. Women were scanned with the conventional rs-EPI sequence and the work-in-progress ss-EPI-mIRBS during the same examination. Four breast radiologists (4-13 years of experience) independently scored both series for overall image quality (1: extremely poor to 9: excellent). All lesions (47 in total, 36 malignant, and 11 benign and high-risk) were evaluated for visibility (1: not visible, 2: visible if location is given, 3: visible) and probability of malignancy (BI-RADS 1 to 5). ADC values were determined by measuring signal intensity in the lesions using dynamic contrast-enhanced (DCE) images for reference. Evaluation times for all assessments were automatically recorded. Results were analyzed using the visual grading characteristics (VGC) and the resulting area under the curve (AUC_VGC) method. Statistical analysis was performed in SPSS, with McNemar tests, and paired t-tests used for comparison.

RESULTS

No significant differences were detected between the two sequences in image quality (AUC_VGC: 0.398, p = 0.087) and lesion visibility (AUC_VGC: 0.534, p = 0.336) scores. Lesion characteristics (e.g benign and high-risk, versus malignant; small (≤10 mm) vs. larger (>10 mm)) did not result in different image quality or lesion visibility between sequences. Sensitivity (rs-EPI: 72.2% vs. ss-EPImIRBS: 78.5%, p = 0.108) and specificity (70.5% vs. 56.8%, p = 0.210, respectively) were comparable. In both sequences the mean ADC value was higher for benign and high-risk lesions than for malignant lesions (ss-EPI-mIRBS: p = 0.022 and rs-EPI: p = 0.055). On average, ss-EPI-mIRBS resulted in decreased overall reading time by 7.7 s/case (p = 0.067); a reduction of 17%. For malignant lesions, average reading time was significantly shorter using ss-EPI-mIRBS compared to rs-EPI (64.0 s/lesion vs. 75.9 s/lesion, respectively, p = 0.039).

CONCLUSION

Based on this study, the ss-EPI sequence using a b-value of 2000 s/mm² enables for a mIRBS acquisition with quality and lesion conspicuity that is comparable to conventional rs-EPI, but with a decreased reading time.

Abbreviated magnetic resonance imaging in breast cancer: A systematic review of literature

BACKGROUND

: magnetic resonance imaging (MRI) has been increasingly used to study breast cancer for screening high-risk cases, pre-operative staging, and problem-solving because of its high sensitivity. However, its cost-effectiveness is still debated. Thus, the concept of abbreviated MRI (ABB-MRI) protocols was proposed as a possible solution for reducing MRI costs.

PURPOSE

: to investigate the role of the abbreviated MRI protocols in detecting and staging breast cancer.

METHODS

: a systematic search of the literature was carried out in the bibliographic databases: Scopus, PubMed, Medline, and Science Direct.

RESULTS

: forty-one articles were included, which described results of the assessment of fifty-three abbreviated protocols for screening, staging, recurrence assessing, and problem-solving or clarification.

CONCLUSIONS

: the use of ABB-MRI protocols allows reducing the acquisition and reading times, maintaining a high concordance with the final interpretation, in comparison to a complete protocol. However, larger prospective and multicentre trials are necessary to validate the performance in specific clinical environments.

The potential utility of abbreviated breast MRI (FAST MRI) as a tool for breast cancer screening: a systematic review and meta-analysis

AIM

To synthesise evidence comparing abbreviated breast magnetic resonance imaging (abMRI) to full-protocol MRI (fpMRI) in breast cancer screening.

MATERIALS AND METHODS

A systematic search was undertaken in multiple databases. Cohort studies without enrichment, presenting accuracy data of abMRI in screening, for any level of risk (population, moderate, high risk) were included. Level of evidence was assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE). Meta-analyses (bivariate random effects model) were performed for abMRI, with fpMRI and histology from fpMRI-positive cases as reference standard, and with follow-up to symptomatic detection added to the fpMRI. The review also covers evidence comparing abMRI with mammographic techniques.

RESULTS

The title and abstract review retrieved 23 articles. Five studies (six articles) were included (2,763 women, 3,251 screening rounds). GRADE assessment of the evidence was very low because the reference standard was interpreted with knowledge of the index test and biopsy was not obtained for all abMRI positives. The overall sensitivity for abMRI, with fpMRI (and histology for fpMRI positives) as reference standard, was 94.8% (95% confidence interval [CI] 85.5-98.2) and specificity as 94.6% (95% CI: 91.5-96.6). Three studies (1,450 women, 1,613 screening rounds) presented follow-up data, enabling comparison between abMRI and fpMRI. Sensitivities and specificities for abMRI did not differ significantly from those for fpMRI (p=0.83 and p=0.37, respectively).

CONCLUSION

A very low level of evidence suggests abMRI could be accurate for breast cancer screening. Research is required, with follow-up to interval cancer, to determine the effect its use could have on clinical outcome.

Influence of residual fat signal on diffusion kurtosis MRI of suspicious mammography findings

Recent studies showed the potential of diffusion kurtosis imaging (DKI) as a tool for improved classification of suspicious breast lesions. However, in diffusion-weighted imaging of the female breast, sufficient fat suppression is one of the main factors determining the success. In this study, the data of 198 patients examined in two study centres was analysed using standard diffusion and kurtosis evaluation methods and three DKI fitting approaches accounting phenomenologically for fat-related signal contamination of the lesions. Receiver operating characteristic curve analysis showed the highest area under the curve (AUC) for the method including fat correction terms (AUC = 0.85, p < 0.015) in comparison to the values obtained with the standard diffusion (AUC = 0.77) and kurtosis approach (AUC = 0.79). Comparing the two study centres, the AUC value improved from 0.77 to 0.86 (p = 0.036) using a fat correction term for the first centre, while no significant difference with no adverse effects was observed for the second centre (AUC 0.89 vs. 0.90, p = 0.95). Contamination of the signal in breast lesions with unsuppressed fat causing a reduction of diagnostic performance of diffusion kurtosis imaging may potentially be counteracted by proposed adapted evaluation methods.

Diffusion-weighted MRI at 3.0 T for detection of occult disease in the contralateral breast in women with newly diagnosed breast cancer

PURPOSE

Diffusion-weighted magnetic resonance imaging (DW-MRI) offers unenhanced method to detect breast cancer without cost and safety concerns associated with dynamic contrast-enhanced (DCE) MRI. Our purpose was to evaluate the performance of DW-MRI at 3.0T in detection of clinically and mammographically occult contralateral breast cancer in patients with unilateral breast cancer.

METHODS

Between 2017 and 2018, 1130 patients (mean age 53.3 years; range 26-84 years) with newly diagnosed unilateral breast cancer who underwent breast MRI and had no abnormalities on clinical and mammographic examinations of contralateral breast were included. Three experienced radiologists independently reviewed DW-MRI (b = 0 and 1000 s/mm²) and DCE-MRI and assigned a BI-RADS category. Using histopathology or 1-year clinical follow-up, performance measures of DW-MRI were compared with DCE-MRI.

RESULTS

A total of 21 (1.9%, 21/1130) cancers were identified (12 ductal carcinoma in situ and 9 invasive ductal carcinoma; mean invasive tumor size, 8.0 mm) in the contralateral breast. Cancer detection rate of DW-MRI was 13-15 with mean of 14 per 1000 examinations (95% confidence interval [CI] 9-23 per 1000 examinations), which was lower than that of DCE-MRI (18-19 with mean of 18 per 1000 examinations, P = 0.01). A lower abnormal interpretation rate (14.0% versus 17.0%, respectively, P < 0.001) with higher specificity (87.3% versus 84.6%, respectively, P < 0.001) but lower sensitivity (77.8% versus 96.8%, respectively, P < 0.001) was noted for DW-MRI compared to DCE-MRI.

CONCLUSIONS

DW-MRI at 3.0T has the potential as a cost-effective tool for evaluation of contralateral breast in women with newly diagnosed breast cancer.

Clinical MR Biomarkers

Non-invasive magnetic resonance imaging (MRI) techniques are increasingly applied in the clinic with a fast growing body of evidence regarding its value for clinical decision making. In contrast to biochemical or histological markers, the key advantages of imaging biomarkers are the non-invasive nature and the spatial and temporal resolution of these approaches. The following chapter focuses on clinical applications of novel MR biomarkers in humans with a strong focus on oncologic diseases. These include both clinically established biomarkers (part 1-4) and novel MRI techniques that recently demonstrated high potential for clinical utility (part 5-7).

Molecular Subtypes Recognition of Breast Cancer in Dynamic Contrast-Enhanced Breast Magnetic Resonance Imaging Phenotypes from Radiomics Data

Background and Objective

Breast cancer is a major cause of mortality among women if not treated in early stages. Recognizing molecular markers from DCE-MRI directly to distinguish the four molecular subtypes without invasive biopsy is helpful for guiding treatment plans for breast cancer, which provides a fast way to consequential treatment plan decision in early time and best opportunity for patients.

Methods

This study presents an approach of molecular subtypes recognition from breast cancer image phenotypes by radiomics. An improved region growth algorithm with dynamic threshold without user interaction is proposed for cancer lesion segmentation, which gives the precise border of lesion other than area with background. The lesions are extracted automatically based on radiologists' annotation which guarantees the lesion is segmented correctly. Various features are extracted on lesions data including texture, morphology, dynamic kinetics, and statistics features carried out on a large patient cohort, which are used to validate the relationship between image phenotypes and the molecular subtypes. A new algorithm of multimodel-based recursive feature elimination is applied on the radiomics data generated by the feature extraction process. This method obtains the feature subset with stable performance for different classification models, and the gradient boosting decision tree model gets the best results of both classification performance and imbalance performance on molecular subtypes.

Result

From the experimental results, 69 optimal features from 143 original features are found by the multimodel-based recursive feature elimination algorithms and the gradient boosting decision tree classifier obtains a good performance with accuracy 0.87, precise 0.88, recall 0.87, and F1-score 0.87. The dataset with 637 patients in this paper has serious imbalance problem on different molecular subtypes, and the the robust features that are generated by multimodel-based recursive feature eliminiation algorithm make the gradient boosting decision tree classifier have good behaviors. The recognition precision for the four molecular subtypes of luminal A, luminal B, HER-2, and basal-like are 0.91, 0.89, 0.83, and 0.87, respectively.

Conclusions

The improved lesion segmentation method gives more precise lesion edge, which not only saves the time of automatic extraction of lesion region of interest without threshold setting for each case, but also prevents the segmentation error by manual and prejudice from different radiologists. The feature selection algorithm of multimodel-based recursive feature elimination has the ability to find robust and optimal features that distinguish the four molecular subtypes from image phenotypes. The gradient boosting decision tree classifier rather plays a main role in recognition than other models used in this paper.

Diffusion-Weighted Imaging With Apparent Diffusion Coefficient Mapping for Breast Cancer Detection as a Stand-Alone Parameter: Comparison With Dynamic Contrast-Enhanced and Multiparametric Magnetic Resonance Imaging

PURPOSE

The aims of this study were to compare dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) with diffusion-weighted imaging (DWI) with apparent diffusion coefficient mapping as a stand-alone parameter without any other supportive sequence for breast cancer detection and to assess its combination as multiparametric MRI (mpMRI) of the breast.

MATERIALS AND METHODS

In this institutional review board-approved single-center study, prospectively acquired data of 106 patients who underwent breast MRI from 12/2010 to 09/2014 for an imaging abnormality (Breast Imaging Reporting and Data System 0, 4/5) were retrospectively analyzed. Four readers independently assessed DWI and DCE as well as combined as mpMRI. Breast Imaging Reporting and Data System categories, lesion size, and mean apparent diffusion coefficient values were recorded. Histopathology was used as the gold standard. Appropriate statistical tests were used to compare diagnostic values.

RESULTS

There were 69 malignant and 41 benign tumors in 106 patients. Four patients presented with bilateral lesions. Dynamic contrast-enhanced MRI was the most sensitive test for breast cancer detection, with an average sensitivity of 100%. Diffusion-weighted imaging alone was less sensitive (82%; P < 0.001) but more specific than DCE-MRI (86.8% vs 76.6%; P = 0.002). Diagnostic accuracy was 83.7% for DWI and 90.6% for DCE-MRI. Multiparametric MRI achieved a sensitivity of 96.8%, not statistically different from DCE-MRI (P = 0.12) and with a similar specificity as DWI (83.8%; P = 0.195), maximizing diagnostic accuracy to 91.9%. There was almost perfect interreader agreement for DWI (κ = 0.864) and DCE-MRI (κ = 0.875) for differentiation of benign and malignant lesions.

CONCLUSION

Dynamic contrast-enhanced MRI is most sensitive for breast cancer detection and thus still indispensable. Multiparametric MRI using DCE-MRI and DWI maintains a high sensitivity, increases specificity, and maximizes diagnostic accuracy, often preventing unnecessary breast biopsies. Diffusion-weighted imaging should not be used as a stand-alone parameter because it detects significantly fewer cancers in comparison with DCE-MRI and mpMRI.

Diffusion-weighted breast imaging

Magnetic resonance imaging (MRI) of the breast represents one of the most sensitive imaging modalities in breast cancer detection. Diffusion-weighted imaging (DWI) is a sequence variation introduced as a complementary MRI technique that relies on mapping the diffusion process of water molecules thereby providing additional information about the underlying tissue. Since water diffusion is more restricted in most malignant tumors than in benign ones owing to the higher cellularity of the rapidly proliferating neoplasia, DWI has the potential to contribute to the identification and characterization of suspicious breast lesions. Thus, DWI might increase the diagnostic accuracy of breast MRI and its clinical value. Future applications including optimized DWI sequences, technical developments in MR devices, and the application of radiomics/artificial intelligence algorithms may expand the potential of DWI in breast imaging beyond its current supplementary role.

Radiomics Based on Adapted Diffusion Kurtosis Imaging Helps to Clarify Most Mammographic Findings Suspicious for Cancer

Purpose To evaluate a radiomics model of Breast Imaging Reporting and Data System (BI-RADS) 4 and 5 breast lesions extracted from breast-tissue-optimized kurtosis magnetic resonance (MR) imaging for lesion characterization by using a sensitivity threshold similar to that of biopsy. Materials and Methods This institutional study included 222 women at two independent study sites (site 1: training set of 95 patients; mean age ± standard deviation, 58.6 years ± 6.6; 61 malignant and 34 benign lesions; site 2: independent test set of 127 patients; mean age, 58.2 years ± 6.8; 61 malignant and 66 benign lesions). All women presented with a finding suspicious for cancer at x-ray mammography (BI-RADS 4 or 5) and an indication for biopsy. Before biopsy, diffusion-weighted MR imaging (b values, 0-1500 sec/mm²) was performed by using 1.5-T imagers from different MR imaging vendors. Lesions were segmented and voxel-based kurtosis fitting adapted to account for fat signal contamination was performed. A radiomics feature model was developed by using a random forest regressor. The fixed model was tested on an independent test set. Conventional interpretations of MR imaging were also assessed for comparison. Results The radiomics feature model reduced false-positive results from 66 to 20 (specificity 70.0% [46 of 66]) at the predefined sensitivity of greater than 98.0% [60 of 61] in the independent test set, with BI-RADS 4a and 4b lesions benefiting from the analysis (specificity 74.0%, [37 of 50]; 60.0% [nine of 15]) and BI-RADS 5 lesions showing no added benefit. The model significantly improved specificity compared with the median apparent diffusion coefficient (P < .001) and apparent kurtosis coefficient (P = .02) alone. Conventional reading of dynamic contrast material-enhanced MR imaging provided sensitivity of 91.8% (56 of 61) and a specificity of 74.2% (49 of 66). Accounting for fat signal intensity during fitting significantly improved the area under the curve of the model (P = .001). Conclusion A radiomics model based on kurtosis diffusion-weighted imaging performed by using MR imaging machines from different vendors allowed for reliable differentiation between malignant and benign breast lesions in both a training and an independent test data set. ^© RSNA, 2018 Online supplemental material is available for this article.