An artificial intelligence system using maximum intensity projection MR images facilitates classification of non-mass enhancement breast lesions

A Machine Learning Model for Predicting the HER2 Positive Expression of Breast Cancer Based on Clinicopathological and Imaging Features

RATIONALE AND OBJECTIVES

To develop a machine learning (ML) model based on clinicopathological and imaging features to predict the Human Epidermal Growth Factor Receptor 2 (HER2) positive expression (HER2-p) of breast cancer (BC), and to compare its performance with that of a logistic regression (LR) model.

MATERIALS AND METHODS

A total of 2541 consecutive female patients with pathologically confirmed primary breast lesions were enrolled in this study. Based on chronological order, 2034 patients treated between January 2018 and December 2022 were designated as the retrospective development cohort, while 507 patients treated between January 2023 and May 2024 were designated as the prospective validation cohort. The patients were randomly divided into a train cohort (n=1628) and a test cohort (n=406) in an 8:2 ratio within the development cohort. Pretreatment mammography (MG) and breast MRI data, along with clinicopathological features, were recorded. Extreme Gradient Boosting (XGBoost) in combination with Artificial Neural Network (ANN) and multivariate LR analyses were employed to extract features associated with HER2 positivity in BC and to develop an ANN model (using XGBoost features) and an LR model, respectively. The predictive value was assessed using a receiver operating characteristic (ROC) curve.

RESULTS

Following the application of Recursive Feature Elimination with Cross-Validation (RFE-CV) for feature dimensionality reduction, the XGBoost algorithm identified tumor size, suspicious calcifications, Ki-67 index, spiculation, and minimum apparent diffusion coefficient (minimum ADC) as key feature subsets indicative of HER2-p in BC. The constructed ANN model consistently outperformed the LR model, achieving the area under the curve (AUC) of 0.853 (95% CI: 0.837-0.872) in the train cohort, 0.821 (95% CI: 0.798-0.853) in the test cohort, and 0.809 (95% CI: 0.776-0.841) in the validation cohort.

CONCLUSION

The ANN model, built using the significant feature subsets identified by the XGBoost algorithm with RFE-CV, demonstrates potential in predicting HER2-p in BC.

A novel radiomics-based technique for identifying vulnerable coronary plaques: a follow-up study

BACKGROUND

Previous reports have suggested that coronary computed tomography angiography (CCTA)-based radiomics analysis is a potentially helpful tool for assessing vulnerable plaques. We aimed to investigate whether coronary radiomic analysis of CCTA images could identify vulnerable plaques in patients with stable angina pectoris.

METHODS

This retrospective study included patients initially diagnosed with stable angina pectoris. Patients were randomly divided into either the training or test dataset at an 8 : 2 ratio. Radiomics features were extracted from CCTA images. Radiomics models for predicting vulnerable plaques were developed using the support vector machine (SVM) algorithm. The model performance was assessed using the area under the curve (AUC); the accuracy, sensitivity, and specificity were calculated to compare the diagnostic performance using the two cohorts.

RESULTS

A total of 158 patients were included in the analysis. The SVM radiomics model performed well in predicting vulnerable plaques, with AUC values of 0.977 and 0.875 for the training and test cohorts, respectively. With optimal cutoff values, the radiomics model showed accuracies of 0.91 and 0.882 in the training and test cohorts, respectively.

CONCLUSION

Although further larger population studies are necessary, this novel CCTA radiomics model may identify vulnerable plaques in patients with stable angina pectoris.

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.

A clinicopathological-imaging nomogram for the prediction of pathological complete response in breast cancer cases administered neoadjuvant therapy

OBJECTIVE

To construct a user-friendly nomogram with MRI and clinicopathological parameters for the prediction of pathological complete response (pCR) after neoadjuvant therapy (NAT) in patients with breast cancer (BC).

METHODS

We retrospectively enrolled consecutive female patients pathologically confirmed with breast cancer who received NAT followed by surgery between January 2018 and December 2022 as the development cohort. Additionally, we prospectively collected eligible candidates between January 2023 and December 2023 as an external validation group at our institution. Pretreatment MRI features and clinicopathological variables were collected, and the pre- and post-treatment background parenchymal enhancement (BPE) and the changes in BPE on two MRIs were compared between patients who achieved pCR and those who did not. Multivariable logistic regression analysis was used to identify independent variables associated with pCR in the development cohort. These independent variables were combined into a predictive nomogram for which performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration plot, decision curve analysis, and external validation.

RESULTS

In the development cohort, there were a total of 276 female patients with a mean age of 48.3 ± 8.7 years, while in the validation cohort, there were 87 female patients with a mean age of 49.0 ± 9.5 years. Independent prognostic factors of pCR included small tumor size, HER2(+), high Ki-67 index,high signal enhancement ratio (SER), low minimum value of apparent diffusion coefficient (ADCmin), and significantly decreased BPE after NAT(change of BPE). The nomogram, which incorporates the above parameters, demonstrated excellent predictive performance in both the development and external validation cohorts, with AUC values of 0.900 and 0.850, respectively. Additionally, the nomogram showed excellent calibration capacities, as indicated by Hosmer-Lemeshow test p values of 0.508 and 0.423 in the two cohorts. Furthermore, the nomogram provided greater net benefits compared to the default simple schemes in both cohorts.

CONCLUSION

A nomogram constructed using tumor size, HER2 status, Ki-67 index, SER, ADCmin, and changes in pre- and post-NAT BPE demonstrated strong predictive performance, calibration ability, and greater net benefits for predicting pCR in patients with BC after NAT. This suggests that the user-friendly nomogram could be a valuable imaging biomarker for identifying suitable candidates for NAT.

Differentiation of Malignancy and Idiopathic Granulomatous Mastitis Presenting as Non-mass Lesions on MRI: Radiological, Clinical, Radiomics, and Clinical-Radiomics Models

RATIONALE AND OBJECTIVES

To investigate the effectiveness of machine learning-based clinical, radiomics, and combined models in differentiating idiopathic granulomatous mastitis (IGM) from malignancy, both presenting as non-mass enhancement (NME) lesions on magnetic resonance imaging (MRI), and to compare these models with radiological evaluation.

MATERIAL AND METHODS

A total of 178 patients (69 IGM and 109 breast cancer patients) with NME on breast MRI evaluated between March 2018 and April 2022, were included in this two-center study. Age, skin changes, presence of fistula, and abscess were recorded from hospital records. Two experienced radiologists evaluated MRI images according to the breast imaging reporting and data system 2013 lexicon. Lesions were segmented independently on T2-weighted, apparent diffusion coefficient, and post-contrast-T1-weighted sequences. Data were split into training and external testing sets. Machine learning models were built using Light GBM (light gradient-boosting machine). Radiological, clinical, radiomics, and clinical-radiomics models were created and compared. Decision curve analysis was performed. Quality of reporting and that of methodology were evaluated using CLEAR and METRICS tools.

RESULTS

IGM group was younger (p = 0.014). Abscesses (p < 0.001), fistulas (p < 0.001), and skin changes (p < 0.001) were significantly more common in the IGM group. No significant difference was detected in terms of lesion size (p = 0.213). In the evaluation of NME, the lowest performance belonged to the radiologists' evaluation (AUC for training, 0.740; for testing, 0.737), while the highest AUC was achieved by the model developed by combined clinical and radiomics features (AUC for training, 0.979; for testing, 0.942).

CONCLUSION

Our study has shown that the machine learning-based clinical-radiomics model might have the potential to accurately discriminate IGM and malignant lesions in evaluating NME areas.

Smart forecasting of artifacts in contrast-enhanced breast MRI before contrast agent administration

OBJECTIVES

To evaluate whether artifacts on contrast-enhanced (CE) breast MRI maximum intensity projections (MIPs) might already be forecast before gadolinium-based contrast agent (GBCA) administration during an ongoing examination by analyzing the unenhanced T1-weighted images acquired before the GBCA injection.

MATERIALS AND METHODS

This IRB-approved retrospective analysis consisted of n = 2884 breast CE MRI examinations after intravenous administration of GBCA, acquired with n = 4 different MRI devices at different field strengths (1.5 T/3 T) during clinical routine. CE-derived subtraction MIPs were used to conduct a multi-class multi-reader evaluation of the presence and severity of artifacts with three independent readers. An ensemble classifier (EC) of five DenseNet models was used to predict artifacts for the post-contrast subtraction MIPs, giving as the input source only the pre-contrast T1-weighted sequence. Thus, the acquisition directly preceded the GBCA injection. The area under ROC (AuROC) and diagnostics accuracy scores were used to assess the performance of the neural network in an independent holdout test set (n = 285).

RESULTS

After majority voting, potentially significant artifacts were detected in 53.6% (n = 1521) of all breast MRI examinations (age 49.6 ± 12.6 years). In the holdout test set (mean age 49.7 ± 11.8 years), at a specificity level of 89%, the EC could forecast around one-third of artifacts (sensitivity 31%) before GBCA administration, with an AuROC = 0.66.

CONCLUSION

This study demonstrates the capability of a neural network to forecast the occurrence of artifacts on CE subtraction data before the GBCA administration. If confirmed in larger studies, this might enable a workflow-blended approach to prevent breast MRI artifacts by implementing in-scan personalized predictive algorithms.

CLINICAL RELEVANCE STATEMENT

Some artifacts in contrast-enhanced breast MRI maximum intensity projections might be predictable before gadolinium-based contrast agent injection using a neural network.

KEY POINTS

• Potentially significant artifacts can be observed in a relevant proportion of breast MRI subtraction sequences after gadolinium-based contrast agent administration (GBCA). • Forecasting the occurrence of such artifacts in subtraction maximum intensity projections before GBCA administration for individual patients was feasible at 89% specificity, which allowed correctly predicting one in three future artifacts. • Further research is necessary to investigate the clinical value of such smart personalized imaging approaches.

The features associated with mammography-occult MRI-detected newly diagnosed breast cancer analysed by comparing machine learning models with a logistic regression model

PURPOSE

To compare machine learning (ML) models with logistic regression model in order to identify the optimal factors associated with mammography-occult (i.e. false-negative mammographic findings) magnetic resonance imaging (MRI)-detected newly diagnosed breast cancer (BC).

MATERIAL AND METHODS

The present single-centre retrospective study included consecutive women with BC who underwent mammography and MRI (no more than 45 days apart) for breast cancer between January 2018 and May 2023. Various ML algorithms and binary logistic regression analysis were utilized to extract features linked to mammography-occult BC. These features were subsequently employed to create different models. The predictive value of these models was assessed using receiver operating characteristic curve analysis.

RESULTS

This study included 1957 malignant lesions from 1914 patients, with an average age of 51.64 ± 9.92 years and a range of 20-86 years. Among these lesions, there were 485 mammography-occult BCs. The optimal features of mammography-occult BC included calcification status, tumour size, mammographic density, age, lesion enhancement type on MRI, and histological type. Among the different ML models (ANN, L1-LR, RF, and SVM) and the LR-based combined model, the ANN model with RF features was found to be the optimal model. It demonstrated the best discriminative performance in predicting mammography false- negative findings, with an AUC of 0.912, an accuracy of 86.90%, a sensitivity of 85.85%, and a specificity of 84.18%.

CONCLUSION

Mammography-occult MRI-detected breast cancers have features that should be considered when performing breast MRI to improve the detection rate for breast cancer and aid in clinician management.

Artificial intelligence in breast imaging: potentials and challenges

Breast cancer, which is the most common type of malignant tumor among humans, is a leading cause of death in females. Standard treatment strategies, including neoadjuvant chemotherapy, surgery, postoperative chemotherapy, targeted therapy, endocrine therapy, and radiotherapy, are tailored for individual patients. Such personalized therapies have tremendously reduced the threat of breast cancer in females. Furthermore, early imaging screening plays an important role in reducing the treatment cycle and improving breast cancer prognosis. The recent innovative revolution in artificial intelligence (AI) has aided radiologists in the early and accurate diagnosis of breast cancer. In this review, we introduce the necessity of incorporating AI into breast imaging and the applications of AI in mammography, ultrasonography, magnetic resonance imaging, and positron emission tomography/computed tomography based on published articles since 1994. Moreover, the challenges of AI in breast imaging are discussed.

Use of a deep learning algorithm for non-mass enhancement on breast MRI: comparison with radiologists' interpretations at various levels

PURPOSE

To evaluate the diagnostic performance of deep learning using the Residual Networks 50 (ResNet50) neural network constructed from different segmentations for distinguishing malignant and benign non-mass enhancement (NME) on breast magnetic resonance imaging (MRI) and conduct a comparison with radiologists with various levels of experience.

MATERIALS AND METHODS

A total of 84 consecutive patients with 86 lesions (51 malignant, 35 benign) presenting NME on breast MRI were analyzed. Three radiologists with different levels of experience evaluated all examinations, based on the Breast Imaging-Reporting and Data System (BI-RADS) lexicon and categorization. For the deep learning method, one expert radiologist performed lesion annotation manually using the early phase of dynamic contrast-enhanced (DCE) MRI. Two segmentation methods were applied: a precise segmentation was carefully set to include only the enhancing area, and a rough segmentation covered the whole enhancing region, including the intervenient non-enhancing area. ResNet50 was implemented using the DCE MRI input. The diagnostic performance of the radiologists' readings and deep learning were then compared using receiver operating curve analysis.

RESULTS

The ResNet50 model from precise segmentation achieved diagnostic accuracy equivalent [area under the curve (AUC) = 0.91, 95% confidence interval (CI) 0.90, 0.93] to that of a highly experienced radiologist (AUC = 0.89, 95% CI 0.81, 0.96; p = 0.45). Even the model from rough segmentation showed diagnostic performance equivalent to a board-certified radiologist (AUC = 0.80, 95% CI 0.78, 0.82 vs. AUC = 0.79, 95% CI 0.70, 0.89, respectively). Both ResNet50 models from the precise and rough segmentation exceeded the diagnostic accuracy of a radiology resident (AUC = 0.64, 95% CI 0.52, 0.76).

CONCLUSION

These findings suggest that the deep learning model from ResNet50 has the potential to ensure accuracy in the diagnosis of NME on breast MRI.

Breast Cancer Growth on Serial MRI: Volume Doubling Time Based on 3-Dimensional Tumor Volume Assessment

BACKGROUND

The volume doubling time (VDT) of breast cancer was most frequently calculated using the two-dimensional (2D) diameter, which is not reliable for irregular tumors. It was rarely investigated using three-dimensional (3D) imaging with tumor volume on serial magnetic resonance imaging (MRI).

PURPOSE

To investigate the VDT of breast cancer using 3D tumor volume assessment on serial breast MRIs.

STUDY TYPE

Retrospective.

SUBJECTS

Sixty women (age at diagnosis: 57 ± 10 years) with breast cancer, assessed by two or more breast MRI examinations. The median interval time was 791 days (range: 70-3654 days).

FIELD STRENGTH/SEQUENCE

3-T, fast spin-echo T2-weighted imaging (T2WI), single-shot echo-planar diffusion-weighted imaging (DWI), and gradient echo dynamic contrast-enhanced imaging.

ASSESSMENT

Three radiologists independently reviewed the morphological, DWI, and T2WI features of lesions. The whole tumor was segmented to measure the volume on contrast-enhanced images. The exponential growth model was fitted in the 11 patients with at least three MRI examinations. The VDT of breast cancer was calculated using the modified Schwartz equation.

STATISTICAL TESTS

Mann-Whitney U test, Kruskal-Wallis test, Chi-squared test, intraclass correlation coefficients, and Fleiss kappa coefficients. A P-value <0.05 was considered statistically significant. The exponential growth model was evaluated using the adjusted R2 and root mean square error (RMSE).

RESULTS

The median tumor diameter was 9.7 mm and 15.2 mm on the initial and final MRI, respectively. The median adjusted R2 and RMSE of the 11 exponential models were 0.97 and 15.8, respectively. The median VDT was 540 days (range: 68-2424 days). For invasive ductal carcinoma (N = 33), the median VDT of the non-luminal type was shorter than that of the luminal type (178 days vs. 478 days). On initial MRI, breast cancer manifesting as a focus or mass lesion showed a shorter VDT than that of a non-mass enhancement (NME) lesion (median VDT: 426 days vs. 665 days).

DATA CONCLUSION

A shorter VDT was observed in breast cancer manifesting as focus or mass as compared to an NME lesion.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

The auxiliary diagnosis of thyroid echogenic foci based on a deep learning segmentation model: A two-center study

OBJECTIVE

The aim of this study is to develop AI-assisted software incorporating a deep learning (DL) model based on static ultrasound images. The software aims to aid physicians in distinguishing between malignant and benign thyroid nodules with echogenic foci and to investigate how the AI-assisted DL model can enhance radiologists' diagnostic performance.

METHODS

For this retrospective study, a total of 2724 ultrasound (US) scans were collected from two independent institutions, encompassing 1038 echogenic foci nodules. All echogenic foci were confirmed by pathology. Three DL segmentation models (DeepLabV3+, U-Net, and PSPNet) were developed, with each model using two different backbones to extract features from the nodular regions with echogenic foci. Evaluation indexes such as Mean Intersection over Union (MIoU), Mean Pixel Accuracy (MPA), and Dice coefficients were employed to assess the performance of the segmentation model. The model demonstrating the best performance was selected to develop the AI-assisted diagnostic software, enabling radiologists to benefit from AI-assisted diagnosis. The diagnostic performance of radiologists with varying levels of seniority and beginner radiologists in assessing high-echo nodules was then compared, both with and without the use of auxiliary strategies. The area under the receiver operating characteristic curve (AUROC) was used as the primary evaluation index, both with and without the use of auxiliary strategies.

RESULTS

In the analysis of Institution 2, the DeepLabV3+ (backbone is MobileNetV2 exhibited optimal segmentation performance, with MIoU = 0.891, MPA = 0.945, and Dice = 0.919. The combined AUROC (0.693 [95% CI 0.595-0.791]) of radiology beginners using AI-assisted strategies was significantly higher than those without such strategies (0.551 [0.445-0.657]). Additionally, the combined AUROC of junior physicians employing adjuvant strategies improved from 0.674 [0.574-0.774] to 0.757 [0.666-0.848]. Similarly, the combined AUROC of senior physicians increased slightly, rising from 0.745 [0.652-0.838] to 0.813 [0.730-0.896]. With the implementation of AI-assisted strategies, the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of both senior physicians and beginners in the radiology department underwent varying degrees of improvement.

CONCLUSIONS

This study demonstrates that the DL-based auxiliary diagnosis model using US static images can improve the performance of radiologists and radiology students in identifying thyroid echogenic foci.

Diagnostic value of Kaiser score combined with breast vascular assessment from breast MRI for the characterization of breast lesions

Objectives

The Kaiser scoring system for breast magnetic resonance imaging is a clinical decision-making tool for diagnosing breast lesions. However, the Kaiser score (KS) did not include the evaluation of breast vascularity. Therefore, this study aimed to use KS combined with breast vascular assessment, defined as KS^*, and investigate the effectiveness of KS^* in differentiating benign from malignant breast lesions.

Methods

This retrospective study included 223 patients with suspicious breast lesions and pathologically verified results. The histopathological diagnostic criteria were according to the fifth edition of the WHO classification of breast tumors. The KS^* was obtained after a joint evaluation combining the original KS and breast vasculature assessment. The receiver operating characteristic (ROC) curve was used for comparing differences in the diagnostic performance between KS^* and KS, and the area under the receiver operating characteristic (AUC) was compared.

Results

There were 119 (53.4%) benign and 104 (46.6%) malignant lesions in total. The overall sensitivity, specificity, and accuracy of increased ipsilateral breast vascularity were 69.2%, 76.5%, and 73.1%, respectively. The overall sensitivity, specificity, and accuracy of AVS were 82.7%, 76.5%, and 79.4%, respectively. For all lesions included the AUC of KS^* was greater than that of KS (0.877 vs. 0.858, P = 0.016). The largest difference in AUC was observed in the non-mass subgroup (0.793 vs. 0.725, P = 0.029).

Conclusion

Ipsilaterally increased breast vascularity and a positive AVS sign were significantly associated with malignancy. KS combined with breast vascular assessment can effectively improve the diagnostic ability of KS for breast lesions, especially for non-mass lesions.

The role of epicardial and pericoronary adipose tissue radiomics in identifying patients with non-ST-segment elevation myocardial infarction from unstable angina

OBJECTIVES

This study aimed to ascertain if the radiomics features of epicardial adipose tissue (EAT) and pericoronary adipose tissue (PCAT) based on coronary computed tomography angiography (CCTA) could identify non-ST-segment elevation myocardial infarction (NSTEMI) from unstable angina (UA).

MATERIALS AND METHODS

This retrospective case-control study included 108 patients with NSTEMI and 108 controls with UA. All patients were separated into training cohort (n = 116), internal validation cohort 1 (n = 50), and internal validation cohort 2 (n = 50) based on the time order of admission. The internal validation cohort 1 used the same scanner and scan parameters as the training cohort, while the internal validation cohort 2 used different canners and scan parameters than the training cohort. The EAT and PCAT radiomics features selected by maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) were adopted to build logistic regression models. Finally, we developed an EAT radiomics model, three vessel-based (right coronary artery [RCA], left anterior descending artery [LAD], and left circumflex artery [LCX]) PCAT radiomics models, and a combined model by combining the three PCAT radiomics models. Discrimination, calibration, and clinical application were employed to assess the performance of all models.

RESULTS

Eight radiomics features of EAT, sixteen of RCA-PCAT, fifteen of LAD-PCAT, and eighteen of LCX-PCAT were selected and used to construct radiomics models. The area under the curves (AUCs) of the EAT, RCA-PCAT, LAD-PCAT, LCX-PCAT and the combined models were 0.708 (95% CI: 0.614-0.802), 0.833 (95% CI:0.759-0.906), 0.720 (95% CI:0.628-0.813), 0.713 (95% CI:0.619-0.807), 0.889 (95% CI:0.832-0.946) in the training cohort, 0.693 (95% CI:0.546-0.840), 0.837 (95% CI: 0.729-0.945), 0.766 (95% CI: 0.625-0.907), 0.675 (95% CI: 0.521-0.829), 0.898 (95% CI: 0.802-0.993) in the internal validation cohort 1, and 0.691 (0.535-0.847), 0.822 (0.701-0.944), 0.760 (0.621-0.899), 0.674 (0.517-0.830), 0.866 (0.769-0.963) in the internal validation cohort 2, respectively.

CONCLUSION

Compared with the RCA-PCAT radiomics model, the EAT radiomics model had a limited ability to discriminate between NSTEMI and UA. The combination of the three vessel-based PCAT radiomics may have the potential to distinguish between NSTEMI and UA.

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.