MRI in the Assessment of BI-RADS® 4 lesions

Diagnostic performance of Kaiser score in the evaluation of breast cancer using MRI: A systematic review and meta-analysis

PURPOSE

To assess the performance of Kaiser score (KS) in detecting and characterizing breast cancer on magnetic resonance imaging (MRI).

METHODS

The protocol was pre-registered at (https://osf.io/83c6j/). We performed a comprehensive search in PubMed, Embase, Cochrane Library, and Web of Science until 30 October 2024 for studies that used KS for detection of breast cancer on MRI. The risk of bias in the included studies was evaluated utilizing Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Diagnostic values of area under the curve (AUC), sensitivity, specificity, positive and negative likelihood ratios, and diagnostic odds ratio were calculated using a random-effects bivariate model. Meta-regression was used to explore the source of heterogeneity when I2 was ≥ 50 %. P-value < 0.05 was considered statistically significant.

RESULTS

A total of 29 studies with 7918 patients and 8451 breast lesions were included. The pooled sensitivity, specificity, and AUC of KS for detecting malignant breast lesions on MRI were 95 % (95 % CI = 94 % to 96 %), 70 % (95 % CI = 64 % to 75 %), and 0.94 (95 % CI = 0.91 to 0.96), while for Breast Imaging Reporting and Data System (BI-RADS), they were 97 % (95 % CI = 92 % to 99 %), 46 % (95 % CI = 30 % to 62 %), and 0.89 (95 % CI = 0.86 to 0.91). Sensitivity difference was not statistically significant (p-value = 0.803), but specificity difference was significant (p-value = 0.001). Also, KS demonstrated slightly better diagnostic accuracy for mass lesions with a sensitivity of 96 % (95 % CI = 94 % to 97 %), specificity of 69 % (95 % CI = 60 % to 77 %), and AUC of 0.96 (95 % CI = 0.94 to 0.97) compared to non-mass lesions with 93 % (95 % CI = 88 % to 96 %), 68 % (95 % CI = 58 % to 77 %), and 0.91 (95 % CI = 0.88 to 0.94) values, respectively. KS showed better performance in larger lesions.

CONCLUSION

The KS's superior diagnostic performance compared to BI-RADS, particularly its ability to avoid unnecessary biopsies, makes it valuable for diagnostic and clinical decision-making.

Ultrafast Breast MRI: A Narrative Review

Breast magnetic resonance imaging (MRI) is considered the most effective method for detecting breast cancer due to its high sensitivity. Yet multiple factors limit its widespread use, including high direct and indirect costs, a prolonged acquisition time with consequent patient discomfort, and a lack of trained radiologists. During the last decade, new strategies have been followed to increase the availability of breast MRI, including the omission of non-essential sequences to generate abbreviated MRI protocols (AB-MRIs) aimed at reducing the acquisition time with the potential of improving the patient's experience and accommodating a higher number of MRI examinations per day. An alternative method is ultrafast MRI (UF-MRI), a novel technique that gathers kinetic data within the first minute after contrast injection, offering high temporal resolution. This enables the analysis of early contrast wash-in curves, showing promising outcomes. In this study, we reviewed the role of UF-MRI in breast imaging and detailed how the integration of this new approach with radiomics and mathematical models might further improve diagnostic accuracy and even have a prognostic role, a fundamental characteristic in the modern scenarios of personalized medicine. In addition, possible clinical applications and advantages of UF-MRI will be discussed.

Combination of ultrafast dynamic contrast-enhanced MRI-based radiomics and artificial neural network in assessing BI-RADS 4 breast lesions: Potential to avoid unnecessary biopsies

Objectives

To investigate whether combining radiomics extracted from ultrafast dynamic contrast-enhanced MRI (DCE-MRI) with an artificial neural network enables differentiation of MR BI-RADS 4 breast lesions and thereby avoids false-positive biopsies.

Methods

This retrospective study consecutively included patients with MR BI-RADS 4 lesions. The ultrafast imaging was performed using Differential sub-sampling with cartesian ordering (DISCO) technique and the tenth and fifteenth postcontrast DISCO images (DISCO-10 and DISCO-15) were selected for further analysis. An experienced radiologist used freely available software (FAE) to perform radiomics extraction. After principal component analysis (PCA), a multilayer perceptron artificial neural network (ANN) to distinguish between malignant and benign lesions was developed and tested using a random allocation approach. ROC analysis was performed to evaluate the diagnostic performance.

Results

173 patients (mean age 43.1 years, range 18-69 years) with 182 lesions (95 benign, 87 malignant) were included. Three types of independent principal components were obtained from the radiomics based on DISCO-10, DISCO-15, and their combination, respectively. In the testing dataset, ANN models showed excellent diagnostic performance with AUC values of 0.915-0.956. Applying the high-sensitivity cutoffs identified in the training dataset demonstrated the potential to reduce the number of unnecessary biopsies by 63.33%-83.33% at the price of one false-negative diagnosis within the testing dataset.

Conclusions

The ultrafast DCE-MRI radiomics-based machine learning model could classify MR BI-RADS category 4 lesions into benign or malignant, highlighting its potential for future application as a new tool for clinical diagnosis.

Evaluation of the differentiation of benign and malignant breast lesions using synthetic relaxometry and the Kaiser score

Objective

To investigate whether there is added value of quantitative parameters from synthetic magnetic resonance imaging (SyMRI) as a complement to the Kaiser score (KS) to differentiate benign and malignant breast lesions.

Materials and methods

In this single-institution study, 122 patients who underwent breast MRI from March 2020 to May 2021 were retrospectively analyzed. SyMRI and dynamic contrast-enhanced MRI were performed using a 3.0-T system. Two experienced radiologists independently assigned the KS and measured the quantitative values of T1 relaxation time (T1), T2 relaxation time (T2), and proton density (PD) from SyMRI. Pathology was regarded as the gold standard. The diagnostic values were compared using the appropriate statistical tests.

Results

There were 122 lesions (86 malignant and 36 benign) in 122 women. The T1 value was identified as the only independent factor for the differentiation of malignant and benign lesions. The diagnostic accuracy of incorporating the T1 into the KS protocol (T1+KS) was 95.1% and 92.1% for all lesions (ALL) and The American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions, respectively, which was significantly higher than that of either T1 (ALL: 82.8%, P = 0.0001; BI-RADS 4: 78.9%, P = 0.002) or KS (ALL: 90.2%, P = 0.031; BI-RADS 4: 84.2%, P = 0.031) alone. The sensitivity and specificity of T1+KS were also higher than those of the T1 or KS alone. The combined diagnosis could have avoided another 15.6% biopsies compared with using KS alone.

Conclusions

Incorporating T1 into the KS protocol improved both the sensitivity and specificity to differentiate benign and malignant breast lesions, thus avoiding unnecessary invasive procedures.

Development and validation of a deep learning model for breast lesion segmentation and characterization in multiparametric MRI

Importance

The utilization of artificial intelligence for the differentiation of benign and malignant breast lesions in multiparametric MRI (mpMRI) assists radiologists to improve diagnostic performance.

Objectives

To develop an automated deep learning model for breast lesion segmentation and characterization and to evaluate the characterization performance of AI models and radiologists.

Materials and methods

For lesion segmentation, 2,823 patients were used for the training, validation, and testing of the VNet-based segmentation models, and the average Dice similarity coefficient (DSC) between the manual segmentation by radiologists and the mask generated by VNet was calculated. For lesion characterization, 3,303 female patients with 3,607 pathologically confirmed lesions (2,213 malignant and 1,394 benign lesions) were used for the three ResNet-based characterization models (two single-input and one multi-input models). Histopathology was used as the diagnostic criterion standard to assess the characterization performance of the AI models and the BI-RADS categorized by the radiologists, in terms of sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC). An additional 123 patients with 136 lesions (81 malignant and 55 benign lesions) from another institution were available for external testing.

Results

Of the 5,811 patients included in the study, the mean age was 46.14 (range 11–89) years. In the segmentation task, a DSC of 0.860 was obtained between the VNet-generated mask and manual segmentation by radiologists. In the characterization task, the AUCs of the multi-input and the other two single-input models were 0.927, 0.821, and 0.795, respectively. Compared to the single-input DWI or DCE model, the multi-input DCE and DWI model obtained a significant increase in sensitivity, specificity, and accuracy (0.831 vs. 0.772/0.776, 0.874 vs. 0.630/0.709, 0.846 vs. 0.721/0.752). Furthermore, the specificity of the multi-input model was higher than that of the radiologists, whether using BI-RADS category 3 or 4 as a cutoff point (0.874 vs. 0.404/0.841), and the accuracy was intermediate between the two assessment methods (0.846 vs. 0.773/0.882). For the external testing, the performance of the three models remained robust with AUCs of 0.812, 0.831, and 0.885, respectively.

Conclusions

Combining DCE with DWI was superior to applying a single sequence for breast lesion characterization. The deep learning computer-aided diagnosis (CADx) model we developed significantly improved specificity and achieved comparable accuracy to the radiologists with promise for clinical application to provide preliminary diagnoses.

Combined diagnosis of multiparametric MRI-based deep learning models facilitates differentiating triple-negative breast cancer from fibroadenoma magnetic resonance BI-RADS 4 lesions

PURPOSE

To investigate the value of the combined diagnosis of multiparametric MRI-based deep learning models to differentiate triple-negative breast cancer (TNBC) from fibroadenoma magnetic resonance Breast Imaging-Reporting and Data System category 4 (BI-RADS 4) lesions and to evaluate whether the combined diagnosis of these models could improve the diagnostic performance of radiologists.

METHODS

A total of 319 female patients with 319 pathologically confirmed BI-RADS 4 lesions were randomly divided into training, validation, and testing sets in this retrospective study. The three models were established based on contrast-enhanced T1-weighted imaging, diffusion-weighted imaging, and T2-weighted imaging using the training and validation sets. The artificial intelligence (AI) combination score was calculated according to the results of three models. The diagnostic performances of four radiologists with and without AI assistance were compared with the AI combination score on the testing set. The area under the curve (AUC), sensitivity, specificity, accuracy, and weighted kappa value were calculated to assess the performance.

RESULTS

The AI combination score yielded an excellent performance (AUC = 0.944) on the testing set. With AI assistance, the AUC for the diagnosis of junior radiologist 1 (JR1) increased from 0.833 to 0.885, and that for JR2 increased from 0.823 to 0.876. The AUCs of senior radiologist 1 (SR1) and SR2 slightly increased from 0.901 and 0.950 to 0.925 and 0.975 after AI assistance, respectively.

CONCLUSION

Combined diagnosis of multiparametric MRI-based deep learning models to differentiate TNBC from fibroadenoma magnetic resonance BI-RADS 4 lesions can achieve comparable performance to that of SRs and improve the diagnostic performance of JRs.

XGboost Prediction Model Based on 3.0T Diffusion Kurtosis Imaging Improves the Diagnostic Accuracy of MRI BiRADS 4 Masses

BACKGROUND

The malignant probability of MRI BiRADS 4 breast lesions ranges from 2% to 95%, leading to unnecessary biopsies. The purpose of this study was to construct an optimal XGboost prediction model through a combination of DKI independently or jointly with other MR imaging features and clinical characterization, which was expected to reduce false positive rate of MRI BiRADS 4 masses and improve the diagnosis efficiency of breast cancer.

METHODS

120 patients with 158 breast lesions were enrolled. DKI, Diffusion-weighted Imaging (DWI), Proton Magnetic Resonance Spectroscopy (¹H-MRS) and Dynamic Contrast-Enhanced MRI (DCE-MRI) were performed on a 3.0-T scanner. Wilcoxon signed-rank test and χ2 test were used to compare patient's clinical characteristics, mean kurtosis (MK), mean diffusivity (MD), apparent diffusion coefficient (ADC), total choline (tCho) peak, extravascular extracellular volume fraction (V_e), flux rate constant (K_ep) and volume transfer constant (K^trans). ROC curve analysis was used to analyze the diagnostic performances of the imaging parameters. Spearman correlation analysis was performed to evaluate the associations of imaging parameters with prognostic factors and breast cancer molecular subtypes. The Least Absolute Shrinkage and Selectionator operator (lasso) and the area under the curve (AUC) of imaging parameters were used to select discriminative features for differentiating the breast benign lesions from malignant ones. Finally, an XGboost prediction model was constructed based on the discriminative features and its diagnostic efficiency was verified in BiRADS 4 masses.

RESULTS

MK derived from DKI performed better for differentiating between malignant and benign lesions than ADC, MD, tCho, K_ep and K^trans (p < 0.05). Also, MK was shown to be more strongly correlated with histological grade, Ki-67 expression and lymph node status. MD, MK, age, shape and menstrual status were selected to be the optimized feature subsets to construct an XGboost model, which exhibited superior diagnostic ability for breast cancer characterization and an improved evaluation of suspicious breast tumors in MRI BiRADS 4.

CONCLUSIONS

DKI is promising for breast cancer diagnosis and prognostic factor assessment. An optimized XGboost model that included DKI, age, shape and menstrual status is effective in improving the diagnostic accuracy of BiRADS 4 masses.

A Comparative Assessment of MR BI-RADS 4 Breast Lesions With Kaiser Score and Apparent Diffusion Coefficient Value

Objectives

To investigate the diagnostic performance of the Kaiser score and apparent diffusion coefficient (ADC) to differentiate Breast Imaging Reporting and Data System (BI-RADS) Category 4 lesions at dynamic contrast-enhanced (DCE) MRI.

Methods

This was a single-institution retrospective study of patients who underwent breast MRI from March 2020 to June 2021. All image data were acquired with a 3-T MRI system. Kaiser score of each lesion was assigned by an experienced breast radiologist. Kaiser score+ was determined by combining ADC and Kaiser score. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of Kaiser score+, Kaiser score, and ADC. The area under the curve (AUC) values were calculated and compared by using the Delong test. The differences in sensitivity and specificity between different indicators were determined by the McNemar test.

Results

The study involved 243 women (mean age, 43.1 years; age range, 18-67 years) with 268 MR BI-RADS 4 lesions. Overall diagnostic performance for Kaiser score (AUC, 0.902) was significantly higher than for ADC (AUC, 0.81; p = 0.004). There were no significant differences in AUCs between Kaiser score and Kaiser score+ (p = 0.134). The Kaiser score was superior to ADC in avoiding unnecessary biopsies (p < 0.001). Compared with the Kaiser score alone, the specificity of Kaiser score+ increased by 7.82%, however, at the price of a lower sensitivity.

Conclusion

For MR BI-RADS category 4 breast lesions, the Kaiser score was superior to ADC mapping regarding the potential to avoid unnecessary biopsies. However, the combination of both indicators did not significantly contribute to breast cancer diagnosis of this subgroup.

Value of breast MRI omics features and clinical characteristics in Breast Imaging Reporting and Data System (BI-RADS) category 4 breast lesions: an analysis of radiomics-based diagnosis

Background

The Breast Imaging Reporting and Data System (BI-RADS) category 4 breast lesions is categorized into 4A, 4B, and 4C, which reflect an increasing malignancy potential from low (2–10%) moderate (10–50%) and high (50–95%). Determining the benign and malignant of BI-RADS category 4 breast lesions is very important for accurate diagnosis and follow-up treatment. This study aimed to explore the value of breast magnetic resonance imaging (MRI) omics features and clinical characteristics in the assessment of BI-RADS category 4 breast lesions.

Methods

This retrospective study analyzed 96 lesions (39 benign and 57 malignant) from 92 patients diagnosed with MRI BI-RADS category 4 lesions in the Second Affiliated Hospital of Dalian Medical University between May 2017 and December 2019. The lesions were sub-categorized as BI-RADS 4A, 4B, or 4C based on the MRI findings. An imaging omics analysis model was applied to extract the MRI features. The positive predictive value (PPV) of each subcategory was calculated, and the area under the curve (AUC) was used to describe the efficiency for different diagnoses. Moreover, we analyzed 17 clinical indicators to assess their diagnostic value for BI-RADS category 4 breast lesions.

Results

The PPVs of BI-RADS 4A, 4B, and 4C were 7.1% (2/28), 41.2% (7/17), and 94.1% (48/51), respectively. The AUC, sensitivity, and specificity were 0.919, 84.2%, and 92.3%, respectively. The combination of T₁-weighted images (T₁WI) with dynamic contrast-enhanced (DCE) MRI yielded the best diagnostic results among all dual sequences. Two clinical indicators [progesterone receptor (PR) and Ki-67 expression] achieved an AUC almost equal to 1.0. The radiomics and redundancy reduction methods reduced the clinical data features from 1,233 to 14.

Conclusions

High diagnostic performance can be achieved in distinguishing malignant breast BI-RADS category 4 lesions using the combination of T₁WI and DCE in MRI. Combining the PR and Ki-67 expression variables can further improve MRI accuracy for breast BI-RADS category 4 lesions.

Extraosseous osteoblastoma: A rare cause of breast mass in a prepubertal girl

Extraosseous osteoblastoma of the breast, a rare disease, was diagnosed in a prepubertal girl. After tumor excision, the patient recovered well and an optimal cosmetic result was achieved. Interdisciplinary discussions about the case are essential.

Application of MRI Radiomics-Based Machine Learning Model to Improve Contralateral BI-RADS 4 Lesion Assessment

Objective

This study aimed to explore the potential of magnetic resonance imaging (MRI) radiomics-based machine learning to improve assessment and diagnosis of contralateral Breast Imaging Reporting and Data System (BI-RADS) category 4 lesions in women with primary breast cancer.

Materials and Methods

A total of 178 contralateral BI-RADS 4 lesions (97 malignant and 81 benign) collected from 178 breast cancer patients were involved in our retrospective dataset. T1 + C and T2 weighted images were used for radiomics analysis. These lesions were randomly assigned to the training (n = 124) dataset and an independent testing dataset (n = 54). A three-dimensional semi-automatic segmentation method was performed to segment lesions depicted on T2 and T1 + C images, 1,046 radiomic features were extracted from each segmented region, and a least absolute shrinkage and operator feature selection method reduced feature dimensionality. Three support vector machine (SVM) classifiers were trained to build classification models based on the T2, T1 + C, and fusion image features, respectively. The diagnostic performance of each model was evaluated and tested using the independent testing dataset. The area under the receiver operating characteristic curve (AUC) was used as a performance metric.

Results

The T1+C image feature-based model and T2 image feature-based model yielded AUCs of 0.71 ± 0.07 and 0.69 ± 0.07 respectively, and the difference between them was not significant (P > 0.05). After fusing T1 + C and T2 imaging features, the proposed model’s AUC significantly improved to 0.77 ± 0.06 (P < 0.001). The fusion model yielded an accuracy of 74.1%, which was higher than that of the T1 + C (66.7%) and T2 (59.3%) image feature-based models.

Conclusion

The MRI radiomics-based machine learning model is a feasible method to assess contralateral BI-RADS 4 lesions. T2 and T1 + C image features provide complementary information in discriminating benign and malignant contralateral BI-RADS 4 lesions.

Use of Contrast-Enhanced MRI in Management of Discordant Core Biopsy Results

OBJECTIVE. Evaluating concordance between core biopsy results and imaging findings is an integral component of breast intervention. Pathologic results deemed benign discordant reflect concern that a malignancy may have been incorrectly sampled. Standard of care currently is surgical excision, although a large percentage of these lesions will be benign at final pathologic analysis. The purpose of this study was to determine whether inclusion of contrast-enhanced MRI would optimize patient care. MATERIALS AND METHODS. Forty-five patients with 46 lesions were identified who underwent contrast-enhanced MRI after receiving discordant ultrasound or stereotactic biopsy results between 2012 and mid 2018. These findings were classified BI-RADS category 4 at diagnostic imaging. Disease-positive was defined as all malignancies and borderline lesions. RESULTS. Fourteen patients had suspicious MRI findings; 31 patients did not. Negative or benign MRI findings were validated by stability at imaging follow-up of at least 1 year in 27 patients (28 lesions) and at least 6 months in four patients. Eight of the total of 46 discordant lesions were ultimately malignant, a rate of 17.3%, an expected result for BI-RADS 4 lesions. Sensitivity, specificity, positive predictive value, and negative predictive value of MRI calculated in the group of 41 patients (42 lesions) with documented stability for at least 1 year were 100%, 93.3%, 85.7%, and 100%. The false-negative rate of MRI was 0%; the false-positive rate was 2 of 30 (6.7%). CONCLUSION. In the management of discordant benign core biopsy results, contrast-enhanced MRI facilitated successful triage of patients to surgery; 31 of the original 45 patients (68.9%) avoided surgery.