Imaging Phenotypes in Women at High Risk for Breast Cancer on Mammography, Ultrasound, and Magnetic Resonance Imaging Using the Fifth Edition of the Breast Imaging Reporting and Data System

Development and validation of ultrasound-based radiomics model to predict germline BRCA mutations in patients with breast cancer

BACKGROUND

Identifying breast cancer (BC) patients with germline breast cancer susceptibility gene (gBRCA) mutation is important. The current criteria for germline testing for BC remain controversial. This study aimed to develop a nomogram incorporating ultrasound radiomic features and clinicopathological factors to predict gBRCA mutations in patients with BC.

MATERIALS AND METHODS

In this retrospective study, 497 women with BC who underwent gBRCA genetic testing from March 2013 to May 2022 were included, including 348 for training (84 with and 264 without a gBRCA mutation) and 149 for validation(36 patients with and 113 without a gBRCA mutation). Factors associated with gBRCA mutations were identified to establish a clinicopathological model. Radiomics features were extracted from the intratumoral and peritumoral regions (3 mm and 5 mm) of each image. The least absolute shrinkage and selection operator regression algorithm was used to select the features and logistic regression analysis was used to construct three imaging models. Finally, a nomogram that combined clinicopathological and radiomics features was developed. The models were evaluated based on the area under the receiver operating characteristic curve (AUC), calibration, and clinical usefulness.

RESULTS

Age at diagnosis, family history of BC, personal history of other BRCA-related cancers, and human epidermal growth factor receptor 2 status were independent predictors of the clinicopathological model. The AUC of the imaging radiomics model combining intratumoral and peritumoral 3 mm areas in the validation set was 0.783 (95% confidence interval [CI]: 0.702-0.862), which showed the best performance among three imaging models. The nomogram yielded better performance than the clinicopathological model in validation sets (AUC: 0.824 [0.755-0.894] versus 0.659 [0.563-0.755], p = 0.007).

CONCLUSION

The nomogram based on ultrasound images and clinicopathological factors performs well in predicting gBRCA mutations in BC patients and may help to improve clinical decisions about genetic testing.

Improved Differential Diagnosis Based on BI-RADS Descriptors and Apparent Diffusion Coefficient for Breast Lesions: A Multiparametric MRI Analysis as Compared to Kaiser Score

RATIONALE AND OBJECTIVES

To develop the nomogram utilizing the American College of Radiology BI-RADS descriptors, clinical features, and apparent diffusion coefficient (ADC) to differentiate benign from malignant breast lesions.

MATERIALS AND METHODS

A total of 341 lesions (161 malignant and 180 benign) were included. Clinical data and imaging features were reviewed. Univariable and multivariable logistic regression analyses were performed to determine the independent variables. ADC as a continuous or classified into binary form with a cutoff value of 1.30 × 10-3 mm2/s, incorporated other independent predictors to construct two nomograms, respectively. Receiver operating curve and calibration plot was employed to test the models' discriminative ability. The diagnostic performance between the developed model and the Kaiser score (KS) was also compared.

RESULTS

In both models, high patient age, the presence of root sign, time-intensity curves (TICs) types (plateau and washout), heterogenous internal enhancement, the presence of peritumoral edema, and ADC were independently associated with malignancy. The AUCs of two multivariable models (AUC, 0.957; 95% CI: 0.929-0.976 and AUC, 0.958; 95% CI: 0.931-0.976) were significantly higher than that of the KS (AUC, 0.919, 95% CI: 0.885-0.946; both P < 0.001). At the same sensitivity of 95.7%, our models showed an increase in specificity by 5.56% (P = 0.076) and 6.11% (P = 0.035), respectively, as compared to the KS.

CONCLUSION

The models incorporating MRI features (root sign, TIC, margins, internal enhancement, and presence of edema), quantitative ADC value, and patient age showed improved diagnostic performance and might have avoided more unnecessary biopsies in comparison with the KS, although further external validation is required.

Deep learning for predicting future lesion emergence in high-risk breast MRI screening: a feasibility study

BACKGROUND

International societies have issued guidelines for high-risk breast cancer (BC) screening, recommending contrast-enhanced magnetic resonance imaging (CE-MRI) of the breast as a supplemental diagnostic tool. In our study, we tested the applicability of deep learning-based anomaly detection to identify anomalous changes in negative breast CE-MRI screens associated with future lesion emergence.

METHODS

In this prospective study, we trained a generative adversarial network on dynamic CE-MRI of 33 high-risk women who participated in a screening program but did not develop BC. We defined an anomaly score as the deviation of an observed CE-MRI scan from the model of normal breast tissue variability. We evaluated the anomaly score's association with future lesion emergence on the level of local image patches (104,531 normal patches, 455 patches of future lesion location) and entire CE-MRI exams (21 normal, 20 with future lesion). Associations were analyzed by receiver operating characteristic (ROC) curves on the patch level and logistic regression on the examination level.

RESULTS

The local anomaly score on image patches was a good predictor for future lesion emergence (area under the ROC curve 0.804). An exam-level summary score was significantly associated with the emergence of lesions at any location at a later time point (p = 0.045).

CONCLUSIONS

Breast cancer lesions are associated with anomalous appearance changes in breast CE-MRI occurring before the lesion emerges in high-risk women. These early image signatures are detectable and may be a basis for adjusting individual BC risk and personalized screening.

RELEVANCE STATEMENT

Anomalies in screening MRI preceding lesion emergence in women at high-risk of breast cancer may inform individualized screening and intervention strategies.

KEY POINTS

• Breast lesions are associated with preceding anomalies in CE-MRI of high-risk women. • Deep learning-based anomaly detection can help to adjust risk assessment for future lesions. • An appearance anomaly score may be used for adjusting screening interval times.

Attitudes of Practicing Radiologists Toward the Management of Palpable Circumscribed Breast Masses

OBJECTIVE

To investigate the attitudes of radiologists toward palpable breast masses with benign features on US and to determine the factors influencing their decision.

METHODS

A 20-question online questionnaire was sent to radiologists with membership of the Iranian Society of Radiology and included questions regarding demographics, practice experience, and management approach to palpable circumscribed breast masses based on patient age and risk factors. Radiologists' management choice for masses in themselves or close relatives/friends was also queried.

RESULTS

In total, 151 radiologists participated (response rate 16%). For palpable breast masses with benign imaging features in women at high risk, the majority of radiologists selected MRI (95/151, 62.9%) and core-needle biopsy (110/151, 72.8%). In average-risk patients, radiologists with >5 years of practice experience selected biopsy more frequently (33/79, 41.8%) than less experienced radiologists (17/79, 23.6%) for patients ≥40 years old (P < 0.001) and patients <40 years old (20/79, 25.3%; 11/72, 15.3%, respectively) (P = 0.014). Similarly, selecting biopsy was more common in radiologists who completed a breast imaging fellowship for patients ≥40 years old (23/45, 51.1% vs 27/106, 25.5%) (P = 0.04), as well as for patients <40 years old (18/45, 40% vs 13/106, 12.3%) (P = 0.02). Radiologists who were <40 years old selected biopsy more frequently if evaluating a mass in themselves (22/86, 25.6%) compared to patients (15/86, 17.4%) (P < 0.001).

CONCLUSION

Radiologist experience and educational background, as well as patient baseline breast cancer risk, can predispose radiologists to choose biopsy for palpable breast masses despite a benign appearance on imaging.

Value of contrast-enhanced mammography combined with the Kaiser score for clinical decision-making regarding tomosynthesis BI-RADS 4A lesions

OBJECTIVES

To investigate the diagnostic performance of contrast-enhanced mammography (CEM) combined with the Kaiser score (KS) in digital breast tomosynthesis (DBT) BI-RADS 4A lesions to potentially reduce unnecessary breast biopsies.

METHODS

This retrospective study evaluated 106 patients with 109 DBT BI-RADS 4A lesions from June 2019 to June 2021. For the absence of enhancement on CEM, the lesions were downgraded to BI-RADS 3. For lesions with enhancement, the readers were asked to classify all enhancing lesions referring to the KS for breast MRI. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic performance. Two readers rated all cases and interreader agreement was assessed by Cohen's kappa coefficients.

RESULTS

There were ninety-five benign lesions and 14 malignant lesions. CEM combined with KS's accuracy, represented by the area under the curve (AUC), ranged between 0.880 and 0.906. The use of the KS improved the performance, with a significant difference relative to a single BI-RADS reading or US (p < 0.001). CEM with KS had higher specificity than CEM with BI-RADS or US (p < 0.001), without difference in sensitivity (p > 0.05). CEM combined with KS could have potentially obviated 72 (75.8%) to 78 (82.1%) unnecessary benign biopsies in 95 benign lesions previously DBT classified as BI-RADS 4A. The interreader agreement was substantial (kappa: 0.727) for KS.

CONCLUSIONS

CEM combined with KS may be used in DBT BI-RADS 4A lesions to substantially reduce unnecessary benign biopsies.

KEY POINTS

• CEM combined with the Kaiser scoring system shows high diagnostic performance for DBT BI-RADS 4A lesions. • The application of CEM combined with the Kaiser scoring system may avoid 75.8% to 82.1% of unnecessary benign breast biopsies. • CEM combined with the KS aids clinical decision-making in DBT BI-RADS 4A lesions.

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.

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.

Are Mutation Carrier Patients Different from Non-Carrier Patients? Genetic, Pathology, and US Features of Patients with Breast Cancer

The purpose of this study is to evaluate the relationship between the pathogenic/likely pathogenic mutations, US features, and histopathologic findings of breast cancer in mutation carriers compared to non-carrier patients. Methods: In this retrospective study, we identified 264 patients with breast cancer and multigene panel testing admitted to our clinic from January 2018 to December 2020. Patient data US findings, US assessment of the axilla, multigene panel tests, histopathology, and immunochemistry reports were reviewed according to the BI-RADS lexicon. Results: The study population was comprised of 40% pathogenic mutation carriers (BRCA1, BRCA2, CHEK2, ATM, PALB, TP 53, NBN, MSH, BRIP 1 genes) and 60% mutation-negative patients. The mean patient age was 43.5 years in the carrier group and 44 years in the negative group. Carrier patients developed breast cancer with benign morphology (acoustic enhancement, soft elastography appearance) compared to non-carriers (p < 0.05). A tendency towards specific US features was observed for each mutation. BRCA1 carriers were associated with BC with microlobulated margins, hyperechoic rim, and soft elastography appearance (p < 0.05). Estrogen receptor (ER)-negative tumors were associated with BRCA1, TP53, and RAD mutations, while BRCA2 and CHEK2 were associated with ER-positive tumors. Conclusions: Patients with pathogenic mutations may exhibit BC with benign US features compared to negative, non-carrier patients. BRCA1, TP53, and RAD carriers account for up to one third of the ER tumors from the carrier group. Axillary US performed worse in depicting involved lymph nodes in carrier patients, compared to negative patients.

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.

Comparing breast cancer imaging characteristics of CHEK2 with BRCA1 and BRCA2 gene mutation carriers

PURPOSE

Breast cancer gene (BRCA) 1 and 2 mutations are frequently studied gene mutations (GM); the incidence of checkpoint kinase 2 (CHEK2) is increasing. We describe the imaging features of breast cancer (BC) in CHEK2 mutations, compared to BRCA 1 and 2 using mammography, ultrasound (US) and magnetic resonance imaging (MRI).

METHOD

Inclusion criteria were primary BC in GM carriers, treated in the same hospital. Age at diagnosis, histology, hormone receptor and human epidermal growth factor receptor 2 (HER2) status were retrieved. Mammography descriptors were mass, asymmetry and suspicious microcalcifications. The enhancement pattern (MRI), shape and border, architectural distortion, the presence of a hyperechoic rim and cystic complex structure (US) were documented. Analyses were performed using SAS software (version 9.4). Fishers' exact test was used to test associations between two categorical variables.

RESULTS

In 191 women, 233 malignant lesions were diagnosed (78 in BRCA1, 109 in BRCA2, 46 in CHEK2). In CHEK2 carriers, mammographically, suspicious microcalcifications (54%) were more prevalent (BRCA2 (48%) and BRCA1 carriers (33%)) (p-value = 0.057) compared to mass lesions (35%). On US, lesions were most frequently ill-defined (86%) (p = 0.579) and irregular (94.5%) (p = 0.098) compared to BRCA2 (77% and 80% resp.) and BRCA1 carriers (71% and 72% resp.). On MRI, mass lesions showed a type 3 curve in CHEK2 (67%) compared to BRCA1 (36%) and BRCA2 (50%) (p = 0.056).

CONCLUSIONS

Malignant radiological characteristics of breast cancer, more specifically suspicious microcalcifications, were more frequently seen in CHEK2 and BRCA2 compared to BRCA1 mutation carriers (without a significant difference) indicating the importance of mammography in follow-up of CHEK2 carriers.

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

Simple Summary

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

Abstract

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

Comparison of Ultrasound Features With Maximum Standardized Uptake Value Assessed by 18F-Fluorodeoxyglucose-Positron Emission Tomography/Computed Tomography for Prognosis of Estrogen Receptor+/Human Epithelial Growth Factor Receptor 2- Breast Cancer

ABSTRACT

estrogen receptor (ER)+/human epithelial growth factor receptor 2 (HER2)- breast cancers have less aggressive traits and a favorable prognosis when treated early. Prediction of prognosis for treatment outcome or survival in ER+/HER2- cancer is important. Ultrasound (US) is an effective and easy technique for breast cancer diagnosis and tumor characterization. Positron emission tomography/computed tomography (PET/CT) is widely used for diagnosis, staging, and therapeutic response in cancer evaluation, and a high maximum standardized uptake value (SUVmax) is associated with poor prognosis. The study aim was to compare the prognostic value of US features with that of the SUVmax assessed by PET/CT in ER+/HER- breast cancer patients. We retrospectively identified breast cancer patients in our institutional database who had undergone preoperative US and PET/CT, and 96 patients with invasive ductal carcinoma and ductal carcinoma in situ were included in this study. The US features of mass shape, margin, echo pattern, orientation, posterior features, boundary, and calcification in the mass were analyzed. We then analyzed the US features to look for correlations with SUVmax and associations with margins, boundaries, posterior features, histological grade, and ki-67 expression. High SUVmax was correlated with irregular shape, not-circumscribed margin, posterior acoustic enhancement, echogenic halo, and calcification in the mass (P < 0.05, all). Posterior acoustic enhancement was correlated with high ki-67 expression. Many US features of ER+/HER- breast cancer showed associations with SUVmax. Some US features of ER+/HER- breast cancer were useful for predicting prognosis.

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

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

Association between Imaging Features using the BI-RADS and Tumor Subtype in Patients with Invasive Breast Cancer

BACKGROUND

Different molecular breast cancer subtypes present different biologic features, treatment options, and clinical prognoses. The breast cancer imaging phenotype may help precisely classify breast cancer in a non-invasive manner.

OBJECTIVE

To identify the association between the imaging and clinicopathologic features of invasive breast cancer according to the molecular subtype.

METHODS

We retrospectively reviewed the electronic medical records of 313 consecutive women with breast cancer who underwent surgery between March 2018 and February 2019. Preoperative imaging studies were also reviewed and the association between the clinicopathologic and imaging features was evaluated according to the molecular subtype.

RESULTS

On mammography, the presence of microcalcifications was correlated with the human epidermal factor receptor 2-positive subtype (67%, 14/21). Luminal A and B tumors were more likely to have a spiculated margin (57% [63/110] and 41% [34/81]), while human epidermal factor receptor 2-positive and triple-negative breast cancers were more likely to have an indistinct margin (56% [10/18] and 35% [17/48]). On ultrasonography, luminal A tumors were likely to be depicted as masses with an irregular shape (85%, 115/136) and spiculated margin (49%, 66/136). On magnetic resonance imaging, triple-negative breast cancer appeared as a mass (n=13) that frequently had an irregular shape (62%, 8/13) but was more likely to be oval or round (39%, 5/13) than other subtypes.

CONCLUSION

Some imaging features on mammography, ultrasonography, and magnetic resonance imaging could be useful predictors of the molecular subtype of breast cancer and may aid precision medicine development for patients with breast cancer according to the subtype.

Diagnostic value of radiomics and machine learning with dynamic contrast-enhanced magnetic resonance imaging for patients with atypical ductal hyperplasia in predicting malignant upgrade

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.

Improved characterization of sub-centimeter enhancing breast masses on MRI with radiomics and machine learning in BRCA mutation carriers

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.

Electronic supplementary material

The online version of this article (10.1007/s00330-020-06991-7) contains supplementary material, which is available to authorized users.

Screening in patients with increased risk of breast cancer (part 2). Where are we now? Actual MRI screening controversies

For women with a high risk of breast cancer, early detection plays an important role. Due to the high incidence of breast cancer, and at a younger age than in the general population, screening begins earlier, and there is considerable evidence that magnetic resonance is the most sensitive diagnostic tool, and the principal American and European guidelines agree on the recommendation to perform annual magnetic resonance (with supplemental annual mammography) as an optimal mode of screening. In addition to the absence of current consensus on which patients should be included in the recommendation for magnetic resonance screening (widely discussed in the introduction of part 1 of this work), there are other aspects that are different between guidelines, that are not specified, or that are susceptible to change based on the evidence of several years of experience, that we have called «controversies», such as the age to begin screening, the possible advisability of using a different strategy in different subgroups, performing alternate versus synchronous magnetic resonance and mammography, the age at which to terminate the two techniques, or how to follow up after risk reduction surgery.The aim of the second part of the paper is, by reviewing the literature, to provide an update in relation to some of the main «controversies» in high risk screening with magnetic resonance. And finally, based on all this, to propose a possible model of optimal and updated screening protocol.

The Kaiser score reliably excludes malignancy in benign contrast-enhancing lesions classified as BI-RADS 4 on breast MRI high-risk screening exams

OBJECTIVES

MRI is an integral part of breast cancer screening in high-risk patients. We investigated whether the application of the Kaiser score, a clinical decision-support tool, may be used to exclude malignancy in contrast-enhancing lesions classified as BI-RADS 4 on breast MRI screening exams.

METHODS

This retrospective study included 183 consecutive, histologically proven, suspicious (MR BI-RADS 4) lesions detected within our local high-risk screening program. All lesions were evaluated according to the Kaiser score for breast MRI by three readers blinded to the final histopathological diagnosis. The Kaiser score ranges from 1 (lowest, cancer very unlikely) to 11 (highest, cancer very likely) and reflects increasing probabilities of malignancy, with scores greater than 4 requiring biopsy. Receiver operating characteristic (ROC) curve analysis was used to evaluate diagnostic accuracy.

RESULTS

There were 142 benign and 41 malignant lesions, diagnosed in 159 patients (mean age, 43.6 years). Median Kaiser scores ranged between 2 and 5 in benign and 7 and 8 in malignant lesions. For all lesions, the Kaiser score's accuracy, represented by the area under the curve (AUC), ranged between 86.5 and 90.2. The sensitivity of the Kaiser score was high, between 95.1 and 97.6% for all lesions, and was best in mass lesions. Application of the Kaiser score threshold for malignancy (≤ 4) could have potentially avoided 64 (45.1%) to 103 (72.5%) unnecessary biopsies in 142 benign lesions previously classified as BI-RADS 4.

CONCLUSIONS

The use of Kaiser score in high-risk MRI screening reliably excludes malignancy in more than 45% of contrast-enhancing lesions classified as BI-RADS 4.

KEY POINTS

• The Kaiser score shows high diagnostic accuracy in identifying malignancy in contrast-enhancing lesions in patients undergoing high-risk screening for breast cancer. • The application of the Kaiser score may avoid > 45% of unnecessary breast biopsies in high-risk patients. • The Kaiser score aids decision-making in high-risk breast cancer MRI screening programs.

Association between ultrasound findings, tumor type, grade, and biological markers in patients with breast cancer

Background

This prospective study included 65 female patients with primary breast cancer. Ultrasound was performed for all patients. Ultrasound findings were analyzed according to the ACR BI-RADS lexicon 5th edition and correlated with tumor type, grade, and biological markers (ER, PR, HER-2/neu, and Ki67). The purpose of this study is to assess the association between ultrasound findings, tumor type, grade, and the state of biological markers in patients with breast cancer.

Results

Irregular shape and speculated margins are more frequently associated with invasive duct carcinoma than DCIS (p value < 0.001). There were no association between the ultrasound findings (shape, margin, orientation, echopattern, and posterior features) and the tumor grade (p value 1.0, 0, 0.544, 1.0, and 1.0), respectively. Irregular shape is more frequently seen in ER and PR positive breast cancers (p value = 0.036 and 0.026, respectively). Non-circumscribed margins were frequently seen in PR positive breast cancers (p value = 0.068). No statistically significant difference between US descriptors and HER-2/neu-positive cases.

Conclusion

Irregularly shaped tumors with speculated margins are frequently seen in invasive duct carcinoma and also more frequently seen in ER-, PR-, and Ki67-positive cases. No relation between ultrasound descriptors and the tumor grade of invasive duct carcinoma. Also, there were no relation between ultrasound descriptors and the state of HER-2/neu.