MRI features of breast cancer immunophenotypes with a focus on luminal estrogen receptor low positive invasive carcinomas

To compare the magnetic resonance imaging (MRI) features of different immunophenotypes of breast carcinoma of no special type (NST), with special attention to estrogen receptor (ER)-low-positive breast cancer. This retrospective, single-centre, Institutional Review Board (IRB)-approved study included 398 patients with invasive breast carcinoma. Breast carcinomas were classified as ER-low-positive when there was ER staining in 1-10% of tumour cells. Pretreatment MRI was reviewed to assess the tumour imaging features according to the 5th edition of the Breast Imaging Reporting and Data System (BI-RADS) lexicon. Of the 398 cases, 50 (12.6%) were luminal A, 191 (48.0%) were luminal B, 26 (6.5%) were luminal ER-low positive, 64 (16.1%) were HER2-overexpressing, and 67 (16.8%) were triple negative. Correlation analysis between MRI features and tumour immunophenotype showed statistically significant differences in mass shape, margins, internal enhancement and the delayed phase of the kinetic curve. An oval or round shape and rim enhancement were most frequently observed in triple-negative and luminal ER-low-positive tumours. Spiculated margins were most common in luminal A and luminal B tumours. A persistent kinetic curve was more frequent in luminal A tumours, while a washout curve was more common in the triple-negative, HER2-overexpressing and luminal ER-low-positive immunophenotypes. Multinomial regression analysis showed that luminal ER-low-positive tumours had similar results to triple-negative tumours for almost all variables. Luminal ER-low-positive tumours present with similar MRI findings to triple-negative tumours, which suggests that MRI can play a fundamental role in adequate radiopathological correlation and therapeutic planning in these patients.

Ultrafast sequence-based prediction model and nomogram to differentiate additional suspicious lesions on preoperative breast MRI

OBJECTIVES

To investigate whether ultrafast sequence improves the diagnostic performance of conventional dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in differentiating additional suspicious lesions (ASLs) on preoperative breast MRI.

MATERIALS AND METHODS

A retrospective database search identified 668 consecutive patients who underwent preoperative breast DCE-MRI with ultrafast sequence between June 2020 and July 2021. Among these, 107 ASLs from 98 patients with breast cancer (36 multifocal, 42 multicentric, and 29 contralateral) were identified. Clinical, pathological, conventional MRI findings, and ultrafast sequence-derived parameters were collected. A prediction model that adds ultrafast sequence-derived parameters to clinical, pathological, and conventional MRI findings was developed and validated internally. Decision curve analysis and net reclassification index statistics were performed. A nomogram was constructed.

RESULTS

The ultrafast model adding time to peak enhancement, time to enhancement, and maximum slope showed a significantly increased area under the receiver operating characteristic curve compared with the conventional model which includes age, human epidermal growth factor receptor 2 expression of index cancer, size of index cancer, lesion type of index cancer, location of ASL, and size of ASL (0.92 vs. 0.82; p = 0.002). The decision curve analysis showed that the ultrafast model had a higher overall net benefit than the conventional model. The net reclassification index of ultrafast model was 23.3% (p = 0.001).

CONCLUSION

A combination of ultrafast sequence-derived parameters with clinical, pathological, and conventional MRI findings can aid in the differentiation of ASL on preoperative breast MRI.

CLINICAL RELEVANCE STATEMENT

Our prediction model and nomogram that was based on ultrafast sequence-derived parameters could help radiologists differentiate ASLs on preoperative breast MRI.

KEY POINTS

Ultrafast MRI can diminish background parenchymal enhancement and possibly improve diagnostic accuracy for additional suspicious lesions (ASLs). Location of ASL, larger size of ASL, and higher maximum slope were associated with malignant ASL. The ultrafast model and nomogram can help preoperatively differentiate additional malignancies.

Multiparametric MRI-based radiomic nomogram for predicting HER-2 2+ status of breast cancer

Objective

To explore the application of multiparametric MRI-based radiomic nomogram for assessing HER-2 2+ status of breast cancer (BC).

Methods

Patients with pathology-proven HER-2 2+ invasive BC, who underwent preoperative MRI were divided into training (72 patients, 21 HER-2-positive and 51 HER-2-negative) and validation (32 patients, 9 HER-2-positive and 23 HER-2-negative) sets by randomization. All were classified as HER-2 2+ FISH-positive (HER-2-positive) or -negative (HER-2-negative) according to IHC and FISH. The 3D VOI was drawn on MR images by two radiologists. ADC, T2WI, and DCE images were analyzed separately to extract features (n = 1906). L1 regularization, F-test, and other methods were used to reduce dimensionality. Binary radiomics prediction models using features from single or combined imaging sequences were constructed using logistic regression (LR) classifier then and validated on a validation dataset. To build a radiomics nomogram, multivariate LR analysis was conducted to identify independent indicators. An evaluation of the model's predictive efficacy was made using AUC.

Results

On the basis of combined ADC, T2WI, and DCE images, ten radiomic features were extracted following feature dimensionality reduction. There was superior diagnostic efficiency of radiomic signature using all three sequences compared to either one or two sequences (AUC for training group: 0.883; AUC for validation group: 0.816). Based on multivariate LR analysis, radiomic signature and peritumoral edema were independent predictors for identifying HER-2 2 +. In both training and validation datasets, nomograms combining peritumoral edema and radiomics signature demonstrated an effective discrimination (AUCs were respectively 0.966 and 0. 884).

Conclusion

The nomogram that incorporated peritumoral edema and multiparametric MRI-based radiomic signature can be used to effectively predict the HER-2 2+ status of BC.

High Peritumoral and Intratumoral T2 Signal Intensity in HER2-Positive Breast Cancers on Preneoadjuvant Breast MRI: Assessment of Associations With Histopathologic Characteristics

BACKGROUND. Intratumoral necrosis and peritumoral edema are features of aggressive breast cancer that may present as high T2 signal intensity (T2 SI). Implications of high T2 SI in HER2-positive cancers are unclear. OBJECTIVE. The purpose of this study was to assess associations with histopathologic characteristics of high peritumoral T2 SI and intratumoral T2 SI of HER2-positive breast cancer on MRI performed before initiation of neoadjuvant therapy. METHODS. This retrospective study included 210 patients (age, 24-82 years) with 211 HER2 breast cancers who, from January 1, 2015, to July 30, 2022, underwent breast MRI before receiving neoadjuvant therapy. Two radiologists independently assessed cancers for high peritumoral T2 SI and high intratumoral T2 SI on fat-suppressed T2-weighted imaging and classified patterns of high peritumoral T2 SI (adjacent to tumor vs prepectoral extension). A third radiologist resolved discrepancies. Multivariable logistic regression analyses were performed to identify associations of high peritumoral and intratumoral T2 SI with histopathologic characteristics (associated ductal carcinoma in situ, hormone receptor status, histologic grade, lymphovascular invasion, and axillary lymph node metastasis). RESULTS. Of 211 HER2-positive cancers, 81 (38.4%) had high peritumoral T2 SI, and 95 (45.0%) had high intratumoral T2 SI. A histologic grade of 3 was independently associated with high peritumoral T2 SI (OR = 1.90; p = .04). Otherwise, none of the five assessed histopathologic characteristics were independently associated with high intratumoral T2 SI or high peritumoral T2 SI (p > .05). Cancers with high T2 SI adjacent to the tumor (n = 29) and cancers with high T2 SI with prepectoral extension (n = 52) showed no significant difference in frequency for any of the histopathologic characteristics (p > .05). Sensitivities and specificities for predicting the histopathologic characteristics ranged from 35.6% to 43.7% and from 59.7% to 70.7%, respectively, for high peritumoral T2 SI, and from 37.3% to 49.6% and from 49.3% to 62.7%, respectively, for high intratumoral T2 SI. Interreader agreement was almost perfect for high peritumoral T2 SI (Gwet agreement coefficient [AC] = 0.93), high intratumoral T2 SI (Gwet AC = 0.89), and a pattern of high peritumoral T2 SI (Gwet AC = 0.95). CONCLUSION. The only independent association between histopathologic characteristics and high T2 SI of HER2-positive breast cancer was observed between a histologic grade of 3 and high peritumoral T2 SI. CLINICAL IMPACT. In contrast with previously reported findings in broader breast cancer subtypes, peritumoral and intratumoral T2 SI had overall limited utility as prognostic markers of HER2-positive breast cancer.

Multicentricity in Different Molecular Subtypes of Breast Cancer: A Cross-sectional Study in Isfahan

Background

Breast cancer is the most common cancer leading to death in women. Women with multicentric breast cancer were reported more likely to have poor prognosis. Here, we decided to study and compare the frequency distribution of multicentricity in different subtypes of breast cancer.

Materials and Methods

This is a cross-sectional study that was performed in 2019-20 on medical records and breast pathology reports of 250 patients who undergone mastectomy due to breast cancer. Demographic data of all patients including age, along with other medical data such as menstruation condition, breast cancer grade, multicentricity status, stage, and expression of estrogen receptor (ER), progesterone (PR), and human epidermal growth factor receptor 2 (HER2) receptors were collected from medical records. Samples were divided into four subtypes of Luminal B, Luminal A, HER2 expressing, and basal-like.

Results

The mean age of patients was 50.21 ± 11.15 years. Ninety-five patients (38%) had multicentricity and HER2 expressing (48.5%) and Luminal A (41.4%) were most common in patients with multicentricity. In addition, basal-like group presented with least multicentricity (13.5%) among the subtypes (P = 0.008). We also showed significant increased chances of multicentricity in Luminal B (odds ratio [OR] = 3.782) (P = 0.033), Luminal A (OR = 5.164) (P = 0.002), and HER2-expressing group (OR = 5.393) (P = 0.011).

Conclusions

Taken together, we showed significantly increased chances of multicentricity in patients with HER2-expression, Luminal A, and Luminal B groups compared to basal-like group or triple negative. These results were in line with most previous studies; however, we showed higher rates of multicentricity among our population compared to some previous reports.

Staging Breast Cancer with MRI, the T. A Key Role in the Neoadjuvant Setting

Breast cancer (BC) is the most common cancer among women worldwide. Neoadjuvant chemotherapy (NACT) indications have expanded from inoperable locally advanced to early-stage breast cancer. Achieving a pathological complete response (pCR) has been proven to be an excellent prognostic marker leading to better disease-free survival (DFS) and overall survival (OS). Although diagnostic accuracy of MRI has been shown repeatedly to be superior to conventional methods in assessing the extent of breast disease there are still controversies regarding the indication of MRI in this setting. We intended to review the complex literature concerning the tumor size in staging, response and surgical planning in patients with early breast cancer receiving NACT, in order to clarify the role of MRI. Morphological and functional MRI techniques are making headway in the assessment of the tumor size in the staging, residual tumor assessment and prediction of response. Radiomics and radiogenomics MRI applications in the setting of the prediction of response to NACT in breast cancer are continuously increasing. Tailored therapy strategies allow considerations of treatment de-escalation in excellent responders and avoiding or at least postponing breast surgery in selected patients.

Breast Cancer Subtypes and Quantitative Magnetic Resonance Imaging: A Systemic Review

Magnetic resonance imaging (MRI) is the most sensitive imaging modality for breast cancer detection. This systematic review investigated the role of quantitative MRI features in classifying molecular subtypes of breast cancer. We performed a literature search of articles published on the application of quantitative MRI features in invasive breast cancer molecular subtype classification in PubMed from 1 January 2002 to 30 September 2021. Of the 1275 studies identified, 106 studies with a total of 12,989 patients fulfilled the inclusion criteria. Bias was assessed based using the Quality Assessment of Diagnostic Studies. All studies were case-controlled and research-based. Most studies assessed quantitative MRI features using dynamic contrast-enhanced (DCE) kinetic features and apparent diffusion coefficient (ADC) values. We present a summary of the quantitative MRI features and their correlations with breast cancer subtypes. In DCE studies, conflicting results have been reported; therefore, we performed a meta-analysis. Significant differences in the time intensity curve patterns were observed between receptor statuses. In 10 studies, including a total of 1276 lesions, the pooled difference in proportions of type Ⅲ curves (wash-out) between oestrogen receptor-positive and -negative cancers was not significant (95% confidence interval (CI): [−0.10, 0.03]). In nine studies, including a total of 1070 lesions, the pooled difference in proportions of type 3 curves between human epidermal growth factor receptor 2-positive and -negative cancers was significant (95% CI: [0.01, 0.14]). In six studies including a total of 622 lesions, the pooled difference in proportions of type 3 curves between the high and low Ki-67 groups was significant (95% CI: [0.17, 0.44]). However, the type 3 curve itself is a nonspecific finding in breast cancer. Many studies have examined the relationship between mean ADC and breast cancer subtypes; however, the ADC values overlapped significantly between subtypes. The heterogeneity of ADC using kurtosis or difference, diffusion tensor imaging parameters, and relaxation time was reported recently with promising results; however, current evidence is limited, and further studies are required to explore these potential applications.

Magnetic Resonance Imaging Phenotypes of Breast Cancer Molecular Subtypes: A Systematic Review

OBJECTIVE

Magnetic resonance imaging (MRI) is the most sensitive imaging modality in detecting breast cancer. The purpose of this systematic review is to investigate the role of human extracted MRI phenotypes in classifying molecular subtypes of breast cancer.

METHODS

We performed a literature search of published articles on the application of MRI phenotypic features in invasive breast cancer molecular subtype classifications by radiologists' interpretation on Medline Complete, Pubmed, and Google scholar from 1st January 2000 to 31st March 2021. Of the 1453 literature identified, 42 fulfilled the inclusion criteria.

RESULTS

All studies were case-controlled, retrospective study and research-based. The majority of the studies assessed the MRI features using American College of Radiology- Breast Imaging Reporting and Data System (ACR-BIRADS) classification and using dynamic contrast-enhanced (DCE) kinetic features, Apparent Diffusion Coefficient (ADC) values, and T2 sequence. Most studies divided invasive breast cancer into 4 main subtypes, luminal A, luminal B, HER2, and triple-negative (TN) cancers, and used 2 readers. We present a summary of the radiologists' extracted breast MRI phenotypical features and their correlating breast cancer subtypes classifications. The characteristic features are morphology, enhancement kinetics, and T2 signal intensity. We found that the TN subtype has the most distinctive MRI features compared to the other subtypes and luminal A and B have many similar features.

CONCLUSION

The MRI features which are predictive of each subtype are the morphology, internal enhancement features, and T2 signal intensity, predominantly between TN and the rest. Radiologists' visual interpretation of some of MRI features may offer insight into the respective invasive breast cancer molecular subtype. However, current evidence are still limited to "suggestive" features instead of a diagnostic standard.  Further research is recommended to explore this potential application, for example, by augmentation of radiologists' visual interpretation by artificial intelligence.

Are we choosing wisely? Drivers of preoperative MRI use in breast cancer patients

INTRODUCTION

Factors contributing to the use of preoperative MRI remain poorly understood.

METHODS

Data from a randomized controlled trial of stage 0-3 breast cancer patients undergoing breast conserving surgery between 2016 and 2018 were analyzed.

RESULTS

Of the 396 patients in this trial, 32.6% had a preoperative MRI. Patient age, race, ethnicity, tumor histology, and use of neoadjuvant therapy were significant predictors of MRI use. On multivariate analysis, younger patients with invasive lobular tumors were more likely to have a preoperative MRI. Rates also varied significantly by individual surgeon (p < 0.001); in particular, female surgeons (39.9% vs. 24.0% for male surgeons, p = 0.001) and those in community practice (58.9% vs. 14.2% for academic, p < 0.001) were more likely to order preoperative MRI. Rates declined over the two years of the study, particularly among female surgeons.

CONCLUSIONS

Preoperative MRI varies with patient age and tumor histology; however, there remains variability by individual surgeon.

Molecular Subtypes of Breast Cancer: A Review for Breast Radiologists

Gene expression profiling has reshaped our understanding of breast cancer by identifying four molecular subtypes: (1) luminal A, (2) luminal B, (3) human epidermal growth factor receptor 2 (HER2)-enriched, and (4) basal-like, which have critical differences in incidence, response to treatment, disease progression, survival, and imaging features. Luminal tumors are most common (60%-70%), characterized by estrogen receptor (ER) expression. Luminal A tumors have the best prognosis of all subtypes, whereas patients with luminal B tumors have significantly shorter overall and disease-free survival. Distinguishing between these tumors is important because luminal B tumors require more aggressive treatment. Both commonly present as irregular masses without associated calcifications at mammography; however, luminal B tumors more commonly demonstrate axillary involvement at diagnosis. HER2-enriched tumors are characterized by overexpression of the HER2 oncogene and low-to-absent ER expression. HER2+ disease carries a poor prognosis, but the development of anti-HER2 therapies has greatly improved outcomes for women with HER2+ breast cancer. HER2+ tumors most commonly present as spiculated masses with pleomorphic calcifications or as calcifications alone. Basal-like cancers (15% of all invasive breast cancers) predominate among "triple negative" cancers, which lack ER, progesterone receptor (PR), and HER2 expression. Basal-like cancers are frequently high-grade, large at diagnosis, with high rates of recurrence. Although imaging commonly reveals irregular masses with ill-defined or spiculated margins, some circumscribed basal-like tumors can be mistaken for benign lesions. Incorporating biomarker data (histologic grade, ER/PR/HER2 status, and multigene assays) into classic anatomic tumor, node, metastasis (TNM) staging can better inform clinical management of this heterogeneous disease.

MRI-based machine learning radiomics can predict HER2 expression level and pathologic response after neoadjuvant therapy in HER2 overexpressing breast cancer

Background

To use clinical and MRI radiomic features coupled with machine learning to assess HER2 expression level and predict pathologic response (pCR) in HER2 overexpressing breast cancer patients receiving neoadjuvant chemotherapy (NAC).

Methods

This retrospective study included 311 patients. pCR was defined as no residual invasive carcinoma in the breast or axillary lymph nodes (ypT0/isN0). Radiomics/statistical analysis was performed using MATLAB and CERR software. After ROC and correlation analysis, selected radiomics parameters were advanced to machine learning modelling alongside clinical MRI-based parameters (lesion type, multifocality, size, nodal status). For predicting pCR, the data was split into a training and test set (80:20).

Findings

The overall pCR rate was 60.5% (188/311). The final model to predict HER2 heterogeneity utilised three MRI parameters (two clinical, one radiomic) for a sensitivity of 99.3% (277/279), specificity of 81.3% (26/32), and diagnostic accuracy of 97.4% (303/311). The final model to predict pCR included six MRI parameters (two clinical, four radiomic) for a sensitivity of 86.5% (32/37), specificity of 80.0% (20/25), and diagnostic accuracy of 83.9% (52/62) (test set); these results were independent of age and ER status, and outperformed the best model developed using clinical parameters only (p=0.029, comparison of proportion Chi-squared test).

Interpretation

The machine learning models, including both clinical and radiomics MRI features, can be used to assess HER2 expression level and can predict pCR after NAC in HER2 overexpressing breast cancer patients.

Funding

NIH/NCI (P30CA008748), Susan G. Komen Foundation, Breast Cancer Research Foundation, Spanish Foundation Alfonso Martin Escudero, European School of Radiology.

Predicting Breast Cancer Molecular Subtype with MRI Dataset Utilizing Convolutional Neural Network Algorithm

To develop a convolutional neural network (CNN) algorithm that can predict the molecular subtype of a breast cancer based on MRI features. An IRB-approved study was performed in 216 patients with available pre-treatment MRIs and immunohistochemical staining pathology data. First post-contrast MRI images were used for 3D segmentation using 3D slicer. A CNN architecture was designed with 14 layers. Residual connections were used in the earlier layers to allow stabilization of gradients during backpropagation. Inception style layers were utilized deeper in the network to allow learned segregation of more complex feature mappings. Extensive regularization was utilized including dropout, L2, feature map dropout, and transition layers. The class imbalance was addressed by doubling the input of underrepresented classes and utilizing a class sensitive cost function. Parameters were tuned based on a 20% validation group. A class balanced holdout set of 40 patients was utilized as the testing set. Software code was written in Python using the TensorFlow module on a Linux workstation with one NVidia Titan X GPU. Seventy-four luminal A, 106 luminal B, 13 HER2+, and 23 basal breast tumors were evaluated. Testing set accuracy was measured at 70%. The class normalized macro area under receiver operating curve (ROC) was measured at 0.853. Non-normalized micro-aggregated AUC was measured at 0.871, representing improved discriminatory power for the highly represented Luminal A and Luminal B subtypes. Aggregate sensitivity and specificity was measured at 0.603 and 0.958. MRI analysis of breast cancers utilizing a novel CNN can predict the molecular subtype of breast cancers. Larger data sets will likely improve our model.

Performance of preoperative breast MRI based on breast cancer molecular subtype

PURPOSE

To assess the performance of preoperative breast MRI biopsy recommendations based on breast cancer molecular subtype.

METHODS

All preoperative breast MRIs at a single academic medical center from May 2010 to March 2014 were identified. Reports were reviewed for biopsy recommendations. All pathology reports were reviewed to determine biopsy recommendation outcomes. Molecular subtypes were defined as Luminal A (ER/PR+ and HER2-), Luminal B (ER/PR+ and HER2+), HER2 (ER-, PR- and HER2+), and Basal (ER-, PR-, and HER2-). Logistic regression assessed the probability of true positive versus false positive biopsy and mastectomy versus lumpectomy.

RESULTS

There were 383 patients included with a molecular subtype distribution of 253 Luminal A, 44 Luminal B, 20 HER2, and 66 Basal. Two hundred and thirteen (56%) patients and 319 sites were recommended for biopsy. Molecular subtype did not influence the recommendation for biopsy (p = 0.69) or the number of biopsy site recommendations (p = 0.30). The positive predictive value for a biopsy recommendation was 42% overall and 46% for Luminal A, 43% for Luminal B, 36% for HER2, and 29% for Basal subtype cancers. The multivariate logistic regression model showed no difference in true positive biopsy rate based on molecular subtype (p = 0.78). Fifty-one percent of patients underwent mastectomy and the multivariate model demonstrated that only a true positive biopsy (odds ratio: 5.3) was associated with higher mastectomy rates.

CONCLUSION

Breast cancer molecular subtype did not influence biopsy recommendations, positive predictive values, or surgical approaches. Only true positive biopsies increased the mastectomy rate.

Breast Cancer Radiogenomics: Current Status and Future Directions

Radiogenomics is an area of research that aims to identify associations between imaging phenotypes ("radio-") and tumor genome ("-genomics"). Breast cancer radiogenomics research in particular has been an especially prolific area of investigation in recent years as evidenced by the wide number and variety of publications and conferences presentations. To date, research has primarily been focused on dynamic contrast enhanced pre-operative breast MRI and breast cancer molecular subtypes, but investigations have extended to all breast imaging modalities as well as multiple additional genetic markers including those that are commercially available. Furthermore, both human and computer-extracted features as well as deep learning techniques have been explored. This review will summarize the specific imaging modalities used in radiogenomics analysis, describe the methods of extracting imaging features, and present the types of genomics, molecular, and related information used for analysis. Finally, the limitations and future directions of breast cancer radiogenomics research will be discussed.

Preoperative breast MRI features associated with positive or close margins in breast-conserving surgery

PURPOSE

To determine preoperative magnetic resonance imaging (MRI) features associated with positive or close margins in patients with breast cancer who underwent breast-conserving surgery (BCS).

MATERIALS AND METHODS

A retrospective review identified 249 patients with invasive ductal carcinoma (IDC) who underwent preoperative MRI and BCS as a primary procedure between 2008 and 2010. The MR images were reviewed for descriptions of findings with no new interpretations made. Margins were defined as positive (tumor touching the inked specimen margin), close (<2 mm tumor-free margin), or negative (≥2 mm tumor-free margin). Multivariate logistic regression analysis was performed to evaluate imaging and clinical factors predictive of positive or close margins.

RESULTS

Of the 249 patients, 83 (33.3%) had positive or close margins and 166 (66.7%) had negative margins on the initial BCS specimen. Multivariate analysis showed that multifocal disease (odds ratio, 4.8; 95% CI, 1.9-12.2; p =  0.001), nonmass enhancement lesion (odds ratio, 3.0; 95% CI, 1.5-6.2, p =  0.003), greater background parenchymal enhancement (odds ratio, 2.5; 95% CI, 1.1-5.6; p =  0.023), larger lesion size (odds ratio, 1.3; 95% CI, 1.0-1.7, p =  0.032), and presence of ductal carcinoma in situ on needle biopsy (odds ratio, 2.4; 95% CI, 1.3-4.6; p = 0.008) were independent predictors of positive or close margins.

CONCLUSIONS

Multifocal disease, nonmass enhancement lesion, or greater background parenchymal enhancement on preoperative breast MRI were significantly associated with positive or close margins. Identifying these MRI features before surgery can be helpful to reduce the reoperation rate in BCS.

Are Mammographically Occult Additional Tumors Identified More Than 2 Cm Away From the Primary Breast Cancer on MRI Clinically Significant?

RATIONALE AND OBJECTIVES

To evaluate the clinical significance of mammographically occult additional tumors identified more than 2cm away from the primary breast cancer on preoperative magnetic resonance imaging (MRI).

MATERIALS AND METHODS

An Institutional Review Board approved review of consecutive preoperative breast MRIs performed from 1/1/08 to 12/31/14, yielded 667 patients with breast cancer. These patients underwent further assessment to identify biopsy proven mammographically occult breast tumors located more than 2cm away from the edge of the primary tumor. Additional MRI characteristics of the primary and secondary tumors and pathology were reviewed. Statistical analysis was performed using SPSS (v. 24).

RESULTS

Of 667 patients with breast cancer, 129 patients had 150 additional ipsilateral mammographically occult tumors that were more than 2cm away from the edge of the primary tumor. One hundred twelve of 129 (86.8%) patients had one additional tumor and 17/129 (13.2%) had two or more additional tumors. In 71/129 (55.0%), additional tumors were located in a different quadrant and in 58/129 (45.0%) additional tumors were in the same quadrant but ≥2cm away. Overall, primary tumor size was significantly larger (mean 1.87± 1.25 cm) than the additional tumors (mean 0.79 ± 0.61cm, p < 0.001). However, in 20/129 (15.5%) the additional tumor was larger and in 26/129 (20.2%) the additional tumor was ≥1cm. The primary tumor was significantly more likely to be invasive (81.4%, 105/129) compared to additional tumors (70%, 105/150, p = 0.03). In 9/129 (7.0%) patients, additional tumors yielded unsuspected invasive cancer orhigher tumor grade. The additional tumor was more likely to be nonmass lesion type (37.3% vs 24% p = 0.02) and focus lesion type (10% vs 0.08%, p < 0.001) compared to primary tumor.

CONCLUSION

Mammographically occult additional tumors identified more than 2cm away from the primary breast tumor on MRI are unlikely to be surgically treated if undiagnosed and may be clinically significant.

Prediction of molecular subtypes of breast cancer using BI-RADS features based on a "white box" machine learning approach in a multi-modal imaging setting

PURPOSE

To develop and validate an interpretable and repeatable machine learning model approach to predict molecular subtypes of breast cancer from clinical metainformation together with mammography and MRI images.

METHODS

We retrospectively assessed 363 breast cancer cases (Luminal A 151, Luminal B 96, HER2 76, and BLBC 40). Eighty-two features defined in the BI-RADS lexicon were visually described. A decision tree model with the Chi-squared automatic interaction detector (CHAID) algorithm was applied for feature selection and classification. A 10-fold cross-validation was performed to investigate the performance (i.e., accuracy, positive predictive value, sensitivity, and F1-score) of the decision tree model.

RESULTS

Seven of the 82 variables were derived from the decision tree-based feature selection and used as features for the classification of molecular subtypes including mass margin calcification on mammography, mass margin types of kinetic curves in the delayed phase, mass internal enhancement characteristics, non-mass enhancement distribution on MRI, and breastfeeding history. The decision tree model accuracy was 74.1%. For each molecular subtype group, Luminal A achieved a sensitivity, positive predictive value, and F1-score of 79.47%, 75.47%, and 77.42%, respectively; Luminal B showed a sensitivity, positive predictive value, and F1-score of 64.58%, 55.86%, and 59.90%, respectively; HER2 had a sensitivity, positive predictive value, and F1-scores of 81.58%, 95.38%, and 87.94%, respectively; BLBC showed sensitivity, positive predictive value, and F1-scores of 62.50%, 89.29%, and 73.53%, respectively.

CONCLUSIONS

We applied a complete "white box" machine learning method to predict the molecular subtype of breast cancer based on the BI-RADS feature description in a multi-modal setting. By combining BI-RADS features in both mammography and MRI, the prediction accuracy is boosted and robust. The proposed method can be easily applied widely regardless of variability of imaging vendors and settings because of the applicability and acceptance of the BI-RADS.

Receptor-based Surrogate Subtypes and Discrepancies with Breast Cancer Intrinsic Subtypes: Implications for Image Biomarker Development

Purpose To determine the concordance and accuracy of imaging surrogates of immunohistochemical (IHC) markers and the molecular classification of breast cancer. Materials and Methods A total of 3050 patients from 17 public breast cancer data sets containing IHC marker receptor status (estrogen receptor/progesterone receptor/human epidermal growth factor receptor 2 [HER2]) and their molecular classification (basal-like, HER2-enriched, luminal A or B) were analyzed. Diagnostic accuracy and concordance as measured with the κ statistic were calculated between the IHC and molecular classifications. Simulations were performed to assess the relationship between accuracy of imaging-based IHC markers to predict molecular classification. A simulation was performed to examine effects of misclassification of molecular type on patient survival. Results Accuracies of intrinsic subtypes based on IHC subtype were 71.7% (luminal A), 53.7% (luminal B), 64.8% (HER2-enriched), and 81.7% (basal-like). The κ agreement was fair (κ = 0.36) for luminal A and HER2-enriched subtypes, good (κ = 0.65) for the basal-like subtype, and poor (κ = 0.09) for the luminal B subtypes. Introduction of image misclassification by simulation lowered image-true subtype accuracies and κ values. Simulation analysis showed that misclassification caused survival differences between luminal A and basal-like subtypes to decrease. Conclusion There is poor concordance between triple-receptor status and intrinsic molecular subtype in breast cancer, arguing against their use in the design of prognostic genomic-based image biomarkers. © RSNA, 2018 Online supplemental material is available for this article.

A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features

BACKGROUND

Recent studies showed preliminary data on associations of MRI-based imaging phenotypes of breast tumours with breast cancer molecular, genomic, and related characteristics. In this study, we present a comprehensive analysis of this relationship.

METHODS

We analysed a set of 922 patients with invasive breast cancer and pre-operative MRI. The MRIs were analysed by a computer algorithm to extract 529 features of the tumour and the surrounding tissue. Machine-learning-based models based on the imaging features were trained using a portion of the data (461 patients) to predict the following molecular, genomic, and proliferation characteristics: tumour surrogate molecular subtype, oestrogen receptor, progesterone receptor and human epidermal growth factor status, as well as a tumour proliferation marker (Ki-67). Trained models were evaluated on the set of the remaining 461 patients.

RESULTS

Multivariate models were predictive of Luminal A subtype with AUC = 0.697 (95% CI: 0.647-0.746, p < .0001), triple negative breast cancer with AUC = 0.654 (95% CI: 0.589-0.727, p < .0001), ER status with AUC = 0.649 (95% CI: 0.591-0.705, p < .001), and PR status with AUC = 0.622 (95% CI: 0.569-0.674, p < .0001). Associations between individual features and subtypes we also found.

CONCLUSIONS

There is a moderate association between tumour molecular biomarkers and algorithmically assessed imaging features.

MRI for the Staging and Evaluation of Response to Therapy in Breast Cancer

Breast magnetic resonance imaging (MRI) is the most sensitive of the available imaging modalities to characterize breast cancer. Breast MRI has gained clinical acceptance for screening high-risk patients, but its role in the preoperative imaging of breast cancer patients remains controversial. This review focuses on the current indications for staging breast MRI, the evidence for and against the role of breast MRI in the preoperative staging workup, and the evaluation of treatment response of breast cancer patients.

Association of preoperative breast MRI features with locoregional recurrence after breast conservation therapy

Background Locoregional recurrence (LRR) following breast conservation therapy (BCT) is associated with an increased risk of distant metastasis and death in patients with breast cancer. Purpose To investigate whether preoperative breast magnetic resonance imaging (MRI) features are associated with the risk of LRR in patients undergoing BCT. Material and Methods A total of 3781 women with primary invasive breast cancer underwent preoperative MRI and BCT between 2003 and 2013. Forty-eight patients who developed LRR comprised the LRR cohort and one-to-one matching (age, tumor stage, grade, and axillary nodal status) of each patient to a control participant was performed in patients who did not develop recurrence. Three readers independently reviewed MR images of the index cancer and the presence of multifocal disease was assessed. Χ² analysis was used to compare imaging and clinical features between LRR and control cohorts, with multivariate logistic regression analysis used to identify independent features. Results Significant differences were found in the proportion of multifocal disease ( P = 0.001), background parenchymal enhancement level ( P = 0.007), and breast cancer molecular subtype ( P = 0.01) between LRR and control cohorts. Multivariate analysis showed that multifocal disease (odds ratio [OR] = 11.9; 95% confidence interval [CI] = 1.4-102.5; P = 0.02) and human epidermal growth factor receptor 2-positive subtype (OR = 12.7; 95% CI = 1.3-127.6; P = 0.03) were both independently associated with LRR. Conclusion Multifocal disease on preoperative breast MRI may indicate an increased risk of LRR in patients treated with BCT.

Who Is Ordering MRIs in Newly Diagnosed Breast Cancer Patients?

The role of MRI in the workup of newly diagnosed breast cancer patients remains controversial. Breast MRI detects additional disease, but this has not translated into improved outcomes. In light of a dramatic rise in MRI use, we investigated patterns of MRI ordering for newly diagnosed breast cancer. All newly diagnosed breast cancer cases presenting for surgical management to a specialized breast center from 2011 to 2013 were reviewed. Patients who had an MRI ordered by their operating surgeon were compared with those who had an MRI completed previously. Of 1037 patients, 504 (49%) with newly diagnosed breast cancer underwent MRI as part of their pre-operative evaluation. Variables associated with MRI use included commercial insurance, increased breast density, genetic testing, mamographically occult disease, and lobular pathology. Of women who presented to our center with an MRI already completed, 63 per cent were ordered by a primary care provider. Of the 504 patients, 233 (44%) who had an MRI underwent an additional biopsy, and 166 (33%) had a resultant change in management. There was no significant difference in MRI-directed change in patient care depending on ordering provider. Further research is needed to develop evidence-based guidelines for preoperative MRI evaluation to optimize patient outcomes.

MRI features predictive of negative surgical margins in patients with HER2 overexpressing breast cancer undergoing breast conservation

Here we develop a tool to predict resectability of HER2+ breast cancer at breast conservation surgery (BCS) utilizing features identified on preoperative breast MRI. We identified patients with HER2+ breast cancer who obtained pre-operative breast MRI and underwent BCS between 2002–2013. From the contoured tumor on pre-operative MRI, shape, histogram, and co-occurrence and size zone matrix texture features were extracted. In univariate analysis, Spearman’s correlation coefficient (Rs) was used to assess the correlation between each image feature and an endpoint (surgical re-excision). For multivariate modeling, we employed a support vector machine (SVM) method in a manner of leave-one-out cross-validation (LOOCV). Of 109 patients with HER2+breast cancer who underwent BCS, 39% underwent surgical re-excision. 62% had residual cancer at re-excision. In univariate analysis, solidity (Rs = −0.32, p = 0.009) and extent (Rs = −0.29, p = 0.019) were significantly associated with re-excision. Skewness in post-contrast 1, 2, and 3 (Rs = 0.25, p = 0.045; Rs = 0.30, p = 0.015; Rs = 0.28, p = 0.026) and kurtosis in post-contrast 1 (Rs = 0.26, p = 0.035) were also statistically significant. LOOCV-based SVM test achieved 74.4% specificity and 71.4% sensitivity when 21 features were used. Thus, tumor texture, histogram and morphological MRI features may assist surgical planning, encouraging wide margins or mastectomy in patients who may otherwise go on to re-excision.

Agreement between MRI and pathologic analyses for determination of tumor size and correlation with immunohistochemical factors of invasive breast carcinoma

Background There may be discordance between tumor size determined by magnetic resonance imaging (MRI) and that observed during pathologic analyses. Purpose To evaluate MRI-pathology concordance of tumor size in patients with invasive breast carcinoma. Material and Methods Data from 307 invasive breast carcinomas were analyzed retrospectively. Preoperative breast MRI was reviewed for size, lesion type, morphology, and dynamic contrast-enhanced tumor kinetics. MRI tumor size was compared with tumor size measurements from the pathologic analysis. Concordance was defined as a difference in diameter of ≤ 0.5 cm. MRI-pathology concordance was compared according to clinical and histopathologic features. Results The mean tumor size on MRI was 2.48 ± 1.41 cm. Tumor measurements determined by MRI were not significantly different from those recorded in the pathologic reports (2.56 ± 1.61 cm, P = 0.199). MRI-pathology concordance was found in 229/307 (74.6%) cases; the size was overestimated in 36 (11.7%) tumors and underestimated in 42 (13.7%). On univariate analysis, MRI-pathology discordance was associated with larger tumor size ( P < 0.001), estrogen receptor (ER) negativity ( P = 0.006), and lymphovascular invasion ( P = 0.003). Human epidermal growth factor receptor 2 positive molecular subtype showed worse correlation between the tumor size measured by MRI and pathology compared with luminal A and luminal B subtypes ( P = 0.008 and 0.007). On multivariate analysis, tumor size and ER status significantly influenced MRI-pathology concordance ( P < 0.05). Conclusion ER negativity and larger tumor size were strongly associated with MRI-pathology discordance in invasive breast carcinomas. Awareness of these factors might improve surgical planning.

Computer-aided evaluation of the correlation between MRI morphology and immunohistochemical biomarkers or molecular subtypes in breast cancer

Studies using tumor circularity (TC), a quantitative MRI morphologic index, to evaluate breast cancer are scarce. The purpose of this study is to evaluate the correlation between TC and immunohistochemical biomarkers or molecular subtypes in breast cancer. 146 patients with 150 breast cancers were selected. All tumors were confirmed by histopathology and examined by 3.0T MRI. TC was calculated by computer-aided software. The associations between TC and patient age, tumor size, histological grade, molecular subtypes, and immunohistochemical biomarkers including estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), and Ki67 were analyzed. TC correlated inversely with tumor size (r = -0.224, P < 0.001), ER (r = -0.490, P < 0.001) and PR (r = -0.484, P < 0.001). However, TC correlated positively with Ki67 (r = 0.332, P < 0.001) and histological grade (r = 0.309, P < 0.001). In multiple linear regression analysis, tumor size, ER, PR and Ki67 were independent influential factors of TC. Compared with HER2-overexpressed (61.6%), luminal A (54.7%) and luminal B (52.3%) subtypes, triple-negative breast cancer (TNBC) showed the highest score of TC (70.8%, P < 0.001). Our study suggests that TC can be used as an imaging biomarker to predict the aggressiveness of newly diagnosed breast cancers. TNBC seems to present as an orbicular appearance when comparing with other subtypes.

Sonographic Phenotypes of Molecular Subtypes of Invasive Ductal Cancer in Automated 3-D Breast Ultrasound

Our aim was to investigate whether Breast Imaging Reporting and Data System-Ultrasound (BI-RADS-US) lexicon descriptors can be used as imaging biomarkers to differentiate molecular subtypes (MS) of invasive ductal carcinoma (IDC) in automated breast ultrasound (ABUS). We included 125 IDCs diagnosed between 2010 and 2014 and imaged with ABUS at two institutes retrospectively. IDCs were classified as luminal A or B, HER2 enriched or triple negative based on reports of histopathologic analysis of surgical specimens. Two breast radiologists characterized all IDCs using the BI-RADS-US lexicon and specific ABUS features. Univariate and multivariate analyses were performed. A multinomial logistic regression model was built to predict the MSs from the imaging characteristics. BI-RADS-US descriptor margins and the retraction phenomenon are significantly associated with MSs (both p < 0.001) in both univariate and multivariate analysis. Posterior acoustic features and spiculation pattern severity were only significantly associated in univariate analysis (p < 0.001). Luminal A IDCs tend to have more prominent retraction patterns than luminal B IDCs. HER2-enriched and triple-negative IDCs present significantly less retraction than the luminal subtypes. The mean accuracy of MS prediction was 0.406. Overall, several BI-RADS-US descriptors and the coronal retraction phenomenon and spiculation pattern are associated with MSs, but prediction of MSs on ABUS is limited.

Association Between Imaging Characteristics and Different Molecular Subtypes of Breast Cancer

RATIONALE AND OBJECTIVE

Breast cancer can be divided into four major molecular subtypes based on the expression of hormone receptor (estrogen receptor and progesterone receptor), human epidermal growth factor receptor 2, HER2 status, and molecular proliferation rate (Ki67). In this study, we sought to investigate the association between breast cancer subtype and radiological findings in the Chinese population.

MATERIALS AND METHODS

Medical records of 300 consecutive invasive breast cancer patients were reviewed from the database: the Breast Imaging Reporting and Data System. The imaging characteristics of the lesions were evaluated. The molecular subtypes of breast cancer were classified into four types: luminal A, luminal B, HER2 overexpressed (HER2), and basal-like breast cancer (BLBC). Univariate and multivariate logistic regression analyses were performed to assess the association between the subtype (dependent variable) and mammography or 15 magnetic resonance imaging (MRI) indicators (independent variables).

RESULTS

Luminal A and B subtypes were commonly associated with "clustered calcification distribution," "nipple invasion," or "skin invasion" (P <0.05). The BLBC subtype was more commonly associated with "rim enhancement" and persistent inflow type enhancement in delayed phase (P <0.05). HER2 overexpressed cancers showed association with persistent enhancement in the delayed phase on MRI and "clustered calcification distribution" on mammography (P <0.05).

CONCLUSION

Certain radiological features are strongly associated with the molecular subtype and hormone receptor status of breast tumor, which are potentially useful tools in the diagnosis and subtyping of breast cancer.

Incremental cancer detection using breast ultrasonography versus breast magnetic resonance imaging in the evaluation of newly diagnosed breast cancer patients

OBJECTIVE

To compare the incremental cancer detection rate (ICDR) using bilateral whole-breast ultrasonography (BWBUS) vs dynamic contrast-enhanced MRI in patients with primary breast cancer.

METHODS

A retrospective database search in a single institution identified 259 patients with breast cancer diagnosed from January 2011 to August 2014 who underwent mammography, BWBUS and MRI before surgery. Patient characteristics, tumour characteristics and lesions seen on each imaging modality were recorded. The sensitivity, specificity and accuracy for each modality were calculated. ICDRs according to index tumour histology and receptor status were also evaluated. The effect of additional cancer detection on surgical planning was obtained from the medical records.

RESULTS

A total of 266 additional lesions beyond 273 index malignancies were seen on at least 1 modality, of which 121 (45%) lesions were malignant and 145 (55%) lesions were benign. MRI was significantly more sensitive than BWBUS (p = 0.01), while BWBUS was significantly more accurate and specific than MRI (p < 0.0001). Compared with mammography, the ICDRs using BWBUS and MRI were significantly higher for oestrogen receptor-positive and triple-negative cancers, but not for human epidermal growth factor receptor 2-positive cancers. 22 additional malignant lesions in 18 patients were seen on MRI only. Surgical planning remained unchanged in 8 (44%) of those 18 patients.

CONCLUSION

MRI was more sensitive than BWBUS, while BWBUS was more accurate and specific than MRI. MRI-detected additional malignant lesions did not change surgical planning in almost half of these patients.

ADVANCES IN KNOWLEDGE

BWBUS may be a cost-effective and practical tool in breast cancer staging.

The Values of Combined and Sub-Stratified Imaging Scores with Ultrasonography and Mammography in Breast Cancer Subtypes

Background and Objectives

The Breast Imaging Reporting and Data System (BI-RADS) of Mammography (MG) and Ultrasonography (US) were equivalent to the “5-point score” and applied for combined and sub-stratified imaging assessments. This study evaluated the value of combined and sub-stratified imaging assessments with MG and US over breast cancer subtypes (BCS).

Materials and Methods

Medical records of 5,037 cases having imaging-guided core biopsy, performed from 2009 to 2012, were retrospectively reviewed. This study selected 1,995 cases (1,457 benign and 538 invasive cancer) having both MG and US before biopsy. These cases were categorized with the “5-point score” for their MG and US, and applied for combined and sub-stratified imaging assessments. Invasive cancers were classified on the basis of BCS, and correlated with combined and sub-stratified imaging assessments.

Results

These selected cases were evaluated by the “5-point score.” MG, US, and combined and sub-stratified imaging assessments all revealed statistically significant (P < 0.001) incidence of malignancy. The sensitivity was increased in the combined imaging score (99.8%), and the specificity was increased in the sub-stratified combined score (75.4%). In the sub-stratified combined imaging assessment, all BCS can be classified with higher scores (abnormality hierarchy), and luminal B subtype showed the most salient result (hierarchy: higher, 95%; lower, 5%).

Conclusions

Combined and sub-stratified imaging assessments can increase sensitivity and specificity of breast cancer diagnosis, respectively, and Luminal B subtype shows the best identification by sub-stratified combined imaging scoring.

Breast MRI radiogenomics: Current status and research implications

Breast magnetic resonance imaging (MRI) radiogenomics is an emerging area of research that has the potential to directly influence clinical practice. Clinical MRI scanners today are capable of providing excellent temporal and spatial resolution, which allows extraction of numerous imaging features via human extraction approaches or complex computer vision algorithms. Meanwhile, advances in breast cancer genetics research has resulted in the identification of promising genes associated with cancer outcomes. In addition, validated genomic signatures have been developed that allow categorization of breast cancers into distinct molecular subtypes as well as predict the risk of cancer recurrence and response to therapy. Current radiogenomics research has been directed towards exploratory analysis of individual genes, understanding tumor biology, and developing imaging surrogates to genetic analysis with the long-term goal of developing a meaningful tool for clinical care. The background of breast MRI radiogenomics research, image feature extraction techniques, approaches to radiogenomics research, and promising areas of investigation are reviewed. J. Magn. Reson. Imaging 2016;43:1269-1278.