A Reliability Comparison of Cone-Beam Breast Computed Tomography and Mammography: Breast Density Assessment Referring to the Fifth Edition of the BI-RADS Atlas

Radiomics in cone-beam breast CT for the prediction of axillary lymph node metastasis in breast cancer: a multi-center multi-device study

OBJECTIVES

To develop a radiomics model in contrast-enhanced cone-beam breast CT (CE-CBBCT) for preoperative prediction of axillary lymph node (ALN) status and metastatic burden of breast cancer.

METHODS

Two hundred and seventy-four patients who underwent CE-CBBCT examination with two scanners between 2012 and 2021 from two institutions were enrolled. The primary tumor was annotated in each patient image, from which 1781 radiomics features were extracted with PyRadiomics. After feature selection, support vector machine models were developed to predict ALN status and metastatic burden. To avoid overfitting on a specific patient subset, 100 randomly stratified splits were made to assign the patients to either training/fine-tuning or test set. Area under the receiver operating characteristic curve (AUC) of these radiomics models was compared to those obtained when training the models only with clinical features and combined clinical-radiomics descriptors. Ground truth was established by histopathology.

RESULTS

One hundred and eighteen patients had ALN metastasis (N + (≥ 1)). Of these, 74 had low burden (N + (1~2)) and 44 high burden (N + (≥ 3)). The remaining 156 patients had none (N0). AUC values across the 100 test repeats in predicting ALN status (N0/N + (≥ 1)) were 0.75 ± 0.05 (0.67~0.93, radiomics model), 0.68 ± 0.07 (0.53~0.85, clinical model), and 0.74 ± 0.05 (0.67~0.88, combined model). For metastatic burden prediction (N + (1~2)/N + (≥ 3)), AUC values were 0.65 ± 0.10 (0.50~0.88, radiomics model), 0.55 ± 0.10 (0.40~0.80, clinical model), and 0.64 ± 0.09 (0.50~0.90, combined model), with all the ranges spanning 0.5. In both cases, the radiomics model was significantly better than the clinical model (both p < 0.01) and comparable with the combined model (p = 0.56 and 0.64).

CONCLUSIONS

Radiomics features of primary tumors could have potential in predicting ALN metastasis in CE-CBBCT imaging.

CLINICAL RELEVANCE STATEMENT

The findings support potential clinical use of radiomics for predicting axillary lymph node metastasis in breast cancer patients and addressing the limited axilla coverage of cone-beam breast CT.

KEY POINTS

• Contrast-enhanced cone-beam breast CT-based radiomics could have potential to predict N0 vs. N + (≥ 1) and, to a limited extent, N + (1~2) vs. N + (≥ 3) from primary tumor, and this could help address the limited axilla coverage, pending future verifications on larger cohorts. • The average AUC of radiomics and combined models was significantly higher than that of clinical models but showed no significant difference between themselves. • Radiomics features descriptive of tumor texture were found informative on axillary lymph node status, highlighting a higher heterogeneity for tumor with positive axillary lymph node.

Radiomics nomogram for predicting axillary lymph node metastasis-a potential method to address the limitation of axilla coverage in cone-beam breast CT: a bi-center retrospective study

PURPOSE

Cone-beam breast CT (CBBCT) has an inherent limitation that the axilla cannot be imaged in its entirety. We aimed to develop and validate a nomogram based on clinical factors and contrast-enhanced (CE) CBBCT radiomics features to predict axillary lymph node (ALN) metastasis and complement limited axilla coverage.

MATERIAL AND METHODS

This retrospective study included 312 patients with breast cancer from two hospitals who underwent CE-CBBCT examination in a clinical trial (NCT01792999) during 2012-2020. Patients from TCIH comprised training set (n = 176) and validation set (n = 43), and patients from SYSUCC comprised external test set (n = 93). 3D ROIs were delineated manually and radiomics features were extracted by 3D Slicer software. RadScore was calculated and radiomics model was constructed after feature selection. Clinical model was built on independent predictors. Nomogram was developed with independent clinical predictors and RadScore. Diagnostic performance was compared among three models by ROC curve, and decision curve analysis (DCA) was used to evaluate the clinical utility of nomogram.

RESULTS

A total of 139 patients were ALN positive and 173 patients were negative. Twelve radiomics features remained after feature selection. Location and focality were selected as independent predictors for ALN status. The AUC of nomogram in external test set was higher than that of clinical model (0.80 vs. 0.66, p = 0.012). DCA demonstrated that the nomogram had higher overall net benefit than that of clinical model.

CONCLUSION

The nomogram combined CE-CBBCT-based radiomics features and clinical factors could have potential in distinguishing ALN positive from negative and addressing the limitation of axilla coverage in CBBCT.

Comparison of background parenchymal enhancement (BPE) on contrast-enhanced cone-beam breast CT (CE-CBBCT) and breast MRI

OBJECTIVES

To compare the background parenchymal enhancement (BPE) levels on contrast-enhanced cone-beam breast CT (CE-CBBCT) and MRI, evaluate inter-reader reliability, and analyze the relationship between clinical factors and BPE level on CE-CBBCT.

METHODS

In this retrospective study, patients who underwent both CE-CBBCT and MRI were analyzed. BPE levels on CE-CBBCT and MRI were assessed by five specialists independently in random fashion, with a wash-out period of 4 weeks. Weighted kappa was used to analyze the agreement between CE-CBBCT and MRI, and intraclass correlation coefficient (ICC) was used to evaluate the inter-reader reliability for each modality. The association between BPE level on CE-CBBCT and clinical factors was evaluated by univariate and multivariate logistic regression.

RESULTS

A total of 221 patients from January 2017 to April 2021 were enrolled. CE-CBBCT showed substantial agreement (weighted kappa = 0.690) with MRI for BPE evaluation, with good degree of inter-reader reliability on both CE-CBBCT (ICC = 0.712) and MRI (ICC = 0.757). Based on majority reports, BPE levels on CE-CBBCT were lower than MRI (p < 0.001). BPE level on CE-CBBCT was significantly associated with menstrual status (odds ratio, OR = 0.125), breast density (OR = 2.308), and previously treated breast cancer (OR = 0.052) (all p < 0.05). BPE level for premenopausal patients was associated with menstrual cycle, with lower BPE level for the 2^nd week of menstrual cycle (OR = 0.246).

CONCLUSIONS

CE-CBBCT showed substantial agreement and comparable inter-reader reliability with MRI for BPE evaluation, indicating that the corresponding BI-RADS lexicons could be used to describe BPE level on CE-CBBCT. The 2^nd week of menstrual cycle timing is suggested as the optimal examination period for CE-CBBCT.

KEY POINTS

• CE-CBBCT showed substantial agreement and comparable inter-reader reliability with MRI for BPE evaluation. • Menstrual status, breast density, and previously treated breast cancer were associated with the BPE level on CE-CBBCT images. • The 2^ndweek of the menstrual cycle is suggested as the optimal examination period for CE-CBBCT.

Applied Machine Learning in Spiral Breast-CT: Can We Train a Deep Convolutional Neural Network for Automatic, Standardized and Observer Independent Classification of Breast Density?

The aim of this study was to investigate the potential of a machine learning algorithm to accurately classify parenchymal density in spiral breast-CT (BCT), using a deep convolutional neural network (dCNN). In this retrospectively designed study, 634 examinations of 317 patients were included. After image selection and preparation, 5589 images from 634 different BCT examinations were sorted by a four-level density scale, ranging from A to D, using ACR BI-RADS-like criteria. Subsequently four different dCNN models (differences in optimizer and spatial resolution) were trained (70% of data), validated (20%) and tested on a “real-world” dataset (10%). Moreover, dCNN accuracy was compared to a human readout. The overall performance of the model with lowest resolution of input data was highest, reaching an accuracy on the “real-world” dataset of 85.8%. The intra-class correlation of the dCNN and the two readers was almost perfect (0.92) and kappa values between both readers and the dCNN were substantial (0.71–0.76). Moreover, the diagnostic performance between the readers and the dCNN showed very good correspondence with an AUC of 0.89. Artificial Intelligence in the form of a dCNN can be used for standardized, observer-independent and reliable classification of parenchymal density in a BCT examination.

The cone-beam breast computed tomography characteristics of breast non-mass enhancement lesions

BACKGROUND

Cone-beam computed tomography (CBBCT) of the breast is emerging as a way of improving breast cancer diagnostic yield.

PURPOSE

To find characteristics of non-mass enhancement (NME) lesions on breast CBBCT and to identify the characteristics that distinguish malignant and benign lesions.

MATERIAL AND METHODS

Breast CBBCT images of 84 NME lesions were analyzed. Internal enhancement distribution and patterns, calcification distribution and suspicious morphology, and ΔHU enhancement values were compared between post-contrast and pre-contrast malignant and benign lesions. Univariate analyses were applied to find the strongest indicators of malignancy, and logistic regression analysis was used to develop a fitting equation for the combined diagnostic model.

RESULTS

In the 84 NME lesions, the indicators of malignancy were as follows: segmental enhancement distribution (P = 0.011, 53.62% sensitivity, 86.67% specificity, 94.87% positive predictive value [PPV], and 28.89% negative predictive value [NPV]), clumped internal enhancement patterns (P = 0.017, 50.72% sensitivity, 86.67% specificity, 94.59% PPV, and 27.66% NPV), ΔHU ≥ 93.57 Hounsfield units (HU) (P = 0.004, 66.67% sensitivity, 73.33% specificity, 92.00% PPV, and 32.35% NPV), and NME lesions with calcification (P = 0.002, 36.23% sensitivity, 20.00% specificity, 82.14% PPV, and 67.57% NPV). The fitting equation for the combined diagnostic model was as follows: Logit (P) = -0.579 +1.318 × enhancement distribution + 1.000 × internal enhancement patterns + 1.539 × ΔHU value + 1.641 ×NME type.

CONCLUSION

Individual diagnostic criteria based on breast CBBCT characteristics (segmental enhancement distribution, clumped internal enhancement patterns, ΔHU values > 93.57 HU, and NME lesions with calcification) had high specificity and PPV; when combined, they had high sensitivity in predicting malignant NME lesions.

Dedicated breast CT: state of the art-Part II. Clinical application and future outlook

Dedicated breast CT is being increasingly used for breast imaging. This technique provides images with no compression, removal of tissue overlap, rapid acquisition, and available simultaneous assessment of microcalcifications and contrast enhancement. In this second installment in a 2-part review, the current status of clinical applications and ongoing efforts to develop new imaging systems are discussed, with particular emphasis on how to achieve optimized practice including lesion detection and characterization, response to therapy monitoring, density assessment, intervention, and implant evaluation. The potential for future screening with breast CT is also addressed. KEY POINTS: • Dedicated breast CT is an emerging modality with enormous potential in the future of breast imaging by addressing numerous clinical needs from diagnosis to treatment. • Breast CT shows either noninferiority or superiority with mammography and numerical comparability to MRI after contrast administration in diagnostic statistics, demonstrates excellent performance in lesion characterization, density assessment, and intervention, and exhibits promise in implant evaluation, while potential application to breast cancer screening is still controversial. • New imaging modalities such as phase-contrast breast CT, spectral breast CT, and hybrid imaging are in the progress of R & D.

Quantitative breast density measurement based on three-dimensional images: a study on cone-beam breast computed tomography

BACKGROUND

Breast density is an independent predictor of breast cancer risk. Quantitative volumetric breast density (QVBD) is expected to provide more information on the prediction of breast cancer risk.

PURPOSE

To evaluate the reliability of QVBD measurements based on cone-beam breast computed tomography (CBBCT) images.

MATERIAL AND METHODS

A total of 216 breasts were used to evaluate the stability of QVBD measurements based on CBBCT images and the correlations between this volumetric measurement and visual and area-based measurement methods. The intra- and inter-observer consistency of QVBD measurements were compared. Visual breast density (VBD) was evaluated with Breast Imaging Reporting and Data System (BI-RADS) standard on CBBCT images. The correlation between QVBD and VBD was evaluated by Spearman correlation coefficient. Receiver operating characteristic (ROC) curve was used to assess the sensitivity and specificity of the volumetric method in distinguishing dense and non-dense breasts. The correlation between QVBD and quantitative area-based breast density (QABD) was determined with Pearson correlation coefficient. Then, the breast volume measured with CBBCT images was compared with the breast specimen obtained during nipple-sparing mastectomy (NSM) by Pearson correlation coefficient and linear regression.

RESULTS

Excellent intra- and inter-observer consistency was found from QVBD measurements. The volumetric method distinguished dense and non-dense breasts at a cutoff value of 9.5%, with 94.5% sensitivity and 77.1% specificity. Positive correlations were found between QVBD and QABD (r=0.890; P<0.001) and between the volume measured with CBBCT images and Archimedes method (r=0.969; P<0.001).

CONCLUSION

CBBCT images can evaluate breast density reliably on a continuous scale.

Breast density in dedicated breast computed tomography: Proposal of a classification system and interreader reliability

The aim of this study was to develop a new breast density classification system for dedicated breast computed tomography (BCT) based on lesion detectability analogous to the ACR BI-RADS breast density scale for mammography, and to evaluate its interrater reliability.In this retrospective study, 1454 BCT examinations without contrast media were screened for suitability. Excluding datasets without additional ultrasound and exams without any detected lesions resulted in 114 BCT examinations. Based on lesion detectability, an atlas-based BCT density (BCTD) classification system of breast parenchyma was defined using 4 categories. Interrater reliability was examined in 40 BCT datasets between 3 experienced radiologists.Among the included lesions were 63 cysts (55%), 18 fibroadenomas (16%), 7 lesions of fatty necrosis (6%), and 6 breast cancers (5%) with a median diameter of 11 mm. X-ray absorption was identical between lesions and breast tissue; therefore, the lack of fatty septae was identified as the most important criteria for the presence of lesions in glandular tissue. Applying a lesion diameter of 10 mm as desired cut-off for the recommendation of an additional ultrasound, an atlas of 4 BCTD categories was defined resulting in a distribution of 17.5% for density A, 39.5% (B), 31.6% (C), and 11.4% (D) with an intraclass correlation coefficient (ICC) among 3 readers of 0.85 to 0.87.We propose a dedicated atlas-based BCTD classification system, which is calibrated to lesion detectability. The new classification system exhibits a high interrater reliability and may be used for the decision whether additional ultrasound is recommended.

Cone-beam breast CT features associated with HER2/neu overexpression in patients with primary breast cancer

OBJECTIVES

To identify the relationship between human epidermal growth factor receptor 2 (HER2) status and cone-beam breast CT (CBBCT) characteristics in surgically resected breast cancer.

METHODS

Preoperative CBBCT of patients with BI-RADS 4 or 5 lesions identified on mammography or ultrasound and dense or very dense breast tissue were retrospectively evaluated in 181 surgically resected breast cancer (triple-negative excluded) between May 2012 and November 2014. A set of CBBCT descriptors was semiquantitatively assessed by consensus double reading. Reader reproducibility was analyzed. Multivariable logistic regression analysis using backward elimination (BEA) with the Wald criterion was performed to identify independent predictive factors of harboring HER2/neu. Principle component analysis (PCA) was used to determine characteristics that might differentiate HER2 status. Receiver operating characteristic (ROC) curve analyses were conducted to determine the predictive capability.

RESULTS

HER2 positive was found in 101 (55.8%) of 181 patients. Inter-observer agreement was high for characteristics' assessment. Based on BEA, pathologic grade, maximum dimension, lobulation, ΔCT, and calcification morphology were confirmed as independent predictive factors of HER2/neu overexpression. PCA showed that calcification- and border-related characteristics were the most important for differentiation. ROC curve analyses showed that CBBCT features (AUC = 0.853) were superior to clinicopathologic features (AUC = 0.613, p < 0.001) and comparable with combination (AUC = 0.856, p = 0.866).

CONCLUSIONS

CBBCT features could be used to prognosticate HER2 status independently, which are potentially complementary to histopathologic result and helpful in guiding biopsy.

KEY POINTS

• Dmax, lobulation, ΔCT, and calcification morphology are independent predictors of HER2 status. • CBBCT features are superior to clinicopathologic features in HER2+/- discrimination. • CBBCT features are comparable with combination with clinicopathologic features in HER2+/- discrimination.