Contrast-enhanced dual-energy mammography: a promising new imaging tool in breast cancer detection

Breast cancer diagnosis from contrast-enhanced mammography using multi-feature fusion neural network

OBJECTIVES

To develop an end-to-end deep neural network for the classification of contrast-enhanced mammography (CEM) images to facilitate breast cancer diagnosis in the clinic.

METHODS

In this retrospective mono-centric study, patients who underwent CEM examinations from January 2019 to August 2021 were enrolled. A multi-feature fusion network combining low-energy (LE) and dual-energy subtracted (DES) images and dual view, as well as bilateral information, was trained and tested using a large CEM dataset with a diversity of breast tumors for breast lesion classification. Its generalization performance was further evaluated on two external datasets. Results were reported using AUC, accuracy, sensitivity, and specificity.

RESULTS

A total of 2496 patients (mean age, 53 years ± 12 (standard deviation)) were included and divided into a training set (1718), a validation set (255), and a testing set (523). The proposed CEM-based multi-feature fusion network achieved the best diagnosis performance with an AUC of 0.96 (95% confidence interval (CI): 0.95, 0.97), compared with the no-fusion model, the left-right fusion model, and the multi-feature fusion network with only LE image inputs. Our models reached an AUC of 0.90 (95% CI: 0.85, 0.94) on a full-field digital mammograph (FFDM) external dataset (86 patients), and an AUC of 0.92 (95% CI: 0.89, 0.95) on a CEM external dataset (193 patients).

CONCLUSION

The developed multi-feature fusion neural network achieved high performance in CEM image classification and was able to facilitate CEM-based breast cancer diagnosis.

CLINICAL RELEVANCE STATEMENT

Compared with low-energy images, CEM images have greater sensitivity and similar specificity in malignant breast lesion detection. The multi-feature fusion neural network is a promising computer-aided diagnostic tool for the clinical diagnosis of breast cancer.

KEY POINTS

• Deep convolutional neural networks have the potential to facilitate contrast-enhanced mammography-based breast cancer diagnosis. • The multi-feature fusion neural network reaches high accuracies in the classification of contrast-enhanced mammography images. • The developed model is a promising diagnostic tool to facilitate clinical breast cancer diagnosis.

Impact of age and breast thickness on mean glandular dose of standard digital mammography and digital breast tomosynthesis

This study compares the mean glandular dose (MGD) across 2D, 3D projection and Contrast-Enhanced Digital Mammography (CEDM) mammographic techniques. The important metadata were extracted from the digital mammography console. 650 subjects were clustered based on projections, age and CBT. The MGD of 2D, 3D, and CEDM was positively correlated with CBT but inversely correlated with the age factor. This study indicate MGD of CEDM was 16% and 22% lower compared to 2D and 3D techniques, respectively.

Contrast-Enhanced Mammography (CEM) Capability to Distinguish Molecular Breast Cancer Subtypes

With breast cancer ranking first among the most common malignant neoplasms in the world, new techniques of early detection are in even more demand than before. Our awareness of tumors' biology is expanding and may be used to treat patients more efficiently. A link between radiology and pathology was searched for in our study, as well as the answer to the question of whether a tumor type can be seen on contrast-enhanced mammography and if such knowledge may serve as part of precision medicine.

Evaluation of exposure factors of dual-energy contrast-enhanced mammography to optimize radiation dose with improved image quality

Background

Dual-energy contrast-enhanced mammography (DECEM) is an advanced breast imaging technique of digital mammography.

Purpose

To assess the total radiation dose received from complete DECEM using different combinations of exposure parameters for low- and high-energy images.

Materials and methods

A dedicated phantom with three different concentrations of iodine inserts was used. Each iodine insert was 10 mm in diameter and concentration of 1.0 mgI/cm³, 2.0 mgI/cm³, and 4.0 mgI/cm³. The phantom was exposed at varying kVp levels. Mean glandular dose (MGD) was estimated. Contrast to noise ratio (CNR) and figure of merit (FOM) of the iodine inserts were used to assess the image quality.

Results

The optimum CNR of the recombined images was obtained by using 28 kVp + 49 kVp tube voltage combination for 50 mm thickness, 50% fibroglandular phantom only with a 26% dose increase compared to the highest voltages (32 kVp + 49 kVp) that can be used for low energy (LE) and high energy (HE) imaging. The CNR value was increased with increasing iodine concentration (R² > 0.99).

Conclusion

The use of as low as possible tube voltage for the LE imaging of standard 50% fibroglandular–50% adipose, 50 mm thickness breast while using the highest tube voltage for HE imaging has reduced the MGD while keeping optimum image quality.

Cancer Conspicuity on Low-energy Images of Contrast-enhanced Mammography Compared With 2D Mammography

OBJECTIVE

Low-energy (LE) images of contrast-enhanced mammography (CEM) have been shown to be noninferior to digital mammography. However, our experience is that LE images are superior to 2D mammography. Our purpose was to compare cancer appearance on LE to 2D images.

METHODS

In this IRB-approved retrospective study, seven breast radiologists evaluated 40 biopsy-proven cancer cases on craniocaudal (CC) and mediolateral oblique (MLO) LE images and recent 2D images for cancer visibility, confidence in margins, and conspicuity of findings using a Likert scale. Objective measurements were performed using contrast-to-noise ratio (CNR) estimated from regions of interest placed on tumor and background parenchyma. Reader agreement was evaluated using Fleiss kappa. Per-reader comparisons were performed using Wilcoxon test and overall comparisons used three-way analysis of variance.

RESULTS

Low-energy images showed improved performance for visibility (CC LE 4.0 vs 2D 3.5, P < 0.001 and MLO LE 3.7 vs 2D 3.5, P = 0.01), confidence in margins (CC LE 3.2 vs 2D 2.8, P < 0.001 and MLO LE 3.1 vs 2D 2.9, P < 0.008), and conspicuity compared to tissue density compared to 2D mammography (CC LE 3.6 vs 2D 3.2, P < 0.001 and MLO LE 3.5 vs 2D 3.2, P < 0.001). The average CNR was significantly higher for LE than for digital mammography (CC 2.1 vs 3.2, P < 0.001 and MLO 2.1 vs 3.4, P < 0.001).

CONCLUSION

Our results suggest that cancers may be better visualized on the LE CEM images compared with the 2D digital mammogram.

Influence of double layer filter on mean glandular dose (MGD) and image quality in low energy image of contrast enhanced spectral mammography (LE-CESM)

INTRODUCTION

The aim of this study was to evaluate mean glandular dose (MGD) and image quality in low energy imaging from contrast-enhanced spectral mammography (CESM) when using double-layer filtration.

METHODOLOGY

A dedicated phantom was used to quantitatively estimate the MGD and image quality. The target slab of the phantom consisted of three iodine coins having a concentration of 1.0 mgI/cm³, 2.0 mgI/cm³, 4.0 mgI/cm³, a 100% adipose equivalent coin and a 100% glandular equivalent coin. The phantom was exposed using a semiautomated function at 28 k, 30 kV and 32 kV. MGD. Contrast to noise ratio (CNR) and figure of merit (FOM) were estimated for Mo/Rh, Mo/Rh + Cu, Mo/Rh + Al and Mo/Rh + Cd combinations using three breast equivalent compositions.

RESULTS

MGD was reduced up to a maximum of 1.03 mGy from 1.17 mGy for 100% adipose tissue. 1.18 mGy from 1.34 mGy for 50% glandular tissue and 1.39 mGy from 1.72 mGy for the 100% glandular phantom when using double-layer filtration. All of the above-mentioned results were obtained for the 50 mm phantom using 32 kV. CNR and FOM values were not significantly reduced with a double-layer filter when compared to a single-layer filter.

CONCLUSION

The present study concluded that Mo/Rh + Cu is the best combination to reduce the MGD significantly when compared to Mo/Rh + Al or Mo/Rh + Cd. Mo/Rh + Cu also achieved optimal image quality when compared to the Mo/Rh single filter combination.

IMPLICATIONS OF PRACTICE

The use of a double-layer filter in low energy imaging of CESM results in a significant reduction in MGD without degrading the quality of the image.

Quantitative Breast Density in Contrast-Enhanced Mammography

Contrast-enhanced mammography (CEM) demonstrates a potential role in personalized screening models, in particular for women at increased risk and women with dense breasts. In this study, volumetric breast density (VBD) measured in CEM images was compared with VBD obtained from digital mammography (DM) or tomosynthesis (DBT) images. A total of 150 women who underwent CEM between March 2019 and December 2020, having at least a DM/DBT study performed before/after CEM, were included. Low-energy CEM (LE-CEM) and DM/DBT images were processed with automatic software to obtain the VBD. VBDs from the paired datasets were compared by Wilcoxon tests. A multivariate regression model was applied to analyze the relationship between VBD differences and multiple independent variables certainly or potentially affecting VBD. Median VBD was comparable for LE-CEM and DM/DBT (12.73% vs. 12.39%), not evidencing any statistically significant difference (p = 0.5855). VBD differences between LE-CEM and DM were associated with significant differences of glandular volume, breast thickness, compression force and pressure, contact area, and nipple-to-posterior-edge distance, i.e., variables reflecting differences in breast positioning (coefficient of determination 0.6023; multiple correlation coefficient 0.7761). Volumetric breast density was obtained from low-energy contrast-enhanced spectral mammography and was not significantly different from volumetric breast density measured from standard mammograms.

Effects of bisphosphonate ligands and PEGylation on targeted delivery of gold nanoparticles for contrast-enhanced radiographic detection of breast microcalcifications

A preclinical murine model of hydroxyapatite (HA) breast microcalcifications (µcals), which are an important clinical biomarker for breast cancer detection, was used to investigate the independent effects of high affinity bisphosphonate (BP) ligands and a polyethylene glycol (PEG) spacer on targeted delivery of gold nanoparticles (Au NPs) for contrast-enhanced radiographic detection. The addition of BP ligands to PEGylated Au NPs (BP-PEG-Au NPs) resulted in five-fold greater binding affinity for targeting HA µcals, as expected, due to the strong binding affinity of BP ligands for calcium. Therefore, BP-PEG-Au NPs were able to target HA µcals in vivo after intramammary delivery, which enabled contrast-enhanced radiographic detection of µcals in both normal and radiographically dense mammary tissues similar to previous results for BP-Au NPs, while PEG-Au NPs did not. The addition of a PEG spacer between the BP targeting ligand and Au NP surface enabled improved in vivo clearance. PEG-Au NPs and BP-PEG-Au NPs were cleared from all mammary glands (MGs) and control MGs, respectively, within 24-48 h after intramammary delivery, while BP-Au NPs were not. PEGylated Au NPs were slowly cleared from MGs by lymphatic drainage and accumulated in the spleen. Histopathology revealed uptake of PEG-Au NPs and BP-PEG-Au NPs by macrophages in the spleen, liver, and MGs; there was no evidence of toxicity due to the accumulation of NPs in organs and tissues compared with untreated controls for up to 28 days after delivery. STATEMENT OF SIGNIFICANCE: Au NP imaging probes and therapeutics are commonly surface functionalized with PEG and/or high affinity targeting ligands for delivery. However, direct comparisons of PEGylated Au NPs with and without a targeting ligand, or ligand-targeted Au NPs with and without a PEG spacer, on in vivo targeting efficiency, biodistribution, and clearance are limited. Therefore, the results of this study are important for the rationale design of targeted NP imaging probes and therapeutics, including the translation of BP-PEG-Au NPs which enable improved sensitivity and specificity for the radiographic detection of abnormalities (e.g., µcals) in women with dense breast tissue.

The impact of contrast-enhanced spectral mammogram (CESM) and three-dimensional breast ultrasound (3DUS) on the characterization of the disease extend in cancer patients

OBJECTIVE

The main importance of imaging breast cancer is to guide conservative surgeries. In this study, we evaluated the role of contrast-enhanced spectral mammogram (CESM) in correlation with three-dimensional (3D) breast ultrasound in characterizing the extension of the intramammary cancer in view of the: (i) the size of the main tumor, (ii) the multiplicity of the breast cancer, and (iii) the peri-tumoral stromal involvement (i.e. free or intraductal extension of the cancer).

METHODS

The study is a prospective analysis that included 300 breast masses proved to be malignant. The masses were evaluated for their size, multiplicity and surrounding stromal involvement. Contrast-based mammography performed with low (22-33 kVp) and high (44-49 kVp) energy exposures that were taken after i.v. injection of contrast agent and followed by bilateral 3D breast ultrasound. Operative data were the gold standard reference.

RESULTS

There was no significant difference between the sizes of the included cancers as measured by CESM and 3D ultrasound and that measured at the pathological analysis. CESM showed higher accuracy (32.7%, n = 98) than 3D ultrasound (24.7%, n = 74) in the size agreement within 5% range. CESM was the most accurate modality (94%, n = 282) in detecting tumor multiplicity, followed by traditional sonomammogram (88%, n = 264), then 3D breast ultrasound (84%, n = 252). Intraductal extension of the breast cancer was best evaluated by the 3D ultrasound with an accuracy value of 98% (n = 294) compared to only 60% (n = 180) by CESM.

CONCLUSION

CESM is a recommended investigation in breast cancer to increase the accuracy of size measurement and the detection of multiple tumors. The addition of 3D ultrasound can enhance the detection of intraductal extension. Advances in knowledge: Choice of conservative breast surgery vs mastectomy is still a debate. We used an advanced, contrast-based, application of the mammogram: CESM and a non-invasive 3D breast ultrasound in the assessment of the local extension of the breast cancer regarding size, perifocal stromal infiltration and multiplicity to guide the selection of proper management in proved cases of breast cancer.

Comparison of screening CEDM and MRI for women at increased risk for breast cancer: A pilot study

OBJECTIVES

Contrast enhanced digital mammography (CEDM) is a new breast imaging technology increasingly used in the diagnostic setting but its utility in the pure screening setting has not been reported. The goal of this pilot study is to prospectively compare screening CEDM to breast MRI in women with an increased risk for breast cancer.

METHODS

In this IRB-approved HIPAA-compliant study, 318 women at increased breast cancer risk were consented (December 2012-May 2015) to undergo CEDM in addition to their scheduled MRI. CEDM was performed within 30days of screening MRI. CEDM was interpreted blinded to MRI. The reference standard was defined as a combination of pathology and 2-year imaging follow-up.

RESULTS

Data from 307/318 patients were evaluable. Three cancers (two invasive cancers, one ductal carcinoma in situ) were detected at first round screening: MRI detected all three and CEDM detected the two invasive cancers. None of the three cancers was seen on the low energy mammograms which are comparable to conventional mammography. At 2year imaging follow up, there were 5 additional screen detected cancers and no palpable cancers. The positive predictive value 3 (PPV₃) for CEDM was 15% (2/13, 95% CI: 2-45%) and 14% for MRI (3/21, 95% CI: 3-36%). The specificity of CEDM and MRI were 94.7% and 94.1% respectively.

CONCLUSIONS

Both CEDM and MRI detected additional cancers not seen on conventional mammography, primarily invasive cancers. Our pilot data suggest that CEDM could be valuable as a supplemental imaging exam for women at increased risk for breast cancer who do not meet the criteria for MRI or for whom access to MRI is limited. Validation in larger multi institutional trials is warranted.

Contrast enhanced dual energy spectral mammogram, an emerging addendum in breast imaging

OBJECTIVE

To assess the role of contrast-enhanced dual-energy spectral mammogram (CEDM) as a problem-solving tool in equivocal cases.

METHODS

44 consenting females with equivocal findings on full-field digital mammogram underwent CEDM. All the images were interpreted by two radiologists independently. Confidence of presence was plotted on a three-point Likert scale and probability of cancer was assigned on Breast Imaging Reporting and Data System scoring. Histopathology was taken as the gold standard. Statistical analyses of all variables were performed.

RESULTS

44 breast lesions were included in the study, among which 77.3% lesions were malignant or precancerous and 22.7% lesions were benign or inconclusive. 20% of lesions were identified only on CEDM. True extent of the lesion was made out in 15.9% of cases, multifocality was established in 9.1% of cases and ductal extension was demonstrated in 6.8% of cases. Statistical significance for CEDM was p-value <0.05. Interobserver kappa value was 0.837.

CONCLUSION

CEDM has a useful role in identifying occult lesions in dense breasts and in triaging lesions. In a mammographically visible lesion, CEDM characterizes the lesion, affirms the finding and better demonstrates response to treatment. Hence, we conclude that CEDM is a useful complementary tool to standard mammogram. Advances in knowledge: CEDM can detect and demonstrate lesions even in dense breasts with the advantage of feasibility of stereotactic biopsy in the same setting. Hence, it has the potential to be a screening modality with need for further studies and validation.

Contrast-enhanced spectral mammography in recalls from the Dutch breast cancer screening program: validation of results in a large multireader, multicase study

OBJECTIVES

Contrast-enhanced spectral mammography (CESM) is a promising problem-solving tool in women referred from a breast cancer screening program. We aimed to study the validity of preliminary results of CESM using a larger panel of radiologists with different levels of CESM experience.

METHODS

All women referred from the Dutch breast cancer screening program were eligible for CESM. 199 consecutive cases were viewed by ten radiologists. Four had extensive CESM experience, three had no CESM experience but were experienced breast radiologists, and three were residents. All readers provided a BI-RADS score for the low-energy CESM images first, after which the score could be adjusted when viewing the entire CESM exam. BI-RADS 1-3 were considered benign and BI-RADS 4-5 malignant. With this cutoff, we calculated sensitivity, specificity and area under the ROC curve.

RESULTS

CESM increased diagnostic accuracy in all readers. The performance for all readers using CESM was: sensitivity 96.9 % (+3.9 %), specificity 69.7 % (+33.8 %) and area under the ROC curve 0.833 (+0.188).

CONCLUSION

CESM is superior to conventional mammography, with excellent problem-solving capabilities in women referred from the breast cancer screening program. Previous results were confirmed even in a larger panel of readers with varying CESM experience.

KEY POINTS

• CESM is consistently superior to conventional mammography • CESM increases diagnostic accuracy regardless of a reader's experience • CESM is an excellent problem-solving tool in recalls from screening programs.

Evaluation of low-energy contrast-enhanced spectral mammography images by comparing them to full-field digital mammography using EUREF image quality criteria

Objective

Contrast-enhanced spectral mammography (CESM) examination results in a low-energy (LE) and contrast-enhanced image. The LE appears similar to a full-field digital mammogram (FFDM). Our aim was to evaluate LE CESM image quality by comparing it to FFDM using criteria defined by the European Reference Organization for Quality Assured Breast Screening and Diagnostic Services (EUREF).

Methods

A total of 147 cases with both FFDM and LE images were independently scored by two experienced radiologists using these (20) EUREF criteria. Contrast detail measurements were performed using a dedicated phantom. Differences in image quality scores, average glandular dose, and contrast detail measurements between LE and FFDM were tested for statistical significance.

Results

No significant differences in image quality scores were observed between LE and FFDM images for 17 out of 20 criteria. LE scored significantly lower on one criterion regarding the sharpness of the pectoral muscle (p < 0.001), and significantly better on two criteria on the visualization of micro-calcifications (p = 0.02 and p = 0.034). Dose and contrast detail measurements did not reveal any physical explanation for these observed differences.

Conclusions

Low-energy CESM images are non-inferior to FFDM images. From this perspective FFDM can be omitted in patients with an indication for CESM.

Key Points

• Low-energy CESM images are non-inferior to FFDM images.

• Micro-calcifications are significantly more visible on LE CESM than on FFDM.

• There is no physical explanation for this improved visibility of micro-calcifications.

• There is no need for an extra FFDM when CESM is indicated.