Digital Breast Tomosynthesis Data Research Articles

Imaging phenotype evaluation from digital breast tomosynthesis data: A preliminary study

Background:Digital breast tomosynthesis (DBT) has been widely adopted as a supplemental imaging modality for diagnostic evaluation of breast cancer and confirmation studies. In this study, a deep learning-based method for characterizing breast tissue patterns in DBT data is presented. Methods:A set of 5388 2D image patches was produced from 230 right mediolateral oblique, 259 left mediolateral oblique, 18 right craniocaudal, and 15 left craniocaudal single-breast DBT studies, using slice-wise annotations of abnormalities and normal tissue. We implemented a patch classifier to predict samples according to two differing scenarios and train it using the patch dataset. First, tissue samples were classified into the following classes: malignant, benign, and normal breast tissue. Second, tissue samples were classified into the following classes: malignant mass, benign mass, benign architectural distortion, malignant architectural distortion, and normal breast tissue. We employed transfer learning and initialized the model base layers with existing pre-trained weights obtained from Globally-Aware Multiple Instance Classifier. Results:High class-wise recall values of 0.8906, 0.8541 and 0.7345 and specificities 0.9558, 0.9575 and 0.8830 were obtained for normal, benign, and malignant classification, respectively. More intricate classification yielded class-wise recall values of 0.8708, 0.8299, 0.9444 and 0.5723 and specificities 0.9406, 0.9833, 0.8943 and 0.9652 for benign mass, normal, malignant architectural distortion, and malignant mass, respectively. However, benign architectural distortion was confused with benign mass and malignant architectural distortion. Conclusions:Combining the proposed phenotype classifier with the commonly used malignant-benign-normal classification enables a more detailed assessment of digital breast tomosynthesis images.

Denoising digital breast tomosynthesis projections using deep learning with synthetic data as training set.

Image denoising based on deep neural networks (DNN) needs a big dataset containing digital breast tomosynthesis (DBT) projections acquired in different radiation doses to be trained, which is impracticable. Therefore, we propose extensively investigating the use of synthetic data generated by software for training DNNs to denoise DBT real data. The approach consists of generating a synthetic dataset representative of the DBT sample space by software, containing noisy and original images. Synthetic data were generated in two different ways: (a)virtual DBT projections generated by OpenVCT and (b)noisy images synthesized from photography regarding noise models used in DBT (e.g., Poisson-Gaussian noise). Then, DNN-based denoising techniques were trained using a synthetic dataset and tested for denoising physical DBT data. Results were evaluated in quantitative (PSNR and SSIM measures) and qualitative (visual analysis) terms. Furthermore, a dimensionality reduction technique (t-SNE) was used for visualization of sample spaces of synthetic and real datasets. The experiments showed that training DNN models with synthetic data could denoise DBT real data, achieving competitive results to traditional methods in quantitative terms but showing a better balance between noise filtering and detail preservation in a visual analysis. T-SNE enables us to visualize if synthetic and real noises are in the same sample space. We propose a solution for the lack of suitable training data to train DNN models for denoising DBT projections, showing that we just need the synthesized noise to be in the same sample space as the target image.

Automatic Classification of Simulated Breast Tomosynthesis Whole Images for the Presence of Microcalcification Clusters Using Deep CNNs.

Microcalcification clusters (MCs) are among the most important biomarkers for breast cancer, especially in cases of nonpalpable lesions. The vast majority of deep learning studies on digital breast tomosynthesis (DBT) are focused on detecting and classifying lesions, especially soft-tissue lesions, in small regions of interest previously selected. Only about 25% of the studies are specific to MCs, and all of them are based on the classification of small preselected regions. Classifying the whole image according to the presence or absence of MCs is a difficult task due to the size of MCs and all the information present in an entire image. A completely automatic and direct classification, which receives the entire image, without prior identification of any regions, is crucial for the usefulness of these techniques in a real clinical and screening environment. The main purpose of this work is to implement and evaluate the performance of convolutional neural networks (CNNs) regarding an automatic classification of a complete DBT image for the presence or absence of MCs (without any prior identification of regions). In this work, four popular deep CNNs are trained and compared with a new architecture proposed by us. The main task of these trainings was the classification of DBT cases by absence or presence of MCs. A public database of realistic simulated data was used, and the whole DBT image was taken into account as input. DBT data were considered without and with preprocessing (to study the impact of noise reduction and contrast enhancement methods on the evaluation of MCs with CNNs). The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance. Very promising results were achieved with a maximum AUC of 94.19% for the GoogLeNet. The second-best AUC value was obtained with a new implemented network, CNN-a, with 91.17%. This CNN had the particularity of also being the fastest, thus becoming a very interesting model to be considered in other studies. With this work, encouraging outcomes were achieved in this regard, obtaining similar results to other studies for the detection of larger lesions such as masses. Moreover, given the difficulty of visualizing the MCs, which are often spread over several slices, this work may have an important impact on the clinical analysis of DBT images.

Abstract 1929: Deep-learning-enabled volumetric breast density estimation with digital breast tomosynthesis

Abstract Background: It has been widely established that breast density is an independent breast cancer risk factor. With the increasing utilization of digital breast tomosynthesis (DBT) in breast cancer screening, there is an opportunity to estimate volumetric breast density (VBD) routinely. However, current available methods extrapolate VBD from 2D images acquired with DBT and/or depend on the existence of raw DBT data which is rarely archived by clinical centers due to cost and storage constraints. This study aims to harness deep learning to develop a computational tool for VBD assessment based solely on 3D reconstructed, “for presentation” DBT images. Methods: We retrospectively analyzed 1,080 negative DBT screening exams (09/20/2011 - 11/25/2016) from the Hospital of the University of Pennsylvania (mean age ± SD, 57 ± 11 years; mean BMI ± SD, 28.7 ± 7.1 kg/m2; racial makeup, 41.2% White, 54.2% Black, 4.6% Other), for which both 3D reconstructed and 2D raw DBT images (Selenia Dimensions, Hologic Inc) were available. All available standard views (left and right mediolateral-oblique and cranio-caudal views) were included for each exam, leading to 7,850 DBT views. Corresponding 3D reference-standard tissue segmentations were generated from a previously validated software that uses both 3D reconstructed slices and raw 2D DBT data to provide VBD metrics, shown to be strongly correlated with VBD measures from MRI image volumes. We based our deep learning algorithm on the U-Net architecture within the open-source Generally Nuanced Deep Learning Framework (GaNDLF) and created a 3-label image segmentation task (background, dense tissue, and fatty tissue). Our dataset was randomly split into training (70%), validation (15%) and test (15%) sets, while ensuring that all views of the same DBT exam were assigned to the same set. The performance of our deep learning algorithm against the corresponding reference-standard segmentations was measured in terms of Dice scores (DSC), with 0 signifying no overlap and 1 signifying perfect overlap, overall, as well as separately for each label. Results: After training was complete, our deep learning algorithm achieved a DSC of 0.78 on the validation, as well as on the test set. Our method accurately segmented background from breast tissue (DSC = 0.94) and demonstrated moderate to high performance in segmenting dense and fatty tissue, respectively (DSC = 0.49 and 0.89). Conclusion: Our preliminary analysis suggests that deep learning shows promise in the estimation of VBD using 3D DBT reconstructed, “for presentation” images. Future work involving transfer learning based on ground truth masks by clinical radiologists could further enhance this method’s performance. In view of rapid clinical conversion to DBT screening, such a tool has the potential to enable large retrospective epidemiologic and personalized risk assessment studies of breast density with DBT. Citation Format: Vinayak S. Ahluwalia, Walter Mankowski, Sarthak Pati, Spyridon Bakas, Ari Brooks, Celine M. Vachon, Emily F. Conant, Aimilia Gastounioti, Despina Kontos. Deep-learning-enabled volumetric breast density estimation with digital breast tomosynthesis [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1929.

Artificial-intelligence-driven volumetric breast density estimation with digital breast tomosynthesis in a racially diverse screening cohort.

e13538 Background: Breast density is considered a well-established breast cancer risk factor. As quasi-3D, digital breast tomosynthesis (DBT) becomes increasingly utilized for screening, there is an opportunity to routinely estimate volumetric breast density (VBD). However, current methods extrapolate VBD from 2D images acquired with DBT and/or depend on the existence of raw DBT data, which is rarely archived due to cost and storage constraints. Using a racially diverse screening cohort, this study evaluates the potential of deep learning for VBD assessment based solely on 3D reconstructed, “for presentation” DBT images. Methods: We retrospectively analyzed 1,080 negative DBT screening exams obtained between 2011 and 2016 from the Hospital of the University of Pennsylvania (racial makeup, 41.2% White, 54.2% Black, 4.6% Other; mean age ± SD, 57 ± 11 years; mean BMI ± SD, 28.7 ± 7.1 kg/m2), for which both 2D raw and 3D reconstructed DBT images (Selenia Dimensions, Hologic Inc) were available. Corresponding 3D reference-standard tissue segmentations were generated from previously validated software that uses both 3D reconstructed slices and raw 2D DBT data to provide VBD metrics, shown to be strongly correlated with VBD measures from MRI image volumes. We based our deep learning algorithm on the U-Net architecture within the open-source Generally Nuanced Deep Learning Framework (GaNDLF) and created a 3-label image segmentation task (background, dense tissue, and fatty tissue). Our dataset was randomly split into training (70%), validation (15%) and test (15%) sets. We report on the performance of our deep learning algorithm against corresponding reference-standard segmentations for a cranio-caudal (CC) view-only subset. We also stratify our results by the two main racial groups (White and Black). Our evaluation measure was the weighted Dice score (DSC), with 0 signifying no overlap and 1 signifying perfect overlap, overall and separately for each label. Results: Our deep learning algorithm achieved an overall DSC of 0.682 (STD = 0.136). It accurately segmented the three labels of background, fatty tissue, and dense tissue, with DSC scores of 0.995, 0.884, and 0.617, respectively. DSC for White and Black women were 0.688 (STD = 0.127) and 0.680 (STD = 0.146), respectively. Conclusions: Our preliminary analysis suggests that deep learning shows promise in the estimation of VBD using 3D DBT reconstructed, “for presentation” CC view images and does not demonstrate bias among racial groups. Future work involving optimization of performance in other breast views as well as transfer learning based on ground truth masks by clinical radiologists could further enhance this method. In view of rapid clinical conversion to DBT screening, such a tool has the potential to enable large retrospective epidemiological and personalized risk assessment studies of breast density with DBT.

Architectural distortion detection based on superior-inferior directional context and anatomic prior knowledge in digital breast tomosynthesis.

In 2020, breast cancer becomes the most leading diagnosed cancer all over the world. The burden is increasing in the prevention and treatment of breast cancer. Accurately detecting breast lesions in screening images is important for early detection of cancer. Architectural distortion (AD) is one of the breast lesions that need to be detected. To develop a deep-learning-based computer-aided detection (CADe) model for AD in digital breast tomosynthesis (DBT). This model uses the superior-inferior directional context of DBT and anatomic prior knowledge to reduce false positive (FP). It can identify some negative samples that cannot be distinguished by deep learning features. The proposed CADe model consists of three steps. In the first step, a deep learning detection network detects two-dimensional (2D) candidates of ADs in DBT slices with the inputs preprocessed by Gabor filters and convergence measure. In the second step, three-dimensional (3D) candidates are obtained by stacking 2D candidates along superior-inferior direction. In the last step, FP reduction for 3D candidates is implemented based on superior-inferior directional context and anatomic prior knowledge of breast. DBT data from 99 cases with AD were used as the training set to train the CADe model, and data from 208 cases were used as an independent test set (including 108 cases with AD and 100 cases without AD as the control group). The free-response receiver operating characteristic and mean true positive fraction (MTPF) in the range of 0.05-2.0 FPs per volume are used to evaluate the model. Compared with the baseline model based on convergence measure, our proposed method demonstrates significant improvement (MTPF: 0.2826±0.0321vs. 0.6640±0.0399). Results of an ablation study show that our proposed context- and anatomy-based FP reduction methods improve the detection performance. The number of FPs per DBT volume reduces from 2.47 to 1.66 at 80% sensitivity after employing these two schemes. The deep learning model demonstrates practical value for AD detection. The results indicate that introducing superior-inferior directional context and anatomic prior knowledge into model can indeed reduce FPs and improve the performance of CADe model.

Intratumoral analysis of digital breast tomosynthesis for predicting the Ki-67 level in breast cancer: A multi-center radiomics study.

To non-invasively evaluate the Ki-67 level in digital breast tomosynthesis (DBT) images of breast cancer (BC) patients based on subregional radiomics. A total of 266 patients who underwent DBT scans were consecutively enrolled at two centers, between September 2017 and September 2021. The whole tumor region was partitioned into various intratumoral subregions, based on individual- and population-level clustering. Handcrafted radiomics and deep learning-based features were extracted from the subregions and from the whole tumor region, and were selected by least absolute shrinkage and selection operator (LASSO) regression, yielding radiomics signatures (RSs). The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to assess the developed RSs. Each breast tumor region was partitioned into an inner subregion (S1) and a marginal subregion (S2). The RSs derived from S1 always generated higher AUCs compared with those from S2 or from the whole tumor region (W), for the external validation cohort (AUCs, S1 vs. W, handcrafted RSs: 0.583 [95% CI, 0.429-0.727] vs. 0.559 [95% CI, 0.405-0.705], p-value: 0.920; deep RSs: 0.670 [95% CI, 0.516-0.802] vs. 0.551 [95% CI, 0.397-0.698], p-value: 0.776). The fusion RSs, combining handcrafted and deep learning-based features derived from S1, yielded the highest AUCs of 0.820 (95% CI, 0.714-0.900) and 0.792 (95% CI, 0.647-0.897) for the internal and external validation cohorts, respectively. The subregional radiomics approach can accurately predict the Ki-67 level based on DBT data; thus, it may be used as a potential non-invasive tool for preoperative treatment planning in BC.

Benefit of digital breast tomosynthesis in symptomatic young women (≤30 years) diagnosed with BI-RADS category 4 or 5 on ultrasound

To evaluate the addition of digital breast tomosynthesis (DBT) in the diagnosis of breast lesions in symptomatic young Chinese women (≤30 years) diagnosed with Breast Imaging Reporting and Data System (BI-RADS) category 4 or 5 on ultrasound, and demonstrate the potential use of combining DBT with ultrasound. This retrospective analysis included 5 years of digital mammography (DM) and DBT data (January 2015 to July 2020). In total, 768 DBT and DM examinations were performed in 713 young women. The results were determined by pathological assessment. Diagnostic performance was measured based on the sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and receiver operating characteristic area under the curve (AUC). Compared with DM alone, DBT+DM increased the sensitivity from 82.5% to 93.2%, specificity from 70.8% to 84%, accuracy from 74% to 86.5%, NPV from 93.6% to 97.4% (all p<0.01). The AUC of DBT+DM (0.946, 95% confidence interval [CI]: 0.927-0.960) was greater than that of DM (0.884, 95% CI: 0.859-0.905; p<0.001). The differences in the BI-RADS category distributions of malignant and benign lesions were both statistically significant (p<0.001). DM alone led to 36 false-negative diagnoses, whereas the inclusion of DBT identified breast cancer in 22 of those cases. There were 4.9% (10/206) false-negative diagnoses in ultrasound. After adding DBT, four breast cancers were detected. An additional six breast cancers were diagnosed by biopsy based on an assessment of BI-RADS 4A by DBT/DM. DBT+DM significantly improves the diagnostic performance in this young population, especially in young people with higher breast density. Moreover, DBT is an effective supplementary examination to ultrasound.

Could Breast Tomosynthesis With Synthetic View Mammography Aid Standard Two-Dimensional Mammography in Evaluation at Symptomatic Triple Assessment Breast Clinics?

BackgroundThis study aimed to determine whether breast tomosynthesis and synthetic view mammography (SM) can aid standard two-dimensional mammography (S2DM) in the evaluation of symptomatic women at triple assessment clinics (TACs).MethodologyDigital breast tomosynthesis (DBT), SM, and S2DM were performed on 400 patients at symptomatic breast TACs between September 2020 and November 2020. Diagnostic findings on mammography and ultrasound were retrospectively recorded and analyzed by a breast-trained radiologist with 13 years of clinical experience. Pathology results for all biopsies were recorded and correlated with the mammographic and ultrasound findings.ResultsThe combination of DBT and SM was superior to S2DM in the following settings: calcifications were more conspicuous on SM than S2DM in 44% of patients with calcifications. Mass margins were better defined on DBT than S2DM in 71% of patients with masses. Distortion was more easily detectable in 11% of patients with distortion on SM and in 44% of patients with distortion on DBT compared with S2DM. All malignant lesions were identified on all modalities.ConclusionsCombined DBT and SM demonstrated several advantages over S2DM alone. SM can provide equal and sometimes superior diagnostic performance with the added benefit of requiring no additional radiation exposure when synthesized from DBT data. We conclude that adding DBT and SM to S2DM aids in the assessment of symptomatic women, and omitting S2DM results in no loss of clinically relevant information for women presenting to symptomatic breast clinics.

Utility of Digital Breast Tomosynthesis with Two-Dimensional Synthesized Mammography Images: A Pictorial Essay.

Background Mammography has been established as the key modality in the detection and diagnosis of breast cancers. Digital breast tomosynthesis (DBT) has emerged as a mammographic technique which allows improved visualization of abnormalities by reducing the effect of overlapping breast tissue. Purpose This article is a pictorial essay which highlights the advantages of DBT with two-dimensional (2D) synthesized mammography (2DSM) images, its clinical applications, and its role in breast imaging. Materials and Methods Selenia Dimensions HD mammography machine performs DBT which acquires a series of low-dose digital mammographic images of the compressed breast followed by full-field digital mammography. Software using specialized algorithms helps to create a 2DSM image reconstructed from the DBT data set. The images are interpreted on a dedicated work station on high-resolution monitors by the radiologist. American College of Radiology Breast Imaging-Reporting and Data System (BI-RADS) lexicon is used for reporting. High-resolution breast ultrasound which includes evaluation of the axilla is done for all cases. Conclusion DBT improves detection and better characterization of lesions which thereby increases confidence of interpretation of mammograms and assigning BI-RADS categories for further management.

Deep Convolutional Neural Network With Adversarial Training for Denoising Digital Breast Tomosynthesis Images.

Digital breast tomosynthesis (DBT) is a quasi-three-dimensional imaging modality that can reduce false negatives and false positives in mass lesion detection caused by overlapping breast tissue in conventional two-dimensional (2D) mammography. The patient dose of a DBT scan is similar to that of a single 2D mammogram, while acquisition of each projection view adds detector readout noise. The noise is propagated to the reconstructed DBT volume, possibly obscuring subtle signs of breast cancer such as microcalcifications (MCs). This study developed a deep convolutional neural network (DCNN) framework for denoising DBT images with a focus on improving the conspicuity of MCs as well as preserving the ill-defined margins of spiculated masses and normal tissue textures. We trained the DCNN using a weighted combination of mean squared error (MSE) loss and adversarial loss. We configured a dedicated x-ray imaging simulator in combination with digital breast phantoms to generate realistic in silico DBT data for training. We compared the DCNN training between using digital phantoms and using real physical phantoms. The proposed denoising method improved the contrast-to-noise ratio (CNR) and detectability index (d') of the simulated MCs in the validation phantom DBTs. These performance measures improved with increasing training target dose and training sample size. Promising denoising results were observed on the transferability of the digital-phantom-trained denoiser to DBT reconstructed with different techniques and on a small independent test set of human subject DBT images.

DIR-DBTnet: Deep iterative reconstruction network for three-dimensional digital breast tomosynthesis imaging.

The goal of this study is to develop a three-dimensional (3D) iterative reconstruction framework based on the deep learning (DL) technique to improve the digital breast tomosynthesis (DBT) imaging performance. In this work, the DIR-DBTnet is developed for DBT image reconstruction by mapping the conventional iterative reconstruction (IR) algorithm to the deep neural network. By design, the DIR-DBTnet learns and optimizes the regularizer and the iteration parameters automatically during the network training with a large amount of simulated DBT data. Numerical, experimental, and clinical data are used to evaluate its performance. Quantitative metrics such as the artifact spread function (ASF), breast density, and the signal difference to noise ratio (SDNR) are measured to assess the image quality. Results show that the proposed DIR-DBTnet is able to reduce the in-plane shadow artifacts and the out-of-plane signal leaking artifacts compared to the filtered backprojection (FBP) and the total variation (TV)-based IR methods. Quantitatively, the full width half maximum (FWHM) of the measured ASF from the clinical data is 27.1% and 23.0% smaller than those obtained with the FBP and TV methods, while the SDNR is increased by 194.5% and 21.8%, respectively. In addition, the breast density obtained from the DIR-DBTnet network is more accurate and consistent with the ground truth. In conclusion, a deep iterative reconstruction network, DIR-DBTnet, has been proposed for 3D DBT image reconstruction. Both qualitative and quantitative analyses of the numerical, experimental, and clinical results demonstrate that the DIR-DBTnet has superior DBT imaging performance than the conventional algorithms.

Technical evaluation of image quality in synthetic mammograms obtained from 15° and 40° digital breast tomosynthesis in a commercial system: a quantitative comparison.

Digital breast tomosynthesis (DBT) has recently gained interest both for breast cancer screening and diagnosis. Its employment has increased also in conjunction with digital mammography (DM), to improve cancer detection and reduce false positive recall rate. Synthetic mammograms (SMs) reconstructed from DBT data have been introduced to replace DM in the DBT + DM approach, for preserving the benefits of the dual-acquisition modality whilst reducing radiation dose and compression time. Therefore, different DBT models have been commercialized and the effective potential of each system has been investigated. In particular, wide-angle DBT was shown to provide better depth resolution than narrow-angle DBT, while narrow-angle DBT allows better identification of microcalcifications compared to wide-angle DBT. Given the increasing employment of SMs as supplement to DBT, a comparison of image quality between SMs obtained in narrow-angle and wide-angle DBT is of practical interest. Therefore, the aim of this phantom study was to evaluate and compare the image quality of SMs reconstructed from 15° (SM15) and 40° (SM40) DBT in a commercial system. Spatial resolution, noise and contrast properties were evaluated through the modulation transfer function (MTF), noise power spectrum, maps of signal-to-noise ratio (SNR), image contrast, contrast-to-noise ratio (CNR) and contrast-detail (CD) thresholds. SM40 expressed higher MTF than SM15, but also lower SNR and CNR levels. SM15 and SM40 were characterized by slight different texture, and a different behavior in terms of contrast was found. SM15 provided better CD performances than SM40. These results suggest that the employment of wide/narrow-angle DBT + SM images should be optimized based on the specific image task.

Mass Detection and Segmentation in Digital Breast Tomosynthesis Using 3D-Mask Region-Based Convolutional Neural Network: A Comparative Analysis.

Digital breast tomosynthesis (DBT) is an emerging breast cancer screening and diagnostic modality that uses quasi-three-dimensional breast images to provide detailed assessments of the dense tissue within the breast. In this study, a framework of a 3D-Mask region-based convolutional neural network (3D-Mask RCNN) computer-aided diagnosis (CAD) system was developed for mass detection and segmentation with a comparative analysis of performance on patient subgroups with different clinicopathological characteristics. To this end, 364 samples of DBT data were used and separated into a training dataset (n = 201) and a testing dataset (n = 163). The detection and segmentation results were evaluated on the testing set and on subgroups of patients with different characteristics, including different age ranges, lesion sizes, histological types, lesion shapes and breast densities. The results of our 3D-Mask RCNN framework were compared with those of the 2D-Mask RCNN and Faster RCNN methods. For lesion-based mass detection, the sensitivity of 3D-Mask RCNN-based CAD was 90% with 0.8 false positives (FPs) per lesion, whereas the sensitivity of the 2D-Mask RCNN- and Faster RCNN-based CAD was 90% at 1.3 and 2.37 FPs/lesion, respectively. For breast-based mass detection, the 3D-Mask RCNN generated a sensitivity of 90% at 0.83 FPs/breast, and this framework is better than the 2D-Mask RCNN and Faster RCNN, which generated a sensitivity of 90% with 1.24 and 2.38 FPs/breast, respectively. Additionally, the 3D-Mask RCNN achieved significantly (p < 0.05) better performance than the 2D methods on subgroups of samples with characteristics of ages ranged from 40 to 49 years, malignant tumors, spiculate and irregular masses and dense breast, respectively. Lesion segmentation using the 3D-Mask RCNN achieved an average precision (AP) of 0.934 and a false negative rate (FNR) of 0.053, which are better than those achieved by the 2D methods. The results suggest that the 3D-Mask RCNN CAD framework has advantages over 2D-based mass detection on both the whole data and subgroups with different characteristics.

Optimization of Breast Tomosynthesis Visualization through 3D Volume Rendering.

3D volume rendering may represent a complementary option in the visualization of Digital Breast Tomosynthesis (DBT) examinations by providing an understanding of the underlying data at once. Rendering parameters directly influence the quality of rendered images. The purpose of this work is to study the influence of two of these parameters (voxel dimension in z direction and sampling distance) on DBT rendered data. Both parameters were studied with a real phantom and one clinical DBT data set. The voxel size was changed from 0.085 × 0.085 × 1.0 mm3 to 0.085 × 0.085 × 0.085 mm3 using ten interpolation functions available in the Visualization Toolkit library (VTK) and several sampling distance values were evaluated. The results were investigated at 90º using volume rendering visualization with composite technique. For phantom quantitative analysis, degree of smoothness, contrast-to-noise ratio, and full width at half maximum of a Gaussian curve fitted to the profile of one disk were used. Additionally, the time required for each visualization was also recorded. Hamming interpolation function presented the best compromise in image quality. The sampling distance values that showed a better balance between time and image quality were 0.025 mm and 0.05 mm. With the appropriate rendering parameters, a significant improvement in rendered images was achieved.

Impact of total variation minimization in volume rendering visualization of breast tomosynthesis data

Background and objectiveTotal Variation (TV) minimization algorithms have achieved great attention due to the virtue of decreasing noise while preserving edges. The purpose of this work is to implement and evaluate two TV minimization methods in 3D. Their performance is analyzed through 3D visualization of digital breast tomosynthesis (DBT) data with volume rendering. MethodsBoth filters were studied with real phantom and one clinical DBT data. One algorithm was applied sequentially to all slices and the other was applied to the entire volume at once. The suitable Lagrange multiplier used in each filter equation was studied to reach the minimum 3D TV and the maximum contrast-to-noise ratio (CNR). Imaging blur was measured at 0° and 90° using two disks with different diameters (0.5 mm and 5.0 mm) and equal thickness. The quality of unfiltered and filtered data was analyzed with volume rendering at 0° and 90°. ResultsFor phantom data, with the sequential filter, a decrease of 25% in 3D TV value and an increase of 19% and 30% in CNR at 0° and 90°, respectively, were observed. When the filter is applied directly in 3D, TV value was reduced by 35% and an increase of 36% was achieved both for CNR at 0° and 90°. For the smaller disk, variations of 0% in width at half maximum (FWHM) at 0° and a decrease of about 2.5% for FWHM at 90° were observed for both filters. For the larger disk, there was a 2.5% increase in FWHM at 0° for both filters and a decrease of 6.28% and 1.69% in FWHM at 90° with the sequential filter and the 3D filter, respectively. When applied to clinical data, the performance of each filter was consistent with that obtained with the phantom. ConclusionsData analysis confirmed the relevance of these methods in improving quality of DBT images. Additionally, this type of 3D visualization showed that it may play an important complementary role in DBT imaging. It allows to visualize all DBT data at once and to analyze properly filters applied to all the three dimensions.Concise AbstractTotal Variation (TV) minimization algorithms are one compressed sensing technique that has achieved great attention due to the virtue of decrease noise while preserve edges transitions. The purpose of this work is to solve the same TV minimization problem in DBT data, by studying two 3D filters. The obtained results were analyzed at 0° and 90° with a 3D visualization through volume rendering. The filters differ in their application. One considers a slice-by-slice optimization, sequentially traversing all slices of the data. The other considers the intensity values of adjacent slices to make this optimization on each voxel. The performance of each filter was also tested with a clinical case. The results obtained were very encouraging with a significantly increased contrast to noise ratio at 0° and 90° and a small reduction in blur at 90° (slight reduction of the out-of-plane artifact).

GPU acceleration of a model-based iterative method for Digital Breast Tomosynthesis

Digital Breast Tomosynthesis (DBT) is a modern 3D Computed Tomography X-ray technique for the early detection of breast tumors, which is receiving growing interest in the medical and scientific community. Since DBT performs incomplete sampling of data, the image reconstruction approaches based on iterative methods are preferable to the classical analytic techniques, such as the Filtered Back Projection algorithm, providing fewer artifacts. In this work, we consider a Model-Based Iterative Reconstruction (MBIR) method well suited to describe the DBT data acquisition process and to include prior information on the reconstructed image. We propose a gradient-based solver named Scaled Gradient Projection (SGP) for the solution of the constrained optimization problem arising in the considered MBIR method. Even if the SGP algorithm exhibits fast convergence, the time required on a serial computer for the reconstruction of a real DBT data set is too long for the clinical needs. In this paper we propose a parallel SGP version designed to perform the most expensive computations of each iteration on Graphics Processing Unit (GPU). We apply the proposed parallel approach on three different GPU boards, with computational performance comparable with that of the boards usually installed in commercial DBT systems. The numerical results show that the proposed GPU-based MBIR method provides accurate reconstructions in a time suitable for clinical trials.

Comparative analysis between synthetic mammography reconstructed from digital breast tomosynthesis and full-field digital mammography for breast cancer detection and visibility

PurposeTo compare observer performance between synthetic mammography (2DSM) and full-field digital mammography (FFDM) for breast cancer detection and visibility. MethodA retrospective analysis was conducted on 136 histopathologically proven cases of breast cancer in patients who underwent FFDM and digital breast tomosynthesis (DBT). 2DSM images were reconstructed from DBT data, and 2DSM and FFDM images were reviewed and evaluated for mammographic features, probability of malignancy (BI-RADS classification), and lesion conspicuity. DBT images were not reviewed. Statistical differences in cancer detection rates between 2DSM and FFDM images were analyzed using the McNemar test, agreement on BI-RADS assessment between 2DSM and FFDM was assessed using Cohen’s kappa test, and the Wilcoxon’s signed rank test was used to compare visibility scores. ResultsMean cancer detection rates with 2DSM and FFDM images were 84.6 % and 87.8 %, respectively. In subgroup analyses, differences in breast density, tumor size, and presence of calcifications were not statistically significant. Agreement between 2DSM and FFDM images for BI-RADS classification was graded as good with Cohen’s k-coefficient of 0.78 ± 0.05. Visibility scores in both modalities of images were similar for all lesions combined; however, 2DSM had significantly better visibility scores for calcified cancers (p < 0.01), and in dense breast tissue (p < 0.01). ConclusionsDiagnostic performances of 2DSM and FFDM images were comparable for detecting breast cancers, and it is possible that 2DSM may eliminate the need for additional FFDM during DBT-based imaging due to advances in image reconstruction methods.

A collection input based support tensor machine for lesion malignancy classification in digital breast tomosynthesis

Digital breast tomosynthesis (DBT) with improved lesion conspicuity and characterization has been adopted in screening practice. DBT-based diagnosis strongly depends on physicians’ experience, so an automatic lesion malignancy classification model using DBT could improve the consistency of diagnosis among different physicians. Tensor-based approaches that use the original imaging data as input have shown promising results for many classification tasks. However, DBT data are pseudo-3D volumetric imaging as the slice spacing of DBT is much coarser than that of the in-plane resolution. Thus, directly constructing DBT as the third-order tensor in a conventional tensor-based classifier with introducing additional information to the original DBT data along the slice-spacing dimension will lead to inconsistency across all three dimensions. To avoid such inconsistency, we introduce a collection input based support tensor machine (CISTM)-based classifier that uses the tensor collection as input for classifying lesion malignancy in DBT. In CISTM, instead of introducing the third dimension directly into the geometry construction, the third-dimension structural relationship is related by weight parameters in the decision function, which is dynamically and automatically constructed during the classifier training process and is more consistent with the pseudo-3D nature of DBT. We tested our method on a DBT dataset of 926 images among which 262 were malignant and 664 were benign. We compared our method with the latest tensor-based method, KSTM (kernelled support tensor machine), which does not consider the unique non-uniform resolution property of DBT. Experimental results illustrate that the CISTM-based classifier is effective for classifying breast lesion malignancy in DBT and that it outperforms the KSTM-based classifier.

Correlation of digital mammography and digital breast tomosynthesis features of self-detected breast cancers with human epidermal growth factor receptor type 2/neu status.

Context:Breast cancer is a heterogeneous disease with several histological subtypes. Its prognosis and management are influenced by human epidermal growth factor receptor type 2 (HER2/neu) expression. Varying grades of HER2/neu overexpression are likely to have different morphological features. Digital breast tomosynthesis (DBT) enhances lesion visibility and hence that it may reveal features closer to histomorphological findings.Aims:The aim of this study is to correlate digital mammography (DM) and DBT findings of self-detected tumors with HER2/neu status, to determine whether differences in imaging features can help predict the degrees of HER2/neu overexpression.Settings and Design:Prospective study conducted in a tertiary care hospital.Methods:For 100 consecutive patients with self-detected lumps, DM and DBT data were reviewed by two radiologists who were blinded to histopathology. Of these, 63 patients with histologically proven breast cancer were recruited and their DM and DBT findings compared and correlated with HER2neu status (scores 0–3+).Statistical Analysis:Pearson's Chi-squared test and Fisher's exact test were used (SPSS version 22.0, IBM).Results:Morphology of lesions at both DM and DBT varied with HER2/neu status (P = 0.04 and 0.015, respectively). HER2-0 tumors mostly presented as masses without microcalcifications (88.8%), while most of HER2-3+ tumors as masses or asymmetries with microcalcifications (61.9%). The presence or absence of calcifications varied significantly with HER2/neu status. Breast imaging-reporting and data system (BI-RADS) scoring varied significantly (P < 0.001) with higher HER2 signal, more frequently associated with BI-RADS 5 score.Conclusion:DM and DBT features vary with the intensity of HER2 immunostaining. Higher BI-RADS scores, microcalcifications, and spiculated margins are frequently associated with HER2/neu 3+ lesions.