Microcalcification Clusters Research Articles

The Influence on Image Reconstruction Methods on Digital Breast Tomosynthesis Guided Vacuum-assisted Biopsy for Clustered Microcalcifications

In this study, we verified the targeting time and coordinates of stereotactic vacuum-assisted biopsy (STVAB) and digital breast tomosynthesis-guided vacuum-assisted biopsy (DBTVAB). We used 23 fabricated phantom samples that consisted of small round, amorphous, and pleomorphic clustered microcalcifications, and two types of image reconstruction methods: filtered back projection (FBP) and iterative super-resolution reconstruction (ISR). Regarding targeting time, DBTVAB tended to be shorter than STVAB in the two image reconstruction methods and the targeting time was significantly shorter for the amorphous and pleomorphic calcifications using DBTVAB with FBP compared to that using STVAB (p=0.022 for amorphous, p=0.041 for pleomorphic). The targeting time for small round calcifications was longer using DBTVAB with ISR compared to that using STVAB (p=0.013). For targeting coordinates, using DBTVAB with FBP showed a significant difference only for pleomorphic calcifications but using DBTVAB with ISR showed no significance. The findings of this study suggest that FBP is more suitable than ISR to be used as an image reconstruction method, and DBTVAB can shorten the targeting time compared to STVAB.

Automatic Pectoral Muscle Removal and Microcalcification Localization in Digital Mammograms.

ObjectivesBreast cancer is the most common cancer diagnosed in women, and microcalcification (MCC) clusters act as an early indicator. Thus, the detection of MCCs plays an important role in diagnosing breast cancer.MethodsThis paper presents a methodology for mammogram preprocessing and MCC detection. The preprocessing method employs automatic artefact deletion and pectoral muscle removal based on region-growing segmentation and polynomial contour fitting. The MCC detection method uses a convolutional neural network for region-of-interest (ROI) classification, along with morphological operations and wavelet reconstruction to reduce false positives (FPs).ResultsThe methodology was evaluated using the mini-MIAS and UTP datasets in terms of segmentation accuracy in the preprocessing phase, as well as sensitivity and the mean FP rate per image in the MCC detection phase. With the mini-MIAS dataset, the proposed methods achieved accuracy scores of 99% for breast segmentation and 95% for pectoral segmentation, a sensitivity score of 82% for MCC detection, and an FP rate per image of 3.27. With the UTP dataset, the methods achieved accuracy scores of 97% for breast segmentation and 91% for pectoral segmentation, a sensitivity score of 78% for MCC detection, and an FP rate per image of 0.74.ConclusionsThe proposed preprocessing method outperformed the state-of-the-art methods for breast segmentation and achieved relatively good results for pectoral muscle removal. Furthermore, the MCC detection module achieved the highest test accuracy in identifying potential ROIs with MCCs compared to other methods.

Classification of microcalcification clusters in digital breast tomosynthesis using ensemble convolutional neural network

BackgroundThe classification of benign and malignant microcalcification clusters (MCs) is an important task for computer-aided diagnosis (CAD) of digital breast tomosynthesis (DBT) images. Influenced by imaging method, DBT has the characteristic of anisotropic resolution, in which the resolution of intra-slice and inter-slice is quite different. In addition, the sharpness of MCs in different slices of DBT is quite different, among which the clearest slice is called focus slice. These characteristics limit the performance of CAD algorithms based on standard 3D convolution neural network (CNN).MethodsTo make full use of the characteristics of the DBT, we proposed a new ensemble CNN, which consists of the 2D ResNet34 and the anisotropic 3D ResNet to extract the 2D focus slice features and 3D contextual features of MCs, respectively. Moreover, the anisotropic 3D convolution is used to build 3D ResNet to avoid the influence of DBT anisotropy.ResultsThe proposed method was evaluated on 495 MCs in DBT images of 275 patients, which are collected from our collaborative hospital. The area under the curve (AUC) of receiver operating characteristic (ROC) and accuracy of classifying benign and malignant MCs using decision-level ensemble strategy were 0.8837 and 82.00%, which were significantly higher than the experimental results of 2D ResNet34 (AUC: 0.8264, ACC: 76.00%) and anisotropic 3D ResNet (AUC: 0.8455, ACC: 76.00%). Compared with the results of 3D features classification in the radiomics, the AUC of the deep learning method with decision-level ensemble strategy was improved by 0.0435, and the F1 score was improved from 79.37 to 85.71%. More importantly, the sensitivity increased from 78.13 to 84.38%, and the specificity increased from 66.67 to 77.78%, which effectively reduced the false positives of diagnosisConclusionThe results fully prove that the ensemble CNN can effectively integrate 2D features and 3D features, improve the classification performance of benign and malignant MCs in DBT, and reduce the false positives.

Computer Vision-Based Microcalcification Detection in Digital Mammograms Using Fully Connected Depthwise Separable Convolutional Neural Network.

Microcalcification clusters in mammograms are one of the major signs of breast cancer. However, the detection of microcalcifications from mammograms is a challenging task for radiologists due to their tiny size and scattered location inside a denser breast composition. Automatic CAD systems need to predict breast cancer at the early stages to support clinical work. The intercluster gap, noise between individual MCs, and individual object’s location can affect the classification performance, which may reduce the true-positive rate. In this study, we propose a computer-vision-based FC-DSCNN CAD system for the detection of microcalcification clusters from mammograms and classification into malignant and benign classes. The computer vision method automatically controls the noise and background color contrast and directly detects the MC object from mammograms, which increases the classification performance of the neural network. The breast cancer classification framework has four steps: image preprocessing and augmentation, RGB to grayscale channel transformation, microcalcification region segmentation, and MC ROI classification using FC-DSCNN to predict malignant and benign cases. The proposed method was evaluated on 3568 DDSM and 2885 PINUM mammogram images with automatic feature extraction, obtaining a score of 0.97 with a 2.35 and 0.99 true-positive ratio with 2.45 false positives per image, respectively. Experimental results demonstrated that the performance of the proposed method remains higher than the traditional and previous approaches.

Role of micropure ultrasound in the assessment of grouped breast microcalcifications with or without a mass lesion

Background Grouped microcalcifications are the tiny grouping of the many calcifications seen on mammography. For pathological examination of mass-free clustered microcalcifications, a mammography is considered because its visualization by conventional ultrasound is limited. Therefore, MicroPure imaging improves its detection and visualization. Objective This study aimed to evaluate the accuracy of MicroPure ultrasound in the diagnosis and characterization of breast microcalcifications with or without a mass in women undergoing-guided biopsies by ultrasound. Patients and methods Thirty women who were referred for breast imaging and diagnosis from Surgery and Oncology Departments to the Radiodiagnosis Department at Tanta Cancer Center were included in this study. Results In terms of diagnosis, 26 (86.7%) women had a mass, in two women (6.7%), a mass was discovered during screening and in two women (6.7%), a mass was discovered during follow-up. There were 26 (86.7%) women with a clustered distribution and four (13.3%) with a segmental distribution. The mean value of microcalcification detected by mammography was 12.87±6.64. Eleven women (36.7%) had benign masses and 19 (63.3%) had malignant masses. In terms of histopathology, 11 (36.7%) women were ductal carcinoma in situ, eight (26.7%) were invasive ductal carcinoma, six (20%) with distal hyperplasia without atypia, two (6.7%) with atypical ductal hyperplasia, two (6.7%) with sclerosing adenosis and one (3.3%) with fibroadenosis. Regarding ultrasound B (US B) mode, 17 (56.7%) women were visible and 13 (43.4%) were not visible. Regarding MicroPure, 25 (83.3%) women were visible and five (16.7%) were not visible. The mean value of microcalcification detected by MicroPure and US B mode are 8.8±6.61 and 5.97±6.7, respectively. Conclusions MicroPure scanning is a hopeful ultrasound tool that might enhance the sensitivity for diagnosis clustered microcalcifications which are not combined with breast mass on mammography.

Clinical management of atypical ductal hyperplasia on vacuum-assisted biopsy of microcalcifications: External validation study of a decision tree selecting patients eligible for surveillance

BackgroundAtypical lesions found on percutaneous breast biopsy raise specific management issues. The aim of this study was to validate the previous performance of a decision tree defined by Forgeard et al to select a subset of patients at low-risk of surgical diagnostic upgrade that would be eligible for surveillance. MethodsA consecutive series of 211 patients diagnosed with ADH on vacuum-assisted biopsy (VAB) of clustered microcalcifications alone, then operated in our institution, was reviewed. Histological findings on percutaneous cores were compared with definitive diagnoses on surgical specimens. The rate of cancer underestimation on VAB was analyzed in the four arms and two management attitudes defined in the scheme, using size and quality of microcalcification removal and the number of ADH foci. ResultsNinety-eight women with ADH met the inclusion criteria. Overall, 20 cancers were diagnosed at surgery, showing a malignancy rate of 44% (17/39 patients) in the surgery group and of 5% (3/59 patients) in the surveillance group, which was not significantly different from the 2% rate in the monitored reference group (p > 0.64). The malignancy rate increased significantly with the size of clustered microcalcifications (0% when < 6mm, 17% when between 6mm and 21 mm, 48% when > 21 mm, p < 0001) and the number of ADH foci on VAB (14% when ≤ 2, 45% when > 2, p < 0.005). ConclusionOur results corroborate – within the limits of large confidence intervals – those obtained with the reference decision tree. Due to statistical uncertainty, however, they need to be prospectively validated in a broader series.

Mammographic microcalcifications and risk of breast cancer

BackgroundMammographic microcalcifications are considered early signs of breast cancer (BC). We examined the association between microcalcification clusters and the risk of overall and subtype-specific BC. Furthermore, we studied how mammographic density (MD) influences the association between microcalcification clusters and BC risk.MethodsWe used a prospective cohort (n = 53,273) of Swedish women with comprehensive information on BC risk factors and mammograms. The total number of microcalcification clusters and MD were measured using a computer-aided detection system and the STRATUS method, respectively. Cox regressions and logistic regressions were used to analyse the data.ResultsOverall, 676 women were diagnosed with BC. Women with ≥3 microcalcification clusters had a hazard ratio [HR] of 2.17 (95% confidence interval [CI] = 1.57–3.01) compared to women with no clusters. The estimated risk was more pronounced in premenopausal women (HR = 2.93; 95% CI = 1.67–5.16). For postmenopausal women, microcalcification clusters and MD had a similar influence on BC risk. No interaction was observed between microcalcification clusters and MD. Microcalcification clusters were significantly associated with in situ breast cancer (odds ratio: 2.03; 95% CI = 1.13–3.63).ConclusionsMicrocalcification clusters are an independent risk factor for BC, with a higher estimated risk in premenopausal women. In postmenopausal women, microcalcification clusters have a similar association with BC as baseline MD.

Upgrade Rate of Atypical Ductal Hyperplasia: Ten Years Experience and Predictive Factors

Atypical ductal hyperplasia (ADH) is a benign epithelial proliferative lesion with histologic features resembling those seen in low grade ductal carcinoma in situ (DCIS). Surgical excision of the biopsy site is the standard management approach. The objective of this study was to determine the upgrade rate from ADH on stereotactic breast biopsies to DCIS or invasive carcinoma (IC) in our institution. We also sought to identify clinical, pathologic and radiologic predictive factors associated with risk of upgrade. Clinical charts, mammograms and pathology reports were reviewed for all women with a stereotactic breast biopsy showing ADH and subsequent surgery at our institution between 2008 and 2018. When available, mammograms were re-reviewed by a radiologist for this study. 295 biopsies were analyzed in 290 patients. Mean age was 56 y old. Upgrade rate was 10.5% of which 7.5% were DCIS and 3.1% IC. Mammograms were reviewed by a radiologist in 161 patients from 2013 to 2018. In this subset of patients, the rate of upgrade was 8.7% (4.35% DCIS and 4.35% IC). A statistically significant difference he largest size of the microcalcification clusters on mammogram was observed between the upgraded and the non-upgraded subgroups (14.2 mm versus 8.9 mm, P=0.03) CONCLUSIONS: The evaluation of the largest size of microcalcification clusters on mammogram as a cut-off feature could be considered to choose between an observational versus a surgical approach. This large series provides contemporary data to assist informed decision making regarding the treatment of our patients.

Medical display application for degraded image sharpness restoration based on the modulation transfer function: initial assessment for a five-megapixel mammography display monitor.

An image-display application for medical liquid-crystal display (LCD) monitors called the sharpness recovery (SR) function has been developed to compensate for image sharpness as a function of deficiencies in the modulation transfer function (MTF) of a monitor. We investigated the effects of the SR function for a five-megapixel (MP) mammography LCD monitor on the resolution and noise properties of the displayed images by measuring the MTF and overall noise power spectrum (NPS), respectively. Furthermore, the effectiveness of the SR function for the 5-MP monitor in displaying subtle microcalcifications on digital mammograms was verified using a two-alternative-forced-choice sensitivity measurement as an initial application for medical image interpretation. Four radiologists compared the visibility of 45 regions of interest with a malignant microcalcification cluster shown on SR-processed and unprocessed mammograms. SR processing improved the MTF of the displayed images by approximately 40% at the Nyquist frequency of the 5-MP monitor, whereas it slightly increased the overall NPS values. All observers indicated that the fraction of cases considered to have better visibility of microcalcifications with the SR processing was significantly greater than that without the processing (averaging 82%, with the 95% confidence interval ranging from 70 to 93%). The SR processing for the 5-MP monitor yielded a significant improvement in the resolution properties of the displayed images, with a certain increase in the image noise. The SR function has the potential to improve the observer performance of radiologists, particularly when reading subtle microcalcifications reproduced on 5-MP monitors.

Detection of microcalcification clusters regions in mammograms combining discriminative deep belief networks

In order to overcome the shortcomings of high false positive rate and poor generalization in the detection of microcalcification clusters regions, this paper proposes a method combining discriminative deep belief networks (DDBNs) to automatically and quickly locate the regions of microcalcification clusters in mammograms. Firstly, the breast region was extracted and enhanced, and the enhanced breast region was segmented to overlapped sub-blocks. Then the sub-block was subjected to wavelet filtering. After that, DDBNs model for breast sub-block feature extraction and classification was constructed, and the pre-trained DDBNs was converted to deep neural networks (DNN) using a softmax classifier, and the network is fine-tuned by back propagation. Finally, the undetected mammogram was inputted to complete the location of suspicious lesions. By experimentally verifying 105 mammograms with microcalcifications from the Digital Database for Screening Mammography (DDSM), the method obtained a true positive rate of 99.45% and a false positive rate of 1.89%, and it only took about 16 s to detect a 2 888 × 4 680 image. The experimental results showed that the algorithm of this paper effectively reduced the false positive rate while ensuring a high positive rate. The detection of calcification clusters was highly consistent with expert marks, which provides a new research idea for the automatic detection of microcalcification clusters area in mammograms.

Hastanemizde Nonpalpabl Meme Lezyonlu Bir Hasta Serisinde Stereotaktik Biyopsi Sonuçları

Aim: Although screening mammography has a high sensitivity in the clinical detection of nonpalpable breast cancer, most mammographically suspicious lesions referred to biopsy are seen to be benign. The rate of malignancy in such lesions that are biopsied with needle–wire localization ranges from 10 to 36%. In this study, we aimed to compare with the literature the pathological results and Breast Imaging Reporting and Data System (BI-RADS) scores of lesions subjected to mammography and excisional biopsy after ultrasonography-guided needle–wire localization and calculate a positive predictive value for each category. Materials and Methods: By electronically reviewing patient files and using the International Statistical Classification of Diseases and Related Health Problems (ICD-10) codes, we identified patients who underwent excisional biopsy after stereotactic marking at the General Surgery Clinic of the Istanbul Sisli Hamidiye Etfal Training and Research Hospital between January 2003 and March 2009. A total of 64 patients were included in the study, of whom 43 had benign and 21 had malignant lesions on postoperative histopathological examination. Data on patient demographic characteristics, indications for marking, and histopathological diagnoses were recorded. The patient BI-RADS scores were determined based on the mammography and breast ultrasonography reports. The BI-RADS classification and histopathological examination results were compared in percentages. Results: The mean patient age was 48.9 (32–76) years. Based on the mammography reports, the most common indications for stereotactic marking and excisional biopsy were microcalcification cluster and spiculated mass. Histopathological examination results revealed malignancy in 8%, 51%, and 100% of the patients whose BI-RADS scores were mammographically determined to be BI-RADS 3, BI-RADS 4, and BI-RADS 5, respectively. Discussion and Conclusion: The BI-RADS-based classification of lesions detected by mammography and ultrasonography can help in predicting malignancy. While BI-RADS 4 and BI-RADS 5 lesions are referred to biopsy primarily, short-term follow-up of BI-RADS 3 lesions as an alternative to biopsy could reduce unnecessary biopsies.

3D microcalcification detection using a color Doppler twinkling artifact with optimized transmit conditions: Preliminary results.

Mammography is the only method that has been proven to detect breast microcalcifications (MCs), but the sensitivity of mammography varies according to breast density. This paper proposes an ultrasound (US) color Doppler twinkling artifact (CDTA) method with optimized transmit conditions to identify breast MCs without ionizing radiation. The transmit conditions for US color Doppler imaging (CDI) were optimized to enhance the sensitivity of the twinkling artifact (TA) that arises from random scattering on rough surfaces of breast MCs. To validate the proposed breast MC detection method, a chicken breast phantom with MC particles (groups of particles <400 and <240 ) was fabricated and scanned by a digital mammography system and an US research platform by an L11-5v linear array probe with a three-dimensional (3D) motion tracking system. From the phantom experiment, the proposed 3D CDTA imaging method with optimized transmit conditions (i.e., a center frequency of 5.0MHz, an f-number of 1.3, and a peak negative pressure of 1.83MPa) successfully detected all 16 MC particles, comparable to detection with mammography. For a human breast surgical specimen in the ex vivo study, all 10 MC clusters, marked by a radiologist on the mammogram, were identified with the proposed 3D CDTA imaging method. In the phantom and ex vivo breast specimen studies, the proposed 3D CDTA imaging method successfully detected MCs, and the spatial localization was highly correlated with the mammogram results. These results indicate that the proposed 3D CDTA imaging method has great potential for the detection of MCs without ionizing radiation.

Mammography features for early markers of aggressive breast cancer subtypes and tumor characteristics: A population-based cohort study.

Current breast cancer risk models identify mostly less aggressive tumors, although only women developing fatal breast cancer will greatly benefit from early identification. Here, we evaluated the use of mammography features (microcalcification clusters, computer‐generated Breast Imaging Reporting and Data System [cBIRADS] density and lack of breast density reduction) as early markers of aggressive subtypes and tumor characteristics. Mammograms were retrieved from a population‐based cohort of women that were diagnosed with breast cancer from 2001 to 2008 in Stockholm‐Gotland County, Sweden. Tumor and patient characteristics were obtained from Stockholm Breast Cancer Quality Register and the Swedish Cancer Registry. Multinomial logistic regression was used to individually model each mammographic feature as a function of molecular subtypes, tumor characteristics and detection mode. A total of 4546 women with invasive breast cancer were included in the study. Women with microcalcification clusters in the affected breast were more likely to have human epidermal growth factor receptor 2 subtype (odds ratio [OR] 1.78; 95% confidence interval [CI] 1.24‐2.54) and potentially less likely to have basal subtype (OR 0.54; 0.30‐0.96) compared to Luminal A subtype. High mammographic cBIRADS showed association with larger tumor size and interval vs screen‐detected cancers. Lack of density reduction was associated with interval vs screen‐detected cancers (OR 1.43; 1.11‐1.83) and potentially of Luminal B subtype vs Luminal A subtype (OR 1.76; 1.04‐2.99). In conclusion, microcalcification clusters, cBIRADS density and lack of breast density reduction could serve as early markers of particular subtypes and tumor characteristics of breast cancer. This information has the potential to be integrated into risk models to identify women at risk for developing aggressive breast cancer in need of supplemental screening.

Predictors of mammographic microcalcifications.

We examined the association between established risk factors for breast cancer and microcalcification clusters and their asymmetry. A cohort study of 53 273 Swedish women aged 30 to 80 years, with comprehensive information on breast cancer risk factors and mammograms, was conducted. Total number of microcalcification clusters and the average mammographic density area were measured using a Computer Aided Detection system and the STRATUS method, respectively. A polygenic risk score for breast cancer, including 313 single nucleotide polymorphisms, was calculated for those women genotyped (N = 7387). Odds ratios (ORs) and 95% confidence intervals (CIs), with adjustment for potential confounders, were estimated. Age was strongly associated with microcalcification clusters. Both high mammographic density (>40 cm2), and high polygenic risk score (80‐100 percentile) were associated with microcalcification clusters, OR = 2.08 (95% CI = 1.93‐2.25) and OR = 1.22 (95% CI = 1.06‐1.48), respectively. Among reproductive risk factors, life‐time breastfeeding duration >1 year was associated with microcalcification clusters OR = 1.22 (95% CI = 1.03‐1.46). The association was confined to postmenopausal women. Among lifestyle risk factors, women with a body mass index ≥30 kg/m2 had the lowest risk of microcalcification clusters OR = 0.79 (95% CI = 0.73‐0.85) and the association was stronger among premenopausal women. Our results suggest that age, mammographic density, genetic predictors of breast cancer, having more than two children, longer duration of breast‐feeding are significantly associated with increased risk of microcalcification clusters. However, most lifestyle risk factors for breast cancer seem to protect against presence of microcalcification clusters. More research is needed to study biological mechanisms behind microcalcifications formation.

Effect of Dose Level on Radiologists’ Detection of Microcalcifications in Digital Breast Tomosynthesis: An Observer Study with Breast Phantoms

To compare radiologists' sensitivity, confidence level, and reading efficiency of detecting microcalcifications in digital breast tomosynthesis (DBT) at two clinically relevant dose levels. Six 5-cm-thick heterogeneous breast phantoms embedded with a total of 144 simulated microcalcification clusters of four speck sizes were imaged at two dose modes by a clinical DBT system. The DBT volumes at the two dose levels were read independently by six MQSA radiologists and one fellow with 1-33 years (median 12 years) of experience in a fully-crossed counter-balanced manner. The radiologist located each potential cluster and rated its conspicuity and his/her confidence that the marked location contained a cluster. The differences in the results between the two dose modes were analyzed by two-tailed paired t-test. Compared to the lower-dose mode, the average glandular dose in the higher-dose mode for the 5-cm phantoms increased from 1.34 to 2.07 mGy. The detection sensitivity increased for all speck sizes and significantly for the two smaller sizes (p <0.05). An average of 13.8% fewer false positive clusters was marked. The average conspicuity rating and the radiologists' confidence level were higher for all speck sizes and reached significance (p <0.05) for the three larger sizes. The average reading time per detected cluster reduced significantly (p <0.05) by an average of 13.2%. For a 5-cm-thick breast, an increase in average glandular dose from 1.34 to 2.07 mGy for DBT imaging increased the conspicuity of microcalcifications, improved the detection sensitivity by radiologists, increased their confidence levels, reduced false positive detections, and increased the reading efficiency.

"A case of non-palpable, multifocal, heterogeneous left breast carcinoma with mammographic presentation of clustered multiple microcalcifications"

"A case of non-palpable, multifocal, heterogeneous left breast carcinoma with mammographic presentation of clustered multiple microcalcifications"

Role of General Adversarial Networks in Mammogram Analysis: A Review.

The Deep Neural Networks have gained prominence in the biomedical domain, becoming the most commonly used networks after machine learning technology. Mammograms can be used to detect breast cancers with high precision with the help of Convolutional Neural Network (CNN) which is deep learning technology. An exhaustive labeled data is required to train the CNN from scratch. This can be overcome by deploying Generative Adversarial Network (GAN) which comparatively needs lesser training data during a mammogram screening. In the proposed study, the application of GANs in estimating breast density, high-resolution mammogram synthesis for clustered microcalcification analysis, effective segmentation of breast tumor, analysis of the shape of breast tumor, extraction of features and augmentation of the image during mammogram classification have been extensively reviewed.

Adaptive Gaussian Mixture Model-Based Statistical Feature Extraction for Computer-Aided Diagnosis of Micro-Calcification Clusters in Mammograms

In mammography, detection and categorization of micro-calcification clusters (MCCs) using computer-aided diagnosis (CAD) systems are very important tasks because MCCs are important signs at an earl...

3D Context-Aware Convolutional Neural Network for False Positive Reduction in Clustered Microcalcifications Detection.

False positives (FPs) reduction is indispensable for clustered microcalcifications (MCs) detection in digital breast tomosynthesis (DBT), since there might be excessive false candidates in the detection stage. Considering that DBT volume has an anisotropic resolution, we proposed a novel 3D context-aware convolutional neural network (CNN) to reduce FPs, which consists of a 2D intra-slices feature extraction branch and a 3D inter-slice features fusion branch. In particular, 3D anisotropic convolutions were designed to learn representations from DBT volumes and inter-slice information fusion isonly performed on the feature map level, which could avoid the influence of anisotropic resolution of DBT volume. The proposed method was evaluated on a large-scale Chinese women population of 877 cases with 1754 DBT volumes and compared with 8 related methods. Experimental results show that the proposed network achieved the best performance with an accuracy of 92.68% for FPs reduction with an AUC of 97.65%, and the FPs are 0.0512 per DBT volume at a sensitivity of 90%. This also proved that making full use of 3D contextual information of DBT volume can improve the performance of the classification algorithm.

A radiomics method to classify microcalcification clusters in digital breast tomosynthesis.

Digital breast tomosynthesis (DBT) is becoming increasingly used in clinical practice. In DBT, the microcalcification clusters may span across multiple slices, which makes it difficult for radiologists to directly assess these distributed clusters for diagnosis. We investigated a radiomics method to classify microcalcification clusters in DBT based on a semiautomatic segmentation process. We performed a retrospective study on a cohort of 275 patients (including 79 benign and 196 malignant cases) with a total of 550 DBT volumes. Our method consisted of three steps. The initial step was to semiautomatically segment the microcalcification clusters. Then, radiomics features were extracted from the initially segmented microcalcification clusters. Finally, the benign and malignant microcalcification clusters were differentiated by the random forest (RF) classifier using selected subset features. The radiomics models were evaluated both on view-based and case-based modes with features selected from different domains. The receiver operating characteristic (ROC) curve and area under the ROC curve (AUC) were used to evaluate the classification performance. Twenty-six key features were selected from a total of 170 radiomics features and these features show promising classification performance. The highest AUC was 0.834 for view-based mode and 0.868 for case-based mode when using features selected from the 3D-domain. The 2D-domain radiomics features showed a statistically similar performance to the 3D features (P>0.05). Radiomics models can provide encouraging performance in classification between malignant and benign microcalcification clusters which are semiautomatically segmented in DBT.