Malignant Microcalcification Clusters Research Articles

Transforming data from the image to the text domain: benign versus malignant micro-calcification classification

In this paper we present a new approach for the classification of benign and malignant micro-calcification clusters by transforming data from the image to the text domain. A string representation is extracted from binary micro-calcification segmentation images. We extracted two different features from the strings and combined different machine learning techniques towards benign versus malignant classification. We evaluated our proposed method on the DDSM database and experimental results indicates a Classification Accuracy equal to 92%.

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.

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.

An approach for classification of malignant and benign microcalcification clusters

The only reliable and successful treatment of breast cancer is its detection through mammography at initial stage. Clusters of microcalcifications are important signs of breast cancer. Manual interpretation of mammographic images, in which the suspicious regions are indicated as areas of varying intensities, is not error free due to a number of reasons. These errors can be reduced by using computer-aided diagnosis systems that result in reduction of either false positives or true negatives. The purpose of the study in this paper is to develop a methodology for distinguishing malignant microcalcification clusters from benign microcalcification clusters. The proposed approach first enhances the region of interest by using morphological operations. Then, two types of features, cluster shape features and cluster texture features, are extracted. A Support Vector Machine is used for classification. A new set of shape features based on the recursive subsampling method is added to the feature set, which improves the classification accuracy of the system. It has been found that these features are capable of differentiating malignant and benign tissue regions. To investigate the performance of the proposed approach, mammogram images are taken from Digital Database for Screening Mammography database and an accuracy of 94.25% has been achieved. The experiments have shown that the proposed classification system minimizes the classification errors and is more efficient in correct diagnosis.

Tree-based modelling for the classification of mammographic benign and malignant micro-calcification clusters

Computer Aided Detection (CAD) systems are being developed to assist radiologists in diagnosis. For breast cancer the emphasis is shifting from detection to classification of abnormalities. The presented work concentrates on the benign versus malignant classification of micro-calcification clusters, which are a specific type of mammographic abnormality associated with the early development of breast cancer. After segmentation (automatic or manual), tree-based representations were used to distinguish between benign and malignant clusters, which takes into account clinical criteria such as the number of micro-calcifications in the clusters and their distribution and is based on the topology of the trees and the connectivity of the micro-calcifications. The idea of using tree structure based on the distance of individual calcifications for the classification of benign and malignant micro-calcification clusters is novel and closely related to clinical perception. Tree structures used in this study are distinct from decision trees classifiers being used in many machine learning approaches. Initial evaluation on the Digital Database for Screening Mammography (DDSM) data shows promising results, with an accuracy equal to 91 %, which is comparable to state of the art CAD systems and is in line with clinical perception of the morphology and appearance of benign and malignant micro-calcification clusters.

Characterisation of microcalcification clusters on 2D digital mammography (FFDM) and digital breast tomosynthesis (DBT): does DBT underestimate microcalcification clusters? Results of a multicentre study.

To compare DBT and FFDM in the classification of microcalcification clusters (MCs) using BI-RADS. This Institutional Review Board-approved study was undertaken in three centres. A total of 107 MCs evaluated with both DBT and FFDM were randomised for prospective reading by six experienced breast radiologists and classified using BI-RADS. The benign/malignant ratio of MC was 66/41. Of 11/107 discordant results, DBT classified MCs as R2 whereas FFDM classified them as R3 in 9 and R4 in 2. Three of these (3/107 = 2.8%) were malignant; 8 (7.5%) were nonmalignant and were correctly classified as R2 on DBT but incorrectly classified as R3 on FFDM. Estimated sensitivity and specificity, respectively, were 100% (95% CI: 91% to 100%) and 94.6% (95% CI: 86.7% to 98.5%) for FFDM and 91.1% (95% CI: 78.8% to 97.5%) and 100% (95% CI: 94.8% to 100%) for DBT. Overall intra- and interobserver agreements were 0.75 (95% CI: 0.61-0.84) and 0.73 (95% CI: 0.62-0.78). Most MCs are scored similarly on FFDM and DBT. Although a minority (11/107) of MCs are classified differently on FFDM (benign MC classified as R3) and DBT (malignant MC classified as R2), this may have clinical relevance. • The BI-RADS classification of MC differs for FFDM and DBT in 11/107 cases • DBT assigned lower BI-RADS classes compared to FFDM in 11 clusters • In 4/107 DBT may have missed some malignant and high-risk lesions • In 7/107 the 'underclassification' on DBT was correct, potentially avoiding unnecessary biopsies • DBT may miss a small proportion of malignant lesions.

Computer-aided detection of clustered microcalcifications in digital breast tomosynthesis: A 3D approach

To design a computer-aided detection (CADe) system for clustered microcalcifications in reconstructed digital breast tomosynthesis (DBT) volumes and to perform a preliminary evaluation of the CADe system. IRB approval and informed consent were obtained in this study. A data set of two-view DBT of 72 breasts containing microcalcification clusters was collected from 72 subjects who were scheduled to undergo breast biopsy. Based on tissue sampling results, 17 cases had breast cancer and 55 were benign. A separate data set of two-view DBT of 38 breasts free of clustered microcalcifications from 38 subjects was collected to independently estimate the number of false-positives (FPs) generated by the CADe system. A radiologist experienced in breast imaging marked the biopsied cluster of microcalcifications with a 3D bounding box using all available clinical and imaging information. A CADe system was designed to detect microcalcification clusters in the reconstructed volume. The system consisted of prescreening, clustering, and false-positive reduction stages. In the prescreening stage, the conspicuity of microcalcification-like objects was increased by an enhancement-modulated 3D calcification response function. An iterative thresholding and 3D object growing method was used to detect cluster seed objects, which were used as potential centers of microcalcification clusters. In the cluster detection stage, microcalcification candidates were identified using a second iterative thresholding procedure, which was applied to the signal-to-noise ratio (SNR) enhanced image voxels with a positive calcification response. Starting with each cluster seed object as the initial cluster center, a dynamic clustering algorithm formed a cluster candidate by including microcalcification candidates within a 3D neighborhood of the cluster seed object that satisfied the clustering criteria. The number, size, and SNR of the microcalcifications in a cluster candidate and the cluster shape were used to reduce the number of FPs. The prescreening stage detected a cluster seed object in 94% of the biopsied microcalcification clusters at a threshold of 100 cluster seed objects per DBT volume. After clustering, the detection sensitivity was 90% at 15 marks per DBT volume. After FP reduction, at 85% sensitivity, the average number of FPs estimated using the data set containing microcalcification clusters was 3.8 per DBT volume, and that estimated using the data set free of microcalcification clusters was 3.4. The detection performance for malignant microcalcification clusters was superior to that for benign clusters. Our study indicates the feasibility of the 3D approach to the detection of clustered microcalcifications in DBT and that the newly designed enhancement-modulated 3D calcification response function is promising for prescreening. Further work is needed to assess the generalizability of our approach and to improve its performance.

Potential Usefulness of Similar Images in the Differential Diagnosis of Clustered Microcalcifications on Mammograms

To evaluate the potential usefulness of images of lesions of a known disease that have a similar appearance to lesions of an unknown disease in distinguishing between benign and malignant clustered microcalcifications on mammograms by removing the unusual cases from the database. Institutional review board approval for this retrospective HIPAA-compliant study of images from a publicly available database was obtained. Unusual lesions, such as malignant-looking benign lesions and benign-looking malignant lesions, were removed from the database. A total of 20 benign and 20 malignant lesions were selected with a stratified randomization method, and it was these lesions that served as unknown cases in this observer study. For each unknown case, eight similar images of benign lesions and eight similar images of malignant lesions were preselected with a computerized scheme. From these preselected images, a breast radiologist subjectively selected the four most similar images of benign lesions and the four most similar images of malignant lesions. Five attending breast radiologists and three breast-imaging fellows participated in the observer study. Observers provided their confidence level regarding malignancy of the unknown case before and after they viewed the similar images. The results were evaluated with multireader multicase receiver operating characteristic (ROC) analysis. For all observers, the areas under the ROC curves (AUCs) were improved when similar images were used. The average AUC for all observers increased from 0.692 without use of similar images to 0.790 with use of similar images (P = .0009). The presentation of similar images can improve radiologists' performance in the differential diagnosis of clustered microcalcifications on mammograms.

B‐spline active rays segmentation of microcalcifications in mammography

Accurate segmentation of microcalcifications in mammography is crucial for the quantification of morphologic properties by features incorporated in computer-aided diagnosis schemes. A novel segmentation method is proposed implementing active rays (polar-transformed active contours) on B-spline wavelet representation to identify microcalcification contour point estimates in a coarse-to-fine strategy at two levels of analysis. An iterative region growing method is used to delineate the final microcalcification contour curve, with pixel aggregation constrained by the microcalcification contour point estimates. A radial gradient-based method was also implemented for comparative purposes. The methods were tested on a dataset consisting of 149 mainly pleomorphic microcalcification clusters originating from 130 mammograms of the DDSM database. Segmentation accuracy of both methods was evaluated by three radiologists, based on a five-point rating scale. The radiologists' average accuracy ratings were 3.96 +/- 0.77, 3.97 +/- 0.80, and 3.83 +/- 0.89 for the proposed method, and 2.91 +/- 0.86, 2.10 +/- 0.94, and 2.56 +/- 0.76 for the radial gradient-based method, respectively, while the differences in accuracy ratings between the two segmentation methods were statistically significant (Wilcoxon signed-ranks test, p < 0.05). The effect of the two segmentation methods in the classification of benign from malignant microcalcification clusters was also investigated. A least square minimum distance classifier was employed based on cluster features reflecting three morphological properties of individual microcalcifications (area, length, and relative contrast). Classification performance was evaluated by means of the area under ROC curve (Az). The area and length morphologic features demonstrated a statistically significant (Mann-Whitney U-test, p < 0.05) higher patient-based classification performance when extracted from microcalcifications segmented by the proposed method (0.82 +/- 0.06 and 0.86 +/- .05, respectively), as compared to segmentation by the radial gradient-based method (0.71 +/- 0.08 and 0.75 +/- 0.08). The proposed method demonstrates improved segmentation accuracy, fulfilling human visual criteria, and enhances the ability of morphologic features to characterize microcalcification clusters.

Die stereotaktische Mammotome®-Brustbiopsie: Erfahrungen im klinischen Alltag und Korrelation der BI-RADS®-Klassifikation mit der Histopathologie

Stereotactic breast biopsy using the Mammotome system allows minimal invasive tissue sampling of suspicious lesions of the breast cancer, e.g. clustered microcalcifications BI-RADS type 3 and 4, and has widely replaced open surgical biopsies. The aim of this retrospective study was to review the results of these biopsies in regard of technical feasibility and complications as well as to correlate initial BI-RADS assessment with histopathology. One hundred thirty-five vacuum-assisted breast biopsies in 124 patients were evaluated. Before biopsy, the mammograms were classified according to the Breast Imaging Reporting and Data System (BI-RADS). All mammograms were reviewed with knowledge of the final histologic diagnosis. Patients with benign diagnoses underwent mammographic follow-up. Excisional biopsy was recommended for diagnoses of in-situ or invasive carcinoma. No serious complications of the biopsies were observed. Histopathology revealed 105 (78%) benign lesions. Benign lesions were classified as BI-RADS 3 in 49 (36%) and as suspicious (BI-RADS 4) in 56 (41%). Thirty lesions (22%) were malignant, of which 26 (87%) were classified BI-RADS 4 or 5. The frequency of malignancy in BI-RADS 4 and 5 was 19 of 75 (25%) and 7 of 7 (100%), respectively. Of the 53 BI-RADS 3 lesions, 4 (8%) were malignant. Mammotome biopsy was shown to be a safe and well-tolerated technique for the work-up of mammographic lesions. The frequency of malignant histopathologic findings in BI-RADS 3 lesions was higher than expected, reflecting the difficulties in the mammographic differentiation of benign and malignant clustered microcalcifications.

Experimental determination of subjective similarity for pairs of clustered microcalcifications on mammograms: Observer study results

Presentation of images of lesions similar to that of an unknown lesion might be useful to radiologists in distinguishing between benign and malignant clustered microcalcifications on mammograms. Investigators have been developing computerized schemes to select similar images from large databases. However, whether selected images are really similar in appearance is not examined for most of the schemes. In order to retrieve images that are useful to radiologists, the selected images must be similar from radiologists' diagnostic points of view. Therefore, in this study, the data of radiologists' subjective similarity for pairs of clustered microcalcification images were obtained from a number of observers, and the intra- and inter-observer variations and the intergroup correlations were determined to investigate whether reliable similarity ratings by human observers can be determined. Nineteen images of clustered microcalcifications, each of which was paired with six other images, were selected for the observer study. Thus, subjective similarity ratings for 114 pairs of clustered microcalcifications were determined by each observer. Thirteen breast, ten general, and ten nonradiologists participated in the observer study; some of them completed the study multiple times. Although the intraobserver variations for the individual readings and the interobserver variations for pairs of observers were not small, the interobserver agreements were improved by taking the average of readings by the same observers. When the similarity ratings by a number of observers were averaged among the groups of breast, general, and nonradiologists, the mean differences of the ratings between the groups decreased, and good concordance correlations (0.846, 0.817, and 0.785) between the groups were obtained. The result indicates that reliable similarity ratings can be determined by use of this method, and the average similarity ratings by breast radiologists can be considered meaningful and useful for the development and evaluation of a computerized scheme for selection of similar images.

Joint two-view information for computerized detection of microcalcifications on mammograms

We are developing new techniques to improve the accuracy of computerized microcalcification detection by using the joint two-view information on craniocaudal (CC) and mediolateral-oblique (MLO) views. After cluster candidates were detected using a single-view detection technique, candidates on CC and MLO views were paired using their radial distances from the nipple. Candidate pairs were classified with a similarity classifier that used the joint information from both views. Each cluster candidate was also characterized by its single-view features. The outputs of the similarity classifier and the single-view classifier were fused and the cluster candidate was classified as a true microcalcification cluster or a false-positive (FP) using the fused two-view information. A data set of 116 pairs of mammograms containing microcalcification clusters and 203 pairs of normal images from the University of South Florida (USF) public database was used for training the two-view detection algorithm. The trained method was tested on an independent test set of 167 pairs of mammograms, which contained 71 normal pairs and 96 pairs with microcalcification clusters collected at the University of Michigan (UM). The similarity classifier had a very low FP rate for the test set at low and medium levels of sensitivity. However, the highest mammogram-based sensitivity that could be reached by the similarity classifier was 69%. The single-view classifier had a higher FP rate compared to the similarity classifier, but it could reach a maximum mammogram-based sensitivity of 93%. The fusion method combined the scores of these two classifiers so that the number of FPs was substantially reduced at relatively low and medium sensitivities, and a relatively high maximum sensitivity was maintained. For the malignant microcalcification clusters, at a mammogram-based sensitivity of 80%, the FP rates were 0.18 and 0.35 with the two-view fusion and single-view detection methods, respectively. When the training and test sets were switched, a similar improvement was obtained, except that both the fusion and single-view detection methods had superior test performances on the USF data set than those on the UM data set. Our results indicate that correspondence of cluster candidates on two different views provides valuable additional information for distinguishing FPs from true microcalcification clusters.

Independent component analysis applied to breast cancer detection on digitized mammograms

In this work we evaluate the possibilities of Independent Component Analysis (ICA) in conjunction with neural networks with the purpose of finding a set of right parameters which lead to an efficient detection of malignant microcalcification clusters (MCCs) on digitized mammograms. Also, as a part of the ICA process, we aim to state the best window size and component number to be used in the working mammograms with a pixel size of 43.5 μm.

Mammography and computerized decision systems: a review.

Computer-aided diagnosis (CAD) systems in mammography have been developed and investigated for several years and recently they have left the research stage to enter the clinical stage. The purpose of this article is to review the present situation of mammography for breast cancer detection and the role played by CAD systems. Results from the recent literature show that CAD systems have the potential to improve the sensitivities of radiologists in the detection of malignant clustered microcalcifications and masses, while keeping specificities at acceptable levels. This leads to the conclusion that CAD systems can be incorporated into clinical practice as a double reading option to radiologists. However, some issues have yet to be tackled for CAD systems to gain better acceptance and more widespread use worldwide.

US of mammographically detected clustered microcalcifications.

To determine whether ultrasonography (US) can depict breast masses associated with mammographically detected clustered microcalcifications and whether the visibility at US is different between benign and malignant lesions. Ninety-four patients with 100 mammographically detected microcalcification clusters prospectively underwent US with a 10- or 12-MHz transducer before mammographically guided presurgical hook-wire localization. The visibility of breast masses at US was correlated with histologic and mammographic findings. Surgical biopsy revealed 62 benign lesions, 30 intraductal cancers, and eight invasive cancers. At US, breast masses associated with microcalcifications were seen in 45 (45%) of 100 cases. US depicted more breast masses associated with malignant (31 [82%] of 38) than with benign (14 [23%] of 62) microcalcifications (P: <.001). In malignant microcalcification clusters larger than 10 mm, US depicted associated breast masses in all 25 cases. There was no statistically significant difference in shape and distribution of calcific particles, as well as in breast composition, at mammography between US visible and invisible groups. Given a known mammographic location, US with a high-frequency transducer can depict breast masses associated with malignant microcalcifications, particularly clusters larger than 10 mm. US can be used to visualize large clusters of microcalcifications that have a very high suspicion of malignancy.

Optimizing parameters for computer-aided diagnosis of microcalcifications at mammography

The purpose of this study was to optimize selection of the mammographic features most useful in discriminating benign from malignant clustered microcalcifications. The computer-aided diagnosis (CAD) system automatically extracted from digitized mammograms 13 quantitative features characterizing microcalcification clusters. Archival cases (n = 134; patient age range, 31-77 years; mean age, 56.8 years) with known histopathologic results (79 malignant, 55 benign) were selected. Three radiologists at three facilities independently analyzed the microcalcifications by using the CAD system. Stepwise discriminant analysis selected the features best discriminating benign from malignant microcalcifications. A classification scheme was constructed on the basis of these optimized features, and its performance was evaluated by using receiver operating characteristic (ROC) analysis. Six of the 13 variables extracted by the CAD system were selected by stepwise determinant analysis for generating the classification scheme, which yielded an ROC curve with an area (Az) of 0.98, specificity of 83.64%, positive predictive value of 89.53%, and accuracy of 91.79% for 98% sensitivity. When patient age was an additional variable, the scheme's performance improved, but this was not statistically significant (Az = 0.98). The ROC curve of the classifier (without age as an additional variable) yielded a high Az of 0.96 for patients younger than 50 years and an even higher (P < .02) Az of 0.99 for those 50 years or older. Stepwise discriminant analysis optimized performance of a classification scheme for microcalcifications by selecting six optimized features. Scheme performance was significantly (P < .02) higher for women 50 years or older, but the addition of patient age as a variable did not produce a statistically significant increase in performance.

Tree structured wavelet transform segmentation of microcalcifications in digital mammography.

A novel multistage algorithm is proposed for the automatic segmentation of microcalcification clusters (MCCs) in digital mammography. First, a previously reported tree structured nonlinear filter is proposed for suppressing image noise, while preserving image details, to potentially reduce the false positive (FP) detection rate for MCCs. Second, a tree structured wavelet transform (TSWT) is applied to the images for microcalcification segmentation. The TSWT employs quadrature mirror filters as basic subunits for both multiresolution decomposition and reconstruction processes, where selective reconstruction of subimages is used to segment MCCs. Third, automatic linear scaling is then used to display the image of the segmented MCCs on a computer monitor for interpretation. The proposed algorithms were applied to an image database of 100 single view mammograms at a resolution of 105 microns and 12 bits deep (4096 gray levels). The database contained 50 cases of biopsy proven malignant MCCs, 8 benign cases, and 42 normal cases. The measured sensitivity (true positive detection rate) was 94% with a low FP detection rate of 1.6 MCCs/image. The image details of the segmented MCCs were reasonably well preserved, for microcalcification of less than 500 microns, with good delineation of the extent of the microcalcification clusters for each case based on visual criteria.