Microcalcification Clusters Research Articles

Sparse Representation for Detection of Microcalcification Clusters

To improve the performance of microcalcification clusters (MCs) detection, we present an approach to detect MCs in mammograms by casting the detection problem as finding sparse representations of test samples with respect to training samples. The ground truth training samples of MCs in mammograms are assumed to be known as a priori. The sparse representation is computed by the l 1 -regularized least square approach using the interior-point method. The new method based on sparse representation expresses each testing sample as a linear combination of all the training samples. The sparse coefficient vector is obtained by l 1 -regularized least square through learning. MCs classification is achieved by defining discriminating functions from the sparse coefficient vector for each category. To investigate its performance, the proposed method is applied to DDSM datasets and compared with support vector machines (SVMs) and twin support vector machines (TWSVMs). The experimental results have shown that the performance of the proposed method is comparable with or better than those methods. In addition, the proposed method is more efficient than SVMs and TWSVMs based methods as it has no need of model selection and parameter optimization. DOI: http://dx.doi.org/10.11591/telkomnika.v10i3.616

Solid neuroendocrine breast carcinoma: mammographic and sonographic features in thirteen cases

This study aimed to determine and quantitate the mammographic and sonographic characteristics in 13 cases of solid neuroendocrine breast carcinoma (NEBC) and to analyze the association of radiological findings with the clinical and histopathologic findings. The clinical data and imaging findings of 13 female patients with histologically confirmed solid NEBC were reviewed. Imaging data were evaluated by two radiologists for a consensual diagnosis. All patients presented with one palpable mass; only 1 experienced occasional breast pain, and 5 complained of fluid discharge. In 7 patients, the masses were firm and mobile. Regional lymph node metastasis was noted in only 1 patient. For the 10 patients who underwent mammography, 6 had a mass, 1 had clustered small nodules with clustered punctuate microcalcifications, 2 had asymmetric focal density, and 1 had solitary punctuate calcification. Most of the masses had irregular shape with indistinct or microlobulated margins. For the 9 patients who underwent ultrasonography (US), 9 masses were depicted, all of which were hypoechoic, mostly with irregular shape and without acoustic phenomena. Different types of acoustic phenomena were also identified. One patient had developed distant metastases during follow-up. NEBC has a variety of presentations, but it is mostly observed on mammograms as a dense, irregular mass with indistinct or microlobulated margins. Sonographically, it typically presents as an irregular, heterogeneously hypoechoic mass with normal sound transmission. Histories of nipple discharge and calcification observed using imaging are not rare.

Effect of image quality on calcification detection in digital mammography

This study aims to investigate if microcalcification detection varies significantly when mammographic images are acquired using different image qualities, including: different detectors, dose levels, and different image processing algorithms. An additional aim was to determine how the standard European method of measuring image quality using threshold gold thickness measured with a CDMAM phantom and the associated limits in current EU guidelines relate to calcification detection. One hundred and sixty two normal breast images were acquired on an amorphous selenium direct digital (DR) system. Microcalcification clusters extracted from magnified images of slices of mastectomies were electronically inserted into half of the images. The calcification clusters had a subtle appearance. All images were adjusted using a validated mathematical method to simulate the appearance of images from a computed radiography (CR) imaging system at the same dose, from both systems at half this dose, and from the DR system at quarter this dose. The original 162 images were processed with both Hologic and Agfa (Musica-2) image processing. All other image qualities were processed with Agfa (Musica-2) image processing only. Seven experienced observers marked and rated any identified suspicious regions. Free response operating characteristic (FROC) and ROC analyses were performed on the data. The lesion sensitivity at a nonlesion localization fraction (NLF) of 0.1 was also calculated. Images of the CDMAM mammographic test phantom were acquired using the automatic setting on the DR system. These images were modified to the additional image qualities used in the observer study. The images were analyzed using automated software. In order to assess the relationship between threshold gold thickness and calcification detection a power law was fitted to the data. There was a significant reduction in calcification detection using CR compared with DR: the alternative FROC (AFROC) area decreased from 0.84 to 0.63 and the ROC area decreased from 0.91 to 0.79 (p < 0.0001). This corresponded to a 30% drop in lesion sensitivity at a NLF equal to 0.1. Detection was also sensitive to the dose used. There was no significant difference in detection between the two image processing algorithms used (p > 0.05). It was additionally found that lower threshold gold thickness from CDMAM analysis implied better cluster detection. The measured threshold gold thickness passed the acceptable limit set in the EU standards for all image qualities except half dose CR. However, calcification detection varied significantly between image qualities. This suggests that the current EU guidelines may need revising. Microcalcification detection was found to be sensitive to detector and dose used. Standard measurements of image quality were a good predictor of microcalcification cluster detection.

Detection of Microcalcification Clusters Using Hessian Matrix and Foveal Segmentation Method on Multiscale Analysis in Digital Mammograms

Mammography is the most efficient technique for detecting and diagnosing breast cancer. Clusters of microcalcifications have been mainly targeted as a reliable early sign of breast cancer and their earliest detection is essential to reduce the probability of mortality rate. Since the size of microcalcifications is very tiny and may be overlooked by the observing radiologist, we have developed a Computer Aided Diagnosis system for automatic and accurate cluster detection. A three-phased novel approach is presented in this paper. Firstly, regions of interest that corresponds to microcalcifications are identified. This can be achieved by analyzing the bandpass coefficients of the mammogram image. The suspicious regions are passed to the second phase, in which the nodular structured microcalcifications are detected based on eigenvalues of second order partial derivatives of the image and microcalcification pixels are segmented out by exploiting the foveal segmentation in multiscale analysis. Finally, by combining the responses coming out from the second order partial derivatives and the foveal method, potential microcalcifications are detected. The detection performance of the proposed method has been evaluated by using 370mammograms. The detection method has a TP ratio of 97.76% with 0.68 false positives per image. We have examined the performance of our computerized scheme using free-response operating characteristics curve.

Twin support vector machines and subspace learning methods for microcalcification clusters detection

This paper presents a novel framework for microcalcification clusters (MCs) detection in mammograms. The proposed framework has three main parts: (1) first, MCs are enhanced by using a simple-but-effective artifact removal filter and a well-designed high-pass filter; (2) thereafter, subspace learning algorithms can be embedded into this framework for subspace (feature) selection of each image block to be handled; and (3) finally, in the resulted subspaces, the MCs detection procedure is formulated as a supervised learning and classification problem, and in this work, the twin support vector machine (TWSVM) is developed in decision-making of MCs detection. A large number of experiments are carried out to evaluate and compare the MCs detection approaches, and the effectiveness of the proposed framework is well demonstrated.

On the Classification of Imbalanced Datasets

In recent research the classifications of imbalanced data sets have received considerable attention. It is natural that due to the class imbalance the classifier tends to favour majority class. In this paper we investigate the performance of different methods for handling data imbalance in the microcalcification classification which is a classical example for data imbalance problem. Micro calcifications are very tiny deposits of calcium that appear as small bright spots in the mammogram. Classification of microcalcification clusters from mammograms plays an important role in computer-aided diagnosis for early detection of breast cancer. In this paper, we review in brief the state of the art techniques in the framework of imbalanced data sets and investigate the performance of different methods for microcalcification classification.

Visibility of microcalcification clusters and masses in breast tomosynthesis image volumes and digital mammography: A 4AFC human observer study

To investigate the visibility of simulated lesions in digital breast tomosynthesis (BT) image volumes compared with 2D digital mammography (DM). Simulated lesions (masses and microcalcifications) were added to images of the same women acquired on a DM system (Mammomat Novation, Siemens) and a BT prototype. The same beam quality was used for the DM and BT acquisitions. The total absorbed dose resulting from a 25-projection BT acquisition and reconstruction (BT(25)) was approximately twice that of a single DM view. By excluding every other projection image from the reconstruction (BT(13)), approximately the same dose as in DM was effected. Simulated microcalcifications were digitally added with varying contrast to the DM and BT images. Simulated masses with 8 mm diameter were also added to BT images. A series of 4-alternative forced choice (4AFC) human observer experiments were conducted. Four medical physicists participated in all experiments, each consisting of 60 trials per experimental condition. The observers interpreted the BT image volumes in cine-mode at a fixed image sequence speed. The required threshold contrast (S(t)) to achieve a detectability index (d') of 2.5 (i.e., 92.5% correct decisions) was determined. The S(t) for mass detection in DM was approximately a factor of 2 higher than required in BT indicating that the detection of masses was improved under BT conditions compared to DM. S(t) for microcalcification detection was higher for BT than for DM at both BT dose levels (BT(25) and BT(13)), with a statistically significant difference in S(t) between DM and BT(13). These results indicate a dose-dependent decrease in detection performance in BT for detection of microcalcifications. In agreement with previous investigations, masses of size 8 mm can be detected with less contrast in BT than in DM indicating improved detection performance for BT. However, for the investigated microcalcifications, the results of this study indicate potentially worse performance for BT than for DM at the same dose level.

Retrieval boosted computer-aided diagnosis of clustered microcalcifications for breast cancer

The authors propose an image-retrieval based approach for case-adaptive classifier design in computer-aided diagnosis (CADx). The conventional approach in CADx is to first train a pattern-classifier based on a set of existing training samples and then apply this classifier to subsequent new cases. The purpose of this work is to improve the classification accuracy of a CADx classifier by making use of a set of known cases retrieved from a reference library that are similar to the case under consideration. In the proposed approach, the authors will first apply image-retrieval to obtain a set of lesion images from a library of known cases that have similar image features to a case being diagnosed (i.e., query). These retrieved cases are then used to optimize a pattern-classifier toward boosting its classification accuracy on the query case. The basic idea is to put more emphasis on those cases that are similar to the query. The proposed approach is demonstrated first using a linear classifier and then extended to a nonlinear classifier induced by kernel principal component analysis. The proposed retrieval-driven approach was tested on a library of mammogram images from 1006 cases (646 benign and 360 malignant) obtained from multiple institutions and was demonstrated to yield significant improvement in classification performance. Measured by the area under the receiver operating characteristic curve (AUC), the case-adaptive approach could boost the classification performance of a linear classifier from AUC = 0.7415 to AUC = 0.7807; similar improvement was also obtained for a nonlinear classifier, with AUC boosted from 0.7527 to 0.7838. Use of additional cases from a reference library that have similar image features can improve the classification accuracy of a CADx classifier on a query case. It can even outperform retraining the classifier with all the cases from the entire reference library. This implies that cases with similar image features are more relevant in defining the local decision boundary of the CADx classifier around the query.

Discriminant Subspace Learning for Microcalcification Clusters Detection

This paper presents a novel approach to microcalcification clusters (MCs) detection in mammograms based on the discriminant subspace learning. The ground truth of MCs in mammograms is assumed to be known as a priori. Several typical subspace learning algorithms, such as principal component analysis (PCA), linear discriminant analysis (LDA), tensor subspace analysis (TSA) and general tensor discriminant Analysis (GTDA), are employed to extract subspace features. In subspace feature domain, the MCs detection procedure is formulated as a supervised learning and classification problem, and SVM is used as a classifier to make decision for the presence of MCs or not. A large number of experiments are carried out to evaluate and compare the performance of the proposed MCs detection algorithms. The experiment result suggests that correlation filters is a promising technique for MCs detection.

Analysis of Machine Learning Techniques Applied to the Classification of Masses and Microcalcification Clusters in Breast Cancer Computer-Aided Detection

Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators of malignancy in the early stages of this disease, when mammography is typically used as the screening technology. Computer-Aided Diagnosis (CAD) systems can support the radiologists’ work, by performing a double-reading process, which provides a second opinion that the physician can take into account in the detection process. This paper presents a CAD model based on computer vision procedures for locating suspicious regions that are later analyzed by artificial neural networks, support vector machines and linear discriminant analysis, to classify them into benign or malignant, based on a set of features that are extracted from lesions to characterize their visual content. A genetic algorithm is used to find the subset of features that provide the greatest discriminant power. Our results show that the SVM presented the highest overall accuracy and specificity for classifying microcalcification clusters, while the NN outperformed the rest for mass-classification in the same parameters. Overall accuracy, sensitivity and specificity were measured.

A guided ant colony algorithm for detection of microcalcification clusters

Women suffering from breast cancer have been taken as a severe concern all around the world, as it directly distresses the next generation to come. The Microcalcification Cluster in the mammograms is one of the vital sign for the early diagnosis of breast cancer. In this paper, an improved Ant Colony Algorithm is proposed for the segmentation of MCs in two-steps:(a) watershed segmentation is applied on the edge map of the digital mammograms, which reduces the over-segmentation property of watershed algorithm enormously, and (b) a Guided Ant Colony Algorithm (GACA) is applied to merge the segmented regions together based on their homogeneity to produce the final segmentation into two different clusters such as normal and abnormal tissues. The performance of the classification is evaluated with Receiver Operating Characteristic curve analysis. The greatest accuracy of 96% is achieved by GACA states the better performance of the proposed method.

Independent Component Analysis to Detect Clustered Microcalcification Breast Cancers

The presence of clustered microcalcifications is one of the earliest signs in breast cancer detection. Although there exist many studies broaching this problem, most of them are nonreproducible due to the use of proprietary image datasets. We use a known subset of the currently largest publicly available mammography database, the Digital Database for Screening Mammography (DDSM), to develop a computer-aided detection system that outperforms the current reproducible studies on the same mammogram set. This proposal is mainly based on the use of extracted image features obtained by independent component analysis, but we also study the inclusion of the patient's age as a nonimage feature which requires no human expertise. Our system achieves an average of 2.55 false positives per image at a sensitivity of 81.8% and 4.45 at a sensitivity of 91.8% in diagnosing the BCRP_CALC_1 subset of DDSM.

A texture analysis method for detection of clustered microcalcifications on digital mammograms

Breast cancer is one of the major causes of death among women. Early detection of breast cancer is possible by the detection of clustered microcalcifications on X-ray mammograms. Texture is an important characteristic used in identifying objects or region of interest in a digitised mammogram. This work focuses on a statistical texture analysis method called Surrounding Region Dependence Method (Kim and Park, 1999) - based on second order histogram in two surrounding regions. Six textural features are extracted and are used to classify region of interests into positive ROIs, containing clustered microcalcifications and negative ROIs composed of normal breast tissues. A 3-layer backpropagation neural network is used as a classifier. Results are evaluated using Receiver Operating Characteristics analysis.

Automated Detection Method for Clustered Microcalcification in Mammogram Image Based on Statistical Textural Features

Breast cancer is the most frightening cancer for women in the world. The current problem that closely related with this issue is how to deal with small calcification part inside the breast called micro calcification (MC). As a preventive way, a breast screening examination called mammogram is provided. Mammogram image with a considerable amount of MC has been a problem for the doctor and radiologist when they should determine correctly the region of interest, in this study is clustered MC. Therefore, we propose to develop an automated method to detect clustered MC utilizing two main methods, multi-branch standard deviation analysis for clustered MC detection and surrounding region dependence method for individual MC detection. Our proposed method was resulting in 70.8% of classification rate, then for the sensitivity and specificity obtained 79% and 87%, respectively. The gained results are adequately promising to be more developed in some areas.

Automated Detection Method for Clustered Microcalcification in Mammogram Image Based on Statistical Textural Features

Breast cancer is the most frightening cancer for women in the world. The current problem that closely related with this issue is how to deal with small calcification part inside the breast called micro calcification (MC). As a preventive way, a breast screening examination called mammogram is provided. Mammogram image with a considerable amount of MC has been a problem for the doctor and radiologist when they should determine correctly the region of interest, in this study is clustered MC. Therefore, we propose to develop an automated method to detect clustered MC utilizing two main methods, multi-branches standard deviation analysis for clustered MC detection and surrounding region dependence method for individual MC detection. Our proposed method was resulting in 70.8% of classification rate, then for the sensitivity and specificity obtained 79% and 87%, respectively. The gained results are adequately promising to be more developed in some areas.

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.

Clinical Analyses of Clustered Microcalcifications after Autologous Fat Injection for Breast Augmentation

Background: Autologous fat injection for breast augmentation has been disputed with regard to its complications for many years, especially regarding calcifications, most of which present with benign features. In previous studies, clustered microcalcifications were not observed after fat injection for breast augmentation, which are usually regarded as malignant calcifications. Methods: From July of 1999 to December of 2009, autologous fat injection for breast augmentation was performed for both breasts in 48 patients. Eight patients with clustered microcalcifications found by mammography after surgery were analyzed retrospectively. For the nonpalpable breast lesions in three patients, the clustered microcalcifications were resected with the help of needle localized breast biopsy. The palpable lump, including clustered microcalcifications, was resected 1 cm away from its border in the other patients. All of the specimens were submitted to pathologic examination. Results: The digitized mammographic films of eight of 48 patients (16.7 percent) showed clustered microcalcifications after autologous fat injection, which were highly suspected of being breast carcinoma microcalcifications, whereas all pathologic examinations indicated fat necroses. Conclusions: Clustered microcalcifications can be found after autologous fat injection for breast augmentation, which cannot be distinguished from malignancy. The mammographic confusion constitutes the problem rather than the success of the procedure itself, and the method should continue to be prohibited.

The simulation of 3D microcalcification clusters in 2D digital mammography and breast tomosynthesis

This work proposes a new method of building 3D models of microcalcification clusters and describes the validation of their realistic appearance when simulated into 2D digital mammograms and into breast tomosynthesis images. A micro-CT unit was used to scan 23 breast biopsy specimens of microcalcification clusters with malignant and benign characteristics and their 3D reconstructed datasets were segmented to obtain 3D models of microcalcification clusters. These models were then adjusted for the x-ray spectrum used and for the system resolution and simulated into 2D projection images to obtain mammograms after image processing and into tomographic sequences of projection images, which were then reconstructed to form 3D tomosynthesis datasets. Six radiologists were asked to distinguish between 40 real and 40 simulated clusters of microcalcifications in two separate studies on 2D mammography and tomosynthesis datasets. Receiver operating characteristic (ROC) analysis was used to test the ability of each observer to distinguish between simulated and real microcalcification clusters. The kappa statistic was applied to assess how often the individual simulated and real microcalcification clusters had received similar scores ("agreement") on their realistic appearance in both modalities. This analysis was performed for all readers and for the real and the simulated group of microcalcification clusters separately. "Poor" agreement would reflect radiologists' confusion between simulated and real clusters, i.e., lesions not systematically evaluated in both modalities as either simulated or real, and would therefore be interpreted as a success of the present models. The area under the ROC curve, averaged over the observers, was 0.55 (95% confidence interval [0.44, 0.66]) for the 2D study, and 0.46 (95% confidence interval [0.29, 0.64]) for the tomosynthesis study, indicating no statistically significant difference between real and simulated lesions (p > 0.05). Agreement between allocated lesion scores for 2D mammography and those for the tomosynthesis series was poor. The realistic appearance of the 3D models of microcalcification clusters, whether malignant or benign clusters, was confirmed for 2D digital mammography images and the breast tomosynthesis datasets; this database of clusters is suitable for use in future observer performance studies related to the detectability of microcalcification clusters. Such studies include comparing 2D digital mammography to breast tomosynthesis and comparing different reconstruction algorithms.

Dose Reduction in Digital Breast Tomosynthesis (DBT) Screening using Synthetically Reconstructed Projection Images: An Observer Performance Study

The aim of this study was to retrospectively compare the interpretive performance of synthetically reconstructed two-dimensional images in combination with digital breast tomosynthesis (DBT) versus full-field digital mammography (FFDM) plus DBT. Ten radiologists trained in reading tomosynthesis examinations interpreted retrospectively, under two modes, 114 mammograms. One mode included the directly acquired full-field digital mammograms combined with DBT, and the other included synthetically reconstructed projection images combined with DBT. The reconstructed images do not require additional radiation exposure. The two modes were compared with respect to sensitivity, namely, recommendation to recall a breast with either a pathology-proven cancer (n = 48) or a high-risk lesion (n = 6), and specificity, namely, no recommendation to recall a breast not depicting an abnormality (n = 144) or depicting only benign abnormalities (n = 30). The average sensitivity for FFDM with DBT was 0.826, compared to 0.772 for synthetic FFDM with DBT (difference, 0.054; P = .017 and P = .053 for fixed and random reader effects, respectively). The proportions of breasts with no or benign abnormalities recommended to be recalled were virtually the same: 0.298 and 0.297 for the two modalities, respectively (95% confidence intervals for the difference, -0.028 to 0.036 and -0.070 to 0.066 for fixed and random reader effects, respectively). Sixteen additional clusters of microcalcifications ("positive" breasts) were missed by all readers combined when interpreting the mode with synthesized images versus FFDM. Lower sensitivity with comparable specificity was observed with the tested version of synthetically generated images compared to FFDM, both combined with DBT. Improved synthesized images with experimentally verified acceptable diagnostic quality will be needed to eliminate double exposure during DBT-based screening.

Dependence of detectability of microcalcification clusters on quality of mammography images

This work compares the detection of microcalcification clusters (MC) in digital mammography images with different image quality levels.