Microcalcification Clusters Research Articles

Automated Feature Set Selection and Its Application to MCC Identification in Digital Mammograms for Breast Cancer Detection

We propose a fully automated algorithm that is able to select a discriminative feature set from a training database via sequential forward selection (SFS), sequential backward selection (SBS), and F-score methods. We applied this scheme to microcalcifications cluster (MCC) detection in digital mammograms for early breast cancer detection. The system was able to select features fully automatically, regardless of the input training mammograms used. We tested the proposed scheme using a database of 111 clinical mammograms containing 1,050 microcalcifications (MCs). The accuracy of the system was examined via a free response receiver operating characteristic (fROC) curve of the test dataset. The system performance for MC identifications was Az = 0.9897, the sensitivity was 92%, and 0.65 false positives (FPs) were generated per image for MCC detection.

A supervised method for microcalcification cluster diagnosis

In this paper, a Computer Aided System for microcalcification cluster diagnosis in mammographic images is presented. The method is characterized by three phases. In fact, single microcalcifications are first localized then microcalcifications having

Patchwork reconstruction with resolution modeling for digital breast tomosynthesis

Digital breast tomosynthesis is a relatively new diagnostic x-ray modality that allows high resolution breast imaging while suppressing interference from overlapping anatomical structures. However, proper visualization of microcalcifications remains a challenge. For the subset of systems considered by the authors, the main cause of deterioration is movement of the x-ray source during exposures. They propose a modified grouped coordinate ascent algorithm that includes a specific acquisition model to compensate for this deterioration. A resolution model based on the movement of the x-ray source during image acquisition is created and combined with a grouped coordinate ascent algorithm. Choosing planes parallel to the detector surface as the groups enables efficient implementation of the position dependent resolution model. In the current implementation, the resolution model is approximated by a Gaussian smoothing kernel. The effect of the resolution model on the iterative reconstruction is evaluated by measuring contrast to noise ratio (CNR) of spherical microcalcifications in a homogeneous background. After this, the new reconstruction method is compared to the optimized filtered backprojection method for the considered system, by performing two observer studies: the first study simulates clusters of spherical microcalcifications in a power law background for a free search task; the second study simulates smooth or irregular microcalcifications in the same type of backgrounds for a classification task. Including the resolution model in the iterative reconstruction methods increases the CNR of microcalcifications. The first observer study shows a significant improvement in detection of microcalcifications (p = 0.029), while the second study shows that performance on a classification task remains the same (p = 0.935) compared to the filtered backprojection method. The new method shows higher CNR and improved visualization of microcalcifications in an observer experiment on synthetic data. Further study of the negative results of the classification task showed performance variations throughout the volume linked to the changing noise structure introduced by the combination of the resolution model and the smoothing prior.

Stereotactic vacuum-assisted breast biopsy: our experience and comparison with stereotactic automated needle biopsy

To evaluate and compare the outcome of stereotactically guided percutaneous, directional, vacuum-assisted breast biopsy (VAB) with the outcome of those performed with 14-gauge automated gun. Between January 2008 and January 2011, altogether 257 stereotactic biopsies were performed in our institute; 193 with the 14-gauge automated needle and 64 with a directional, vacuum-assisted instrument. Patients with malignant or high risk lesions were encouraged to undergo an excisional biopsy. We evaluated and compared concordance between the biopsy results and subsequent examinations (surgical excision or follow up) for both methods. VAB demonstrated 57 (89 %) benign lesions, 2 (3 %) high risk and 5 (8 %) malignant lesions. We obtained post-bioptic mammographic or histological evaluation for altogether 51 lesions, with one (12.5 %) false negative case, one case of underestimation of borderline lesion, and no false positive cases. Clusters of microcalcifiation were completely removed in 18 lesions (28 %). Vacuum-assisted biopsy outperformed the 14-gauge automated needle biopsy with a lower disease underestimation, sensitivity and false-negative rates; however these differences were not statistically significant due to small data files and relatively small number of identified malignant lesions in the vacuum-assisted biopsy group.VAB completely removed significantly more clusters of microcalcifications in comparison to the automated needle biopsy, which significantly reduced the need for surgery in benign lesions (Tab. 7, Fig. 3, Ref. 32).

Microcalcification clusters processing in mammograms based on relevance vector machine with adaptive kernel learning

Using the method of adaptive kernel learning based relevance vector machine (ARVM) and combining the morphological filtering and the clustering criterion recommended by Kallergi, a new algorithm for microcalcification (MC) clusters processing in mammograms is investigated. Firstly, the detection of MC is formulated as a supervised-learning problem. Then the ARVM is used as a classifier to determine whether an MC object is present at each location in the mammogram and a morphological processing is used to remove the isolated spurious pixels. Finally, the identified MC clusters are obtained by Kallergi criterion. To improve the computational speed, a fast processing method based on ARVM is developed, in which the whole image is decomposed first into sub-image blocks for parallel operation. Experimental results indicate that the ARVM method outperforms the RVM method and, in particular, the fast processing method could greatly reduce the testing time.

Detection of microcalcification clusters in digitized X-ray mammograms using unsharp masking and image statistics

A fully automated method for detecting microcalcification (MC) clusters in regions of interest (ROIs) extracted from digitized X-ray mammograms is proposed. In the first stage, an unsharp masking is used to perform the contrast enhancement of the MCs. In the second stage, the ROIs are decomposed into a 2-level contourlet representation and the reconstruction is obtained by eliminating the low-frequency subband in the second level. In the third stage, statistical textural features are extracted from the ROIs and they are classified using support vector machines. To test the performance of the method, 57 ROIs selected from the Mammographic Image Analysis Society's MiniMammogram database are used. The true positive and false positive rates are used to evaluate the performance of the classification, and the results are compared with those from other studies presented in the literature. The results show that the classification method of unsharp masking and low-band eliminated image statistics is convenient for MC cluster detection. In particular, a true positive rate of about 94% is achieved at the rate of 0.06 false positives per image.

Mammogram tumour classification using modified segmentation techniques

Sophisticated technologies in the field of medical electronics have helped to improve the lives of patients. In this work, an intelligent system for the identification of micro-calcification clusters in digitised mammograms is proposed. The proposed intelligent system consists of two stages: segmentation algorithm and a neural network/kernel system. The system was tested for mammogram images for the Mammographic Image Analysis Society and Digital Database for Screening Mammographic Databases. Different classifiers such as support vector machines, learning vector quantiser, radial basis function and back propagation neural network are used and tested. Support vector machine classifier outperforms other classifiers. The proposed system incorporates improved segmentation and better classification. The proposed intelligent system gives a better accuracy. The execution time is considerably low-befitting real-time applications. The application of the system can be used to identify tumours as benign or malignant.

On Wavelet Transform General Modulus Maxima Metric for Singularity Classification in Mammograms

Continuous wavelet transform is employed to detect singularities in 2-D signals by tracking modulus maxima along maxima lines and particularly applied to microcalcification detection in mammograms. The microcalcifications are modeled as smoothed positive impulse functions. Other target property detection can be performed by adjusting its mathematical model. In this application, the general modulus maximum and its scale of each singular point are detected and statistically analyzed locally in its neighborhood. The diagnosed microcalcification cluster results are compared with health tissue results, showing that general modulus maxima can serve as a suspicious spot detection tool with the detection performance no significantly sensitive to the breast tissue background properties. Performed fractal analysis of selected singularities supports the statistical findings. It is important to select the suitable computation parameters-thresholds of magnitude, argument and frequency range-in accordance to mathematical description of the target property as well as spatial and numerical resolution of the analyzed signal. The tests are performed on a set of images with empirically selected parameters for 200 μm/pixel spatial and 8 bits/pixel numerical resolution, appropriate for detection of the suspicious spots in a mammogram. The results show that the magnitude of a singularity general maximum can play a significant role in the detection of microcalcification, while zooming into a cluster in image finer spatial resolution both magnitude of general maximum and the spatial distribution of the selected set of singularities may lead to the breast abnormality characterization.

A ROBUST APPROACH TO CLASSIFY MICROCALCIFICATION IN DIGITAL MAMMOGRAMS USING CONTOURLET TRANSFORM AND SUPPORT VECTOR MACHINE

Mammogram is the best available radiographic method to detect breast cancer in the early stage. However detecting a microcalcification clusters in the early stage is a tough task for the radiologist. Herein we present a novel approach for classifying microcalcification in digital mammograms using Nonsubsampled Contourlet Transform (NSCT) and Support Vector Machine (SVM). The classification of microcalcification is achieved by extracting the microcalcification features from the Contourlet coefficients of the image and the outcomes are used as an input to the SVM for classification. The system classifies the mammogram images as normal or abnormal and the abnormal severity as benign or malignant. The evaluation of the system is carried on using Mammography Image Analysis Society (MIAS) database. The experimental result shows that the proposed method provides improved classification rate.

Improvement of Automated Detection Method for Clustered Microcalcification Based on Wavelet Transformation and Support Vector Machine

The main problem that corresponding with breast cancer is how to deal with small calcification part inside the breast called microcalcification (MC). A breast screening examination called mammogram is provided as preventive way. Mammogram image with a considerable amount of MC or called clustered MC has been a problem for the doctor and the radiologist. Particularly, when they should determine correctly the region of interest. This work is an improvement work from the previous work. It utilizes the Daubechies D4 wavelet as a feature extractor and the SVM classifier as an effective binary classifier. The escalating point shown with 84.44% of classification performance, 90% of sensitivity and 91.43% of specificity.

Classification of Clustered Microcalcifications in Mammograms using Particle Swarm Optimization and Least-Squares Support Vector Machine

Feature selection and classifier hyper-parameter optimization are important stages of any computer-aided diagnosis (CADx) system for mammography. The optimal selection for shape features, kernel parameter, and classifier regularization constant is crucial to achieve a good generalization and performance of least-squares support vector machines (LSSVMs). This paper presents a morphology-based CADx that uses a computationally attractive and unified scheme for accomplishing the model selection task. A heuristic parameter search based on particle swarm optimization (PSO) not only reduces the dimensionality of the input feature space but also optimizes hyper-parameters of the classifier. The performance of the proposed shape-based CADx including PSO-LSSVM parameter selection method is examined using 60 microcalcification clusters. Using different cross-validation procedures, the proposed PSO-LSSVM demonstrated a good generalization ability by producing classification accuracies higher than 92%. The best classification accuracy of 97% was obtained using the leave-one-out cross-validation procedure. Comparing the performance of PSO-LSSVM with PSO-SVM method that uses conventional SVM formulation, results demonstrated the attractive computational complexity and classification performance of PSO-LSSVM. General Terms Feature selection, Pattern recognition.

Stereotactic Vacuum-Assisted Biopsies on a Digital Breast 3D-Tomosynthesis System

The purpose of this study was to describe our operating process and to report results of 118 stereotactic vacuum-assisted biopsies performed on a digital breast 3D-tomosynthesis system. From October 2009 to December 2010, 118 stereotactic vacuum assisted biopsies have been performed on a digital breast 3D-tomosynthesis system. Informed consent was obtained for all patients. A total of 106 patients had a lesion, six had two lesions. Sixty-one lesions were clusters of micro-calcifications, 54 were masses and three were architectural distortions. Patients were in lateral decubitus position to allow shortest skin-target approach (or sitting). Specific compression paddle, adapted on the system, performed, and graduated, allowing localization in X-Y. Tomosynthesis views define the depth of lesion. Graduated Coaxial localization kit determines the beginning of the biopsy window. Biopsies were performed with an ATEC-Suros, 9 Gauge handpiece. All biopsies, except one, have reached the lesions. Five hemorrhages were incurred in the process, but no interruption was needed. Eight breast hematomas, were all spontaneously resolved. One was an infection. About 40% of patients had a skin ecchymosis. Processing is fast, easy, and requires lower irradiation dose than with classical stereotactic biopsies. Histology analysis reported 45 benign clusters of micro-calcifications, 16 malignant clusters of micro-calcifications, 24 benign masses, and 33 malignant masses. Of 13 malignant lesions, digital 2D-mammography failed to detect eight lesions and underestimated the classification of five lesions. Digital breast 3D-tomosynthesis depicts malignant lesions not visualized on digital 2D-mammography. Development of tomosynthesis biopsy unit integrated to stereotactic system will permit histology analysis for suspicious lesions.

PERFORMANCE OF A CAD SCHEME APPLIED TO IMAGES OBTAINED FROM MAMMOGRAPHIC FILM DIGITIZATION AND FULL-FIELD DIGITAL MAMMOGRAPHY (FFDM)

This work has as purpose to compare the effects of a CAD scheme applied to digitized and direct digital mamograms sets. A routine designed to be applied to mammogram in DICOM standard was developed and a schema based on the Watershed Transform to masses detection was applied to 252 ROIs from 130 digitized mammograms, resulting in 92% of true positive and 10% of false positives. For clustered microcalcifications detection, another procedure was applied to 165 ROIs from 120 mammograms, resulting in 93% of true positive and 16% of false positive. By using the same procedures to 154 digital mammograms obtained from FFDM, the rates have shown a little decrease in the scheme performance: 89% of true positive and 16% of false positive for masses detection; 90% of true positive and 27% of false positive for clusters detection. Although the tests with digital mammograms have been carried with a smaller number of images and different cases compared to the digitized ones, including several dense breasts images, the results can be considered comparable, mainly for clustered microcalcifications detection with a difference of only 3% between the sensibility rates for the both images sets. Another important feature affecting these results is the contrast difference between the two images set. This implies the need of extensive investigations not only with a larger number of cases from FFDM but also on the parameters related to its image acquisition as well as to its corresponding processing

Health Care Improvement: Comparative Analysis of Two CAD Systems in Mammographic Screening

Technological innovations have produced remarkable results in the health care sector. In particular, computer-aided detection (CAD) systems are becoming very useful and helpful in supporting physicians for early detection and control of some diseases such as neoplastic pathologies. In this paper, two different CAD systems able to detect and to localize microcalcification clusters in mammographic images are implemented. The two methods utilize an artificial neural network and a support vector machine, respectively, as classifier. Adopting the MIAS database as procedure testing, the performance of the two implemented systems are compared in terms of sensitivity, specificity, accuracy, free-response operating characteristic curves, and Cohen's kappa coefficient. The obtained values for the previous parameters show the efficiency of both methods to operate as “second opinion” in microcalcification cluster detection, improving the screening process efficiency.

Quantitative visually lossless compression ratio determination of JPEG2000 in digitized mammograms.

The current study presents a quantitative approach towards visually lossless compression ratio (CR) threshold determination of JPEG2000 in digitized mammograms. This is achieved by identifying quantitative image quality metrics that reflect radiologists' visual perception in distinguishing between original and wavelet-compressed mammographic regions of interest containing microcalcification clusters (MCs) and normal parenchyma, originating from 68 images from the Digital Database for Screening Mammography. Specifically, image quality of wavelet-compressed mammograms (CRs, 10:1, 25:1, 40:1, 70:1, 100:1) is evaluated quantitatively by means of eight image quality metrics of different computational principles and qualitatively by three radiologists employing a five-point rating scale. The accuracy of the objective metrics is investigated in terms of (1) their correlation (r) with qualitative assessment and (2) ROC analysis (A z index), employing pooled radiologists' rating scores as ground truth. The quantitative metrics mean square error, mean absolute error, peak signal-to-noise ratio, and structural similarity demonstrated strong correlation with pooled radiologists' ratings (r, 0.825, 0.823, -0.825, and -0.826, respectively) and the highest area under ROC curve (A z , 0.922, 0.920, 0.922, and 0.922, respectively). For each quantitative metric, the highest accuracy values of corresponding ROC curves were used to define metric cut-off values. The metrics cut-off values were subsequently used to suggest a visually lossless CR threshold, estimated to be between 25:1 and 40:1 for the dataset analyzed. Results indicate the potential of the quantitative metrics approach in predicting visually lossless CRs in case of MCs in mammography.

Sparse Representation for Detection of Microcalcification Clusters

Sparse Representation for Detection of Microcalcification Clusters

Tomosynthesis in X-ray: proven additional value?

Digital breast tomosynthesis (DBT) is a new promising modality for breast imaging. Breast tomosynthesis is based on a full-field digital mammography (FFDM) platforms, and the DBT images are obtained in the same standard projections (cranio-caudal and mediolateral oblique views) as for conventional mammography [1,2]. The tomographic images or “slices” are usually reconstructed at 1mm intervals and presented in the default setting as thin “slices” on the dedicated work-station. The images may, however, also be displayed as a volume consisting of several slices (“slabs”). The idea of using DBT is that the shape and margins of breast masses may be more clearly delineated by reducing or eliminating overlapping tissue, and the ability to distinguish superimposed tissue from breast lesions would be improved. Thus, it is suggested that this new technology may improve the specificity as compared with conventional mammography. Furthermore, the elimination of superimposed breast tissue should theoretically improve the detection of lesions otherwise hidden by dense breast parenchyma. The ability of DBT to reduce or eliminate the interpretation problems caused by overlapping breast tissue may be particularly valuable in women with dense breasts. Furthermore, it is suggested that digital breast tomosynthesis may improve the detection of architectural distortion especially in women with heterogeneous dense breasts. Theoretically, the very thin spiculations seen in architectural distortion would be expected to be more easily identified on 1mm thin slices as compared with a conventional projection mammogram. There has been a lot of concern regarding the perception (detection) and analysis (characterization) of calcifications on digital breast tomosynthesis. Theoretically, micro-calcifications may represent a challenge for DBT due to the so-called “thin-sliceeffect” since only few or microcalcifications might be seen on each slice and not all calcifications of cluster as is the case on conventional FFDM projection images. Viewing the microcalcifications in a “slab”-mode may resolve some of these problems, and a larger study comparing sharpness, contrast, and diagnostic quality of microcalcifications concluded that calcifications can be demonstrated with equal or even greater clarity on DBT than on mammography [3]. Analysis of microcalcification clusters on DBT may have a learning curve effect. There have been only few publications on DBT in a clinical setting so far, and consequently the future role of tomosynthesis, whether its implementation will be in mammography screening or in clinical (i.e., “diagnostic”) imaging, or in both settings, is still not clear.

Sparse Representation for Detection of Microcalcification Clusters

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. From these samples of the interest object class, a vocabulary of information-rich object parts is automatically constructed. The sparse representation is computed by the l1-regularized least square approach using the interior-point method. The method based on sparse representation expresses each testing sample as a linear combination of all the training samplesfrom the vocabulary. The sparse coefficient vector is obtained by l1-regularized least square through learning. MCs detectionis achieved by defining discriminatefunctions 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.

Characterization and guided-procedures of breast suspicious microcalcifications: can MicroPure ultrasound do it?

ObjectiveTo assess the diagnostic value of high-frequency (MicroPure) ultrasound in evaluating suspicious microcalcifications and to determine its capability in biopsy guidance. Subjects and methodsSixty-two cases with suspicious microcalcifications detected on mammographic examination had been re-evaluated by MicroPure US. The studied cases underwent true cut tissue/surgical excision biopsy. Histopathology revealed 25 benign and 37 malignant lesions and was considered the gold standard of reference. ResultsMalignant microcalcifications were easier to be visible at MicroPure US, as they were detected in 86.5% (n=32/39) compared to only 68% (n=17/25) of the benign lesions. US depicted more breast masses associated with malignant microcalcifications in 78% (n=29/37) than those associated with benign ones seen in 36% (n=9/25).Visibility of suspicious microcalcifications at US was aided by preliminary mammogram. Given known mammography location of these microcalcifications had made their visualization accessible by MicroPure US in 79% (n=49) of the cases. ConclusionMicroPure ultrasound cannot discriminate benign from malignant breast microcalcifications. MicroPure can be useful in detecting clustered microcalcifications that are not accessible by B-mode ultrasound; provided knowledge of their mammographic location and thus can provide better guidance for pre-surgical wire localization and ultrasound-guided biopsies.

Mammographic Image Denoising and Enhancement Using the Anscombe Transformation, Adaptive Wiener Filtering, and the Modulation Transfer Function

A new restoration methodology is proposed to enhance mammographic images through the improvement of contrast features and the simultaneous suppression of noise. Denoising is performed in the first step using the Anscombe transformation to convert the signal-dependent quantum noise into an approximately signal-independent Gaussian additive noise. In the Anscombe domain, noise is filtered through an adaptive Wiener filter, whose parameters are obtained by considering local image statistics. In the second step, a filter based on the modulation transfer function of the imaging system in the whole radiation field is applied for image enhancement. This methodology can be used as a preprocessing module for computer-aided detection (CAD) systems to improve the performance of breast cancer screening. A preliminary assessment of the restoration algorithm was performed using synthetic images with different levels of quantum noise. Afterward, we evaluated the effect of the preprocessing on the performance of a previously developed CAD system for clustered microcalcification detection in mammographic images. The results from the synthetic images showed an increase of up to 11.5 dB (p = 0.002) in the peak signal-to-noise ratio. Moreover, the mean structural similarity index increased up to 8.3 % (p < 0.001). Regarding CAD performance, the results suggested that the preprocessing increased the detectability of microcalcifications in mammographic images without increasing the false-positive rates. Receiver operating characteristic analysis revealed an average increase of 14.1 % (p = 0.01) in overall CAD performance when restored image sets were used.