SVM-Based Microcalcification Detection in Digital Mammograms

This paper presents a computer-aided diagnosis (CAD) system for automatic detection of clustered microcalcifications (MCs) in digitized mammograms. The proposed system consists of two main steps. First, potential MC pixels in the mammograms are segmented out by using four mixed features consisting of two wavelet features and two gray level statistical features and then the potential MC pixels are labeled into potential individual MC objects by their spatial connectivity. Second, MCs are detected by extracting a set of 17 features from the potential individual MC objects. The classifier which is used in the first step is a multilayer feedforward neural network classifier but for the second step we have used Adaboost with SVM-based component classifier. Component classifiers which we used in our combining method are SVM classifiers with RBF kernel. The method was applied to a database of 40 mammograms (Nijmegen database) containing 105 clusters of MCs. A free-response operating characteristics (FROC) curve is used to evaluate the performance of CAD system. Results show that the proposed system gives quite satisfactory performance. In particular, 89.55% mean true positive detection rate is achieved at the cost of 0.921 false positive per image.

This paper attempts to pinpoint different techniques for Pectoral Muscle (PM) segmentation, Microcalcification (MC) detection and classification in digital mammograms. The segmentation of PM and detection of MC and its classification are mostly based on image processing and data mining techniques. The review centered on major techniques in image processing and data mining that is employed for PM segmentation, MC detection and classification in digital mammograms. Breast cancer is one of the significant causes of death among women aged above 40. Mammography is considered the most successful means for prompt and timely detection of breast cancers. One notable visual indication of the malignant growth is the appearance of Masses, Architectural Distortions, and Microcalcification Clusters (MCCs). There are some disadvantages and hurdles for mankind viewers, and it is hard for radiologists to supply both precise and steady assessment for a large number of mammograms created in extensive screening. Computer Aided Detection has been employed to help radiologists in detecting MC and MCCs. The automatic recognition of malignant MCCs could be very helpful for diagnostic purpose. In this paper, we summarize the methods of automatic detection and classification of MCs in digitized mammograms. Pectoral muscle segmentation techniques are also summarized. The techniques used for segmentation of PM, MC detection and classification in a digitized mammogram are reviewed.

Detection of microcalcifications in digital mammograms using combined model-based and statistical textural features

In this paper, we present a novel approach to detect microcalcifications (MCCs) in the mammograms. Microcalcification has approximately a size of several pixels in diameter on early cancer mammograms and has low contrast. So it is difficult to detection the microcalcifications. The essential idea of propose approach is to apply morphological and wavelet transform to locate the micro calcifications in digital mammograms. The presented method overcome higher true positive rate (TPR) but higher false positive (FP) problem by using single wavelet transform or morphology. The experiment results show the presented method has higher TPR and reducing FP obviously. Using the mammogram data form the Mammographic Image Analysis Society (MIAS) database the TPR is 80.2% at the cost of average 2.5 false microcalcifications per region of interest (ROI)

Clustered microcalcifications (MCCs) on mammograms are important hints of breast cancer. Nevertheless, it is a complex and difficult task for radiologists to detect the clustered MCCs from the tissue background of mammograms only by naked eyes. This paper presents a method for computer-aided detection of MCCs in digital mammograms. The detection algorithm mainly consists of two different methods. The first one, based on the difference-image technique, recognizes high-frequency signals and very high-frequency noise. The second one is able to extract high-frequency signal by exploiting a wavelet based noise suppression and neural network (NN) classification. In the false-positive reduction step, false signals are separated from MCCs by means of an AND operation on signals from two methods. The algorithm is tested with a series of clinical mammograms. A sensitivity ofmore than 90% is obtained at a relatively low false-positive (FP) detection of 2.18 per image. The results are compared with thejudgement ofradiological experts, and they are very encouraging.

The appearance of micro-calcifications in mammograms is a crucial early sign of breast cancer. Automatic micro-calcification detection techniques play an important role in cancer diagnosis and treatment. This, however, still remains a challenging task. This paper presents novel algorithms for the detection of micro-calcifications using stochastic resonance (SR) noise. In these algorithms, a suitable dose of noise is added to the abnormal mammograms such that the performance of a suboptimal lesion detector is improved without altering the detector's parameters. First, a SR noise-based detection approach is presented to improve some suboptimal detectors which suffer from model mismatch due to the Gaussian assumption. Furthermore, a SR noise-based detection enhancement framework is presented to deal with more general model mismatch cases. Our algorithms and the framework are tested on a set of 75 representative abnormal mammograms. They yield superior performance when compared with several classification and detection approaches developed in our work as well as those available in the literature.

Clustered microcalcifications (MCs) in mammograms are an important early sign of breast cancer in women. Their accurate detection is important in computer-aided detection (CADe). In this paper, we integrated the possibilistic fuzzy c-means (PFCM) clustering algorithm and weighted support vector machine (WSVM) for the detection of MC clusters in full-field digital mammograms (FFDM). For each image, suspicious MC regions are extracted with region growing and active contour segmentation. Then geometry and texture features are extracted for each suspicious MC, a mutual information-based supervised criterion is used to select important features, and PFCM is applied to cluster the samples into two clusters. Weights of the samples are calculated based on possibilities and typicality values from the PFCM, and the ground truth labels. A weighted nonlinear SVM is trained. During the test process, when an unknown image is presented, suspicious regions are located with the segmentation step, selected features are extracted, and the suspicious MC regions are classified as containing MC or not by the trained weighted nonlinear SVM. Finally, the MC regions are analyzed with spatial information to locate MC clusters. The proposed method is evaluated using a database of 410 clinical mammograms and compared with a standard unweighted support vector machine (SVM) classifier. The detection performance is evaluated using response receiver operating (ROC) curves and free-response receiver operating characteristic (FROC) curves. The proposed method obtained an area under the ROC curve of 0.8676, while the standard SVM obtained an area of 0.8268 for MC detection. For MC cluster detection, the proposed method obtained a high sensitivity of 92 % with a false-positive rate of 2.3 clusters/image, and it is also better than standard SVM with 4.7 false-positive clusters/image at the same sensitivity.

Spectral Phase Based Medical Image Processing 1

In computer-aided detection of microcalcifications (MCs), the detection accuracy is often compromised by frequent occurrence of false positives (FPs), which can be attributed to a number of factors, including imaging noise, inhomogeneity in tissue background, linear structures, and artifacts in mammograms. In this study, the authors investigated a unified classification approach for combating the adverse effects of these heterogeneous factors for accurate MC detection. To accommodate FPs caused by different factors in a mammogram image, the authors developed a classification model to which the input features were adapted according to the image context at a detection location. For this purpose, the input features were defined in two groups, of which one group was derived from the image intensity pattern in a local neighborhood of a detection location, and the other group was used to characterize how a MC is different from its structural background. Owing to the distinctive effect of linear structures in the detector response, the authors introduced a dummy variable into the unified classifier model, which allowed the input features to be adapted according to the image context at a detection location (i.e., presence or absence of linear structures). To suppress the effect of inhomogeneity in tissue background, the input features were extracted from different domains aimed for enhancing MCs in a mammogram image. To demonstrate the flexibility of the proposed approach, the authors implemented the unified classifier model by two widely used machine learning algorithms, namely, a support vector machine (SVM) classifier and an Adaboost classifier. In the experiment, the proposed approach was tested for two representative MC detectors in the literature [difference-of-Gaussians (DoG) detector and SVM detector]. The detection performance was assessed using free-response receiver operating characteristic (FROC) analysis on a set of 141 screen-film mammogram (SFM) images (66 cases) and a set of 188 full-field digital mammogram (FFDM) images (95 cases). The FROC analysis results show that the proposed unified classification approach can significantly improve the detection accuracy of two MC detectors on both SFM and FFDM images. Despite the difference in performance between the two detectors, the unified classifiers can reduce their FP rate to a similar level in the output of the two detectors. In particular, with true-positive rate at 85%, the FP rate on SFM images for the DoG detector was reduced from 1.16 to 0.33 clusters/image (unified SVM) and 0.36 clusters/image (unified Adaboost), respectively; similarly, for the SVM detector, the FP rate was reduced from 0.45 clusters/image to 0.30 clusters/image (unified SVM) and 0.25 clusters/image (unified Adaboost), respectively. Similar FP reduction results were also achieved on FFDM images for the two MC detectors. The proposed unified classification approach can be effective for discriminating MCs from FPs caused by different factors (such as MC-like noise patterns and linear structures) in MC detection. The framework is general and can be applicable for further improving the detection accuracy of existing MC detectors.

Microcalcification (MC) clusters in mammograms can be important early signs of breast cancer in women. Accurate detection of MC clusters is an important but challenging problem. In this paper, we propose the use of a recently developed machine learning technique -- relevance vector machine (RVM) -- for automatic detection of MCs in digitized mammograms. RVM is based on Bayesian estimation theory, and as a feature it can yield a decision function that depends on only a very small number of so-called <i>relevance vectors</i>. We formulate MC detection as a supervised-learning problem, and use RVM to classify if an MC object is present or not at each location in a mammogram image. MC clusters are then identified by grouping the detected MC objects. The proposed method is tested using a database of 141 clinical mammograms, and compared with a support vector machine (SVM) classifier which we developed previously. The detection performance is evaluated using the free-response receiver operating characteristic (FROC) curves. It is demonstrated that the RVM classifier matches closely with the SVM classifier in detection performance, and does so with a much sparser kernel representation than the SVM classifier. Consequently, the RVM classifier greatly reduces the computational complexity, making it more suitable for real-time processing of MC clusters in mammograms.

Computer aided detection system for micro calcifications in digital mammograms

In this paper, we propose a novel combinational SVM algorithm via a set of decision rules to achieve better performances in microcalcification detection inside digital mammograms towards computer aided breast cancer diagnosis. Based on the discovery that the polynomial SVM is sensitive to MC (microcalcification) pixels and the linear SVM is sensitive to non-MC pixels, we designed an adaptive threshold mechanism via establishment of their correspondences to exploit the complementary nature between the polynomial SVM and the linear SVM. Experiments show that the proposed algorithm successfully reduced false positive detection rate while keeping the true positive detection rate competitive.

Detection of microcalcifications using nonlinear beamforming techniques.

We aimed to evaluate the influence of image reduction using a bi-cubic interpolation method on the accuracy of detection of clustered microcalcifications (MCLs) and masses on digital mammograms. Digital mammograms (n=194) of 97 subjects were selected retrospectively, comprising 47 patients with clustered MCLs or masses and 52 controls. Images were acquired in the craniocaudal view by phase-contrast mammography (PCM). Original PCM images comprised 25-&mu;m pixels. The reduced images converted from the originals by bi-cubic interpolation were of 50-&mu;m pixel size. Five observers independently interpreted all images, and rated their confidence concerning the presence of lesions on a continuous 0-100 scale. Receiver-operating characteristic (ROC) analysis was performed using the jackknife method and LABMRMC program. Differences in areas under the curve (AUC) values based on 95% confidence intervals were evaluated. The average AUC values for detection of masses were 0.8435 and 0.8646 for the original and reduced images, respectively. The difference between the average AUC values was not statistically significant (<i>p</i>=0.5855). Average AUC values for clustered MCLs detection were 0.9273 and 0.9574 for the original and reduced images, respectively. This difference was not statistically significant (<i>p</i>=0.1949). Detection of masses and clustered MCLs on digital mammograms was unaffected by bi-cubic interpolation image reduction.

The most usually used least squares support vector machines(LS-SVM) modeling method In near infrared(NIR) spectra measurement are based on a single kernel function. However, the single kernel function can not describe the whole data very well, thus affecting the LS-SVM modeling results. In this paper, we introduced the mixtures of kernels to replace the original single kernel, then the LS-SVM based on the mixtures of kernels was applied to model prediction. It was proved by the experimental results that the algorithm can obviously improve the model prediction performance of diesel cetane number based on the LS-SVM compared with other methods in existence.