A method for detecting microcalcifications in digital mammograms.

Mammography is one of the most efficient imaging techniques for the early detection and diagnosis of breast cancer in woman. The appearance of microcalcifications (MCs) in X-ray mammograms can be regarded as important early diagnostic feature of breast cancer. However, the detection of MCs in X-ray mammograms only depend on radiologists by visual inspection is a difficult task. In this paper, a novel algorithm for the automated detection of MCs in digital mammograms is described. The aim of approach is to locate suspicious MCs by analyzing the distribution of brightness over the digital mammograms. The algorithm for the detection of MCs is performed in two steps. First, the digital X-ray mammogram intensity surface is well-fitted by the least squares support vector machines (LS-SVM), and then the maximum extremum points are detected on the fitted intensity surface by convolving the image with the second order directional derivative operators deduced from the mapped LS-SVM with mixture of kernels. The proposed approach is developed and evaluated by using MIAS database. The experimental results demonstrate the possible MCs are detected accurately and efficiently.

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.

This study proposed a method to evaluate proper experimental conditions of eddy current tests under a low signal-to-noise ratio. This method was applied to quantify the detection reliability of the eddy current test to detect corrosion pits on the surface of austenitic stainless-steel weld cladding from the perspectives of probability of detection and probability of false alarm. The fluctuations of flaw signal and noise were described using truncated bivariate normal distributions of a two-dimensional vector composed of the real and imaginary components of a signal. The probabilities of detection and false alarms were formalized as cumulative distributions of the estimated distributions of the maximum flaw signal and the noise exceeding a decision threshold. The receiver operating characteristic curves were created by coupling the probabilities of detection and false alarms at various thresholds. The area under the curve was used to quantify the detection reliability, simultaneously considering the probabilities of detection and false alarms. The results obtained in this study support the applicability of this method in quantitatively evaluating the detection reliability of a non-destructive inspection under a low signal-to-noise ratio.

We aimed to quantitatively assess the effect of baseline breast density on the incidence, stage, and mortality, and also the natural course of the disease, considering the sensitivity of mammography to clarify its causal or masking effect. In total, 15,658 women ages 45 to 59 years from the Kopparberg randomized controlled trial in Sweden were prospectively followed from 1977 until 2004 to ascertain breast cancer incidence and death. Dense breast tissue collected at the beginning of the study was defined as pattern IV or V by the Tabár classification. Conventional risk factors were also collected at baseline. The three-state Markov model was used to estimate the preclinical incidence rate and the mean sojourn time given the fixed sensitivity. Dense breast tissue was significantly associated with breast cancer incidence [relative risk (RR)=1.57 (1.18-1.67)] and with breast cancer mortality [RR=1.91 (1.26-2.91)] after adjusting for other risk factors. Cumulative incidence rates irrespective of nonadvanced and advanced breast cancer were higher in dense breast tissue compared with nondense tissue but no difference in survival was detected between dense and nondense breast tissue. Dense breast tissue had a higher preclinical incidence rate (causal effect) and shorter mean sojourn time (masking effect) compared with nondense breast tissue by controlling the sensitivity of mammography. We corroborated the effect of baseline breast density with a higher incidence and mortality and also showed its contribution to a masking effect with long-term follow-up data. Results suggest that the screening policy with a predominantly shorter screening interval and with alternative imaging techniques might be indicated in women with dense breast tissue.

This paper presents an approach for early breast cancer diagnostic by employing combination of artificial neural networks (ANN) and wavelet based subband image decomposition which detect microcalcification in digital mammograms. The microcalcifications correspond to high-frequency components of the image spectrum, detection of microcalcifications is achieved by decomposing the mammograms into different frequency subbands, suppressing the low-frequency subband, and finally, reconstructing the mammogram from the subbands containing only high frequencies. For this approach we employed different types of wavelet packets. We used the result as an input of neural network for classification. The proposed methodology is tested using the Nijmegen and the Mammographic Image Analysis Society (MIAS) mammographic databases and images collected from local hospitals. Results are presented as the receiver operating characteristic (ROC) performance and are quantified by the area under the ROC curve.

Automated breast ultrasound is likely to be a key player in the future of imaging for women with dense breast tissue. There has previously been a gap in the ability of technology to screen dense breast tissue. Dense tissue can not only obscure cancer when imaged with x-ray mammography, but is also a risk factor, increasing the risk of breast cancer four- to six-fold for women with fibroglandular tissue greater than 60%. Ultrasound has been proven to find cancers that are not visible with mammography. Automated breast ultrasound standardizes the use of ultrasound, producing a more comprehensive and consistent image, which physicians can review quickly and easily. There is a promising future for the use of automated ultrasound for screening women with dense breast tissue. Automated breast ultrasound is proving to be a useful adjunct to mammography, which helps to catch cancer at an earlier and more treatable stage.

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.

Research indicates that incorporating supplemental breast ultrasound in addition to mammography can enhance the sensitivity of public mammography screening, particularly for women with dense breast tissue. However, little information exists regarding the feasibility of integrating ultrasound into public mammography screening. Moreover, limited data exist on the awareness, perceptions, and experiences of both screening clients and healthcare providers regarding dense breast tissue, its impact on screening effectiveness, and the acceptability and implications of incorporating additional ultrasound. In a prospective, controlled mixed-methods study, 31 semi-structured telephone interviews were conducted with both screening professionals and clients identified as having dense breast tissue. Six mammography screening centres in Germany participated in the qualitative part of the DIMASOS2 study (Density-Indicated Mammographic-Sonographic Breast Cancer Screening), where additional ultrasound was offered to women aged 50 to 69 years identified as having dense breast tissue. The interviews were analysed using qualitative content analysis. Clients expressed appreciation for the additional ultrasound examination; half of them were already aware of their dense breast tissue but lacked knowledge about its implications for diagnostic accuracy. Healthcare professionals felt that diagnostic sensitivity of mammography screening needed to be improved, but also faced challenges such as insufficient evidence for adjunct measures, concerns about overdiagnosis and false positives, and substantial organisational barriers to implementing ultrasound examinations. This study highlights a gap in open discussions about breast density and its impact on screening accuracy. The absence of evidence-based information hampers informed decision making for both healthcare providers and clients. Moreover, substantial organisational constraints hinder the incorporation of breast ultrasound into public screening programme, leading to a complex and unsatisfactory situation for healthcare professionals and clients.

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

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.

Application of Abbreviated Protocol of Magnetic Resonance Imaging for Breast Cancer Screening in Dense Breast Tissue

The aim of this study was to evaluate the association between insulin-like growth factor 1 receptor (IGF-1R) expression in breast cancer tissue and mammographic density and the clinical significance of IGF-1R overexpression. A total of 167 patients with primary invasive breast cancer were analyzed. Mammographic breast density and IGF-1R overexpression were correlated with clinicopathological parameters and analyzed by overall survival (OS) and disease-free survival (DFS). Increased breast tissue density was significantly associated with age, body mass index, menopausal status, histological grade and IGF-1R overexpression in the univariate analysis and with age (P=0.001), histological grade (P=0.045) and IGF-1R overexpression (P=0.021) in the multivariate analysis. IGF-1R overexpression was significantly associated with dense breast tissue in patients aged >40 years (P=0.002). IGF-1R overexpression in breast cancer in premenopausal women was associated with human epidermal growth factor receptor 2 (HER-2) positivity (P=0.016) and worse DFS (P=0.0414). There was no significant difference in OS and DFS between dense and non-dense breast tissue. IGF-1R expression in breast cancer tissue was significantly associated with mammographic breast tissue density in patients aged >40 years. It appears that IGF-1R expression in breast cancer tissue plays an important role in breast cancer in patients with dense breast tissue. In premenopausal women, IGF-1R overexpression in breast cancer tissue was significantly associated with HER-2 positivity and poor DFS.

This paper presents a novel analytical derivation of the false alarm probability (FAP) and detection probability (DP) for non-line-of-sight (NLOS) detection based on LTE signals. Position estimation in indoor or urban area with cellular wireless communication systems is getting more and more important. However, especially in these environments NLOS propagation causes positioning errors in the order of hundreds of meters. Thus, detection and mitigation of NLOS signals is a critical task. In this paper, we derive the FAP and DP on power-scaled detectors based on LTE multipath signals. The derivation considers frequency-selective fading channels taking sub-sample multipath interference, channel dynamics and initial frequency offsets into account. The results show a simple way to calculate the DP versus FAP. Simulation results verify the analytical probabilities for the WINNER II C2 channel model. Additionally, the simulations show the improved FAP of an antenna array at the receiver.

Automatic detection of clustered microcalcifications in digital mammograms using mathematical morphology and neural networks

In this paper, we describe an algorithm for enhancement and detection of microcalcifications in digital mammograms. The microcalcifications are first enhanced by a undecimated wavelet transform and segmented by a classification based method. After spatial features are extracted from the segmented images, a neural network and a Bayes classifier are used to identify clustered microcalcifications. We have tested this algorithm on 40 regions-of-interest images extracted from the database provided by the University Hospital of Nijmegen.