Search

Breast cancer is the most common cancer among women and the second leading cause of female cancer mortality following lung cancer. Breast cancer also affects men but with a low incidence rate. However, the survival rate for men is much lower than women's. Early screening to identify breast abnormalities can increase the survival rate. Since the causes of this disease are not all known, primary prevention seems impossible. Therefore, early detection is the major key to surviving this disease. If breast cancer is detected earlier, there are more treatment options and a better chance for survival. The first sign of numerous breast cancer cases is the presence of microcalcifications in mammograms, which are small crystals of calcium apatites ranging from 0.1 mm to 0.5 mm. In this paper, we propose a multi-objective optimization approach to determine the optimal boundary between the signal subspace and noise subspace in TR-MUSIC algorithm.

Breast cancer is the most common type of cancer among women and it is the major cause of female cancer-related deaths worldwide. Microcalcifications, which are small crystals of calcium apatites, are considered the first sign of breast cancer in more than half of all breast cancer cases. Since these calcium apatites are very small and may be easily overlooked by the radiologists, automatic image processing systems can help radiologists in early diagnosis of breast cancer. In these systems, detection and segmentation of breast microcalcifications from the background tissue are important steps. The purpose of this work is to evaluate the performance of several breast microcalcifications segmentation techniques and select the best technique using a multicriteria decision making approach. The approaches were applied on 630 mammograms from the Digital Database for Screening Mammography. Of the 630 images, 315 images correspond to malignant cases and 315 correspond to benign cases. The efficiency of the considered techniques was evaluated by using five metrics, namely a similarity index, the extra overlap fraction, sensitivity, specificity, and accuracy.

In this paper we examine data fusion methods for multi-view data classification. We present a decision concept which explicitly takes into account the input multi-view structure, where for each case there is a different subset of relevant views. This data fusion concept, which we dub Mixture of Views, is implemented by a special purpose neural network architecture. It is demonstrated on the task of classifying breast microcalcifications as benign or malignant based on CC and MLO mammography views. The single view decisions are combined by a data-driven decision, according to the relevance of each view in a given case, into a global decision. The method is evaluated on a large multi-view dataset extracted from the standardized digital database for screening mammography (DDSM). The experimental results show that our method outperforms previously suggested fusion methods.

In this paper we address the problem of differentiating between malignant and benign tumors based on their appearance in the CC and MLO mammography views. Classification of clustered breast microcalcifications into benign and malignant categories is an extremely challenging task for computerized algorithms and expert radiologists alike. We describe a deep-learning classification method that is based on two view-level decisions, implemented by two neural networks, followed by a single-neuron layer that combines the viewlevel decisions into a global decision that mimics the biopsy results. Our method is evaluated on a large multi-view dataset extracted from the standardized digital database for screening mammography (DDSM). Experimental results show that our network structure significantly improves on previously suggested methods.

Early detection is key to surviving breast cancer. The earliest indication of potential breast cancer detectable by current screening methods is the presence of microcalcifications. The low efficiency of ultrasound in detecting these microcalcifications is due to several factors, including the low spatial resolution of the ultrasound images and the speckle noise, which masks the tiny microcalcifications. This paper aims to investigate the efficiency of the time reversal multiple signal classification algorithm in detecting breast microcalcifications. Experiments were performed on numerical phantoms, and results show that the TR-MUSIC algorithm efficiency depends on several parameters.

Breast microcalcifications are one of the most important mammographic findings related to the existence of the breast cancer. Radiologists usually characterize microcalcifications based on their morphologies, the distribution within the cluster they form, the shape of the cluster and its relative location inside the breast. In this study, we focus on the latter factor and we study its effect on the probability of malignancy. The main purpose of our study is to generate probabilistic breast cancer atlases for clusters of microcalcifications in order to visualize the influence of cluster location on cancer probability. We propose a framework for the generation of such atlases, including segmentation of important breast landmarks and projection of different clusters of microcalcifications on a reference breast shape. The generation of the atlases is implemented using mammograms from the Digital Database of Screening Mammography. The obtained probabilistic atlases reveal specific areas in the breast of higher occurrence of clusters and higher risk of malignancy.

The usefulness of breast ultrasound could be extended by improving the detection of microcalcifications by being able to extract and enhance true microcalcifications whilst simultaneously eliminating hyperechoic spots that can lead to false-positive detections of microcalcifications (false-microcalcifications). This study investigated the use of a strain-compounding technique with Nakagami imaging to provide information associated with scatterer and elastic characteristics of tissues when attempting to identify microcalcifications and false-microcalcifications. To validate this concept, raw data of ultrasound backscattered signals were collected from 20 lesions with suspicious microcalcifications (15 microcalcifications and 5 false-microcalcifications verified by mammography and ultrasound-guided biopsy). For each region in which microcalcifications were suspected, estimates of the mean Nakagami parameter (m avg ) in the strain-compounding Nakagami images were normalized to those of the corresponding reference Nakagami images. Receiver operating characteristic (ROC) curve analysis was adopted to assess the diagnostic performances. The results demonstrated that the normalized m avg estimates for microcalcifications and false-microcalcifications were 0.98±0.12 and 2.11±0.30 (p

Classification of breast microcalcifications and clusters depends characteristics selected to be the input for an automated classifier. Artificial neural networks have been used to aid in classification of structures on mammograms images. However, to achieve the classification, some attributes have to be adequately extracted from the images in the database used for tests. As a part of a CAD scheme in development, our intention is to establish a ANN-based classifier, intended to distribute detected clustered microcalcifications in one of 5 classes, according to BI-RADS classification (normal, benign, probably benign, suspicious and probably malignant). This work reports a part of this procedure, by extracting and selecting most of significant characteristics regarding digitized mammography images containing clustered microcalcifications. Two distinct classes-probably benign and suspicious-are considered in order to compare the selected characteristics incidence distribution. Distance between both classes could be estimated by using Gaussian curves. Images used for the tests were from a database composed by mammograms digitized with 600 dpi of spatial resolution in a andbit grayscale. The regions of interest were selected based on physicians reports on the existence of a cluster. This study has shown that characteristics just as irregularity, number of microcalcifications in a cluster, and cluster area are already enough to separate the processed images in two very distinct classes-suspicious and probably benign, although other features could be necessary for a more detailed classification.

A method for the automatic detection and the three dimensional localization of clustered microcalcifications is described. It is based on the analysis of two mammograms: one is the craniocaudal view and the other is the mediolateral view. Both mammograms are digitized with 400 dpi, their resolution allows us to have 16 pixels per millimeter, and to detect small microcalcifications (125 micrometer). The basic detection algorithm allows the correct detection of microcalcifications (MC) in the range of 90 % and even more for 2D clusters. The clusters (CL) detected on each mammogram are matched and their position is given in 3D by using a continuous deformation model of the breast tissues during their compression in the mammographic system. Clusters containing 3 or more microcalcifications can be isolated and positionned in the breast tissues. Their precise localization based on the deformation model can be used to guide the needle for biopsies.