A fully automated scheme for mammographic segmentation and classification based on breast density and asymmetry

Spatial Distribution Analysis of Novel Texture Feature Descriptors for Accurate Breast Density Classification

Breast density has been recognised as an important biomarker that indicates the risk of developing breast cancer. Accurate classification of breast density plays a crucial role in developing a computer-aided detection (CADe) system for mammogram interpretation. This paper proposes a novel texture descriptor, namely, rotation invariant uniform local quinary patterns (RIU4-LQP), to describe texture patterns in mammograms and to improve the robustness of image features. In conventional processing schemes, image features are obtained by computing histograms from texture patterns. However, such processes ignore very important spatial information related to the texture features. This study designs a new feature vector, namely, K-spectrum, by using Baddeley's K-inhom function to characterise the spatial distribution information of feature point sets. Texture features extracted by RIU4-LQP and K-spectrum are utilised to classify mammograms into BI-RADS density categories. Three feature selection methods are employed to optimise the feature set. In our experiment, two mammogram datasets, INbreast and MIAS, are used to test the proposed methods, and comparative analyses and statistical tests between different schemes are conducted. Experimental results show that our proposed method outperforms other approaches described in the literature, with the best classification accuracy of 92.76% (INbreast) and 86.96% (MIAS).

A Fast Hybrid Classification Algorithm with Feature Reduction for Medical Images

In this paper, we are introducing a fast hybrid fuzzy classification algorithm with feature reduction for medical images. We incorporated the quantum-based grasshopper computing algorithm (QGH) with feature extraction using fuzzy clustering technique (C-means). QGH integrates quantum computing into machine learning and intelligence applications. The objective of our technique is to the integrate QGH method, specifically into cervical cancer detection that is based on image processing. Many features such as color, geometry, and texture found in the cells imaged in Pap smear lab test are very crucial in cancer diagnosis. Our proposed technique is based on the extraction of the best features using a more than 2600 public Pap smear images and further applies feature reduction technique to reduce the feature space. Performance evaluation of our approach evaluates the influence of the extracted feature on the classification precision by performing two experimental setups. First setup is using all the extracted features which leads to classification without feature bias. The second setup is a fusion technique which utilized QGH with the fuzzy C-means algorithm to choose the best features. In the setups, we allocate the assessment to accuracy based on the selection of best features and of different categories of the cancer. In the last setup, we utilized a fusion technique engaged with statistical techniques to launch a qualitative agreement with the feature selection in several experimental setups.

Convolutional Neural Networks for Breast Density Classification: Performance and Explanation Insights

We propose and evaluate a procedure for the explainability of a breast density deep learning based classifier. A total of 1662 mammography exams labeled according to the BI-RADS categories of breast density was used. We built a residual Convolutional Neural Network, trained it and studied the responses of the model to input changes, such as different distributions of class labels in training and test sets and suitable image pre-processing. The aim was to identify the steps of the analysis with a relevant impact on the classifier performance and on the model explainability. We used the grad-CAM algorithm for CNN to produce saliency maps and computed the Spearman’s rank correlation between input images and saliency maps as a measure of explanation accuracy. We found that pre-processing is critical not only for accuracy, precision and recall of a model but also to have a reasonable explanation of the model itself. Our CNN reaches good performances compared to the state-of-art and it considers the dense pattern to make the classification. Saliency maps strongly correlate with the dense pattern. This work is a starting point towards the implementation of a standard framework to evaluate both CNN performances and the explainability of their predictions in medical image classification problems.

Methodology for Exploring Patterns of Epigenetic Information in Cancer Cells Using Data Mining Technique

Epigenetic changes are a necessary characteristic of all cancer types. Tumor cells usually target genetic changes and epigenetic alterations as well. It is most beneficial to identify epigenetic similar features among cancer various types to be able to discover the appropriate treatments. The existence of epigenetic alteration profiles can aid in targeting this goal. In this paper, we propose a new technique applying data mining and clustering methodologies for cancer epigenetic changes analysis. The proposed technique aims to detect common patterns of epigenetic changes in various cancer types. We demonstrated the validation of the new technique by detecting epigenetic patterns across seven cancer types and by determining epigenetic similarities among various cancer types. The experimental results demonstrate that common epigenetic patterns do exist across these cancer types. Additionally, epigenetic gene analysis performed on the associated genes found a strong relationship with the development of various types of cancer and proved high risk across the studied cancer types. We utilized the frequent pattern data mining approach to represent cancer types compactly in the promoters for some epigenetic marks. Utilizing the built frequent pattern item set, the most frequent items are identified and yield the group of the bi-clusters of these patterns. Experimental results of the proposed method are shown to have a success rate of 88% in detecting cancer types according to specific epigenetic pattern.

Unsupervised domain adaptation for the segmentation of breast tissue in mammography images

BACKGROUND AND OBJECTIVE

Breast density refers to the proportion of glandular and fatty tissue in the breast and is recognized as a useful factor assessing breast cancer risk. Moreover, the segmentation of the high-density glandular tissue from mammograms can assist medical professionals visualizing and localizing areas that may require additional attention. Developing robust methods to segment breast tissues is challenging due to the variations in mammographic acquisition systems and protocols. Deep learning methods are effective in medical image segmentation but they often require large quantities of labelled data. Unsupervised domain adaptation is an area of research that employs unlabelled data to improve model performance on variations of samples derived from different sources.

METHODS

First, a U-Net architecture was used to perform segmentation of the fatty and glandular tissues with labelled data from a single acquisition device. Then, adversarial-based unsupervised domain adaptation methods were used to incorporate single unlabelled target domains, consisting of images from a different machine, into the training. Finally, the domain adaptation model was extended to include multiple unlabelled target domains by combining a reconstruction task with adversarial training.

RESULTS

The adversarial training was found to improve the generalization of the initial model on new domain data, demonstrating clearly improved segmentation of the breast tissues. For training with multiple unlabelled domains, combining a reconstruction task with adversarial training improved the stability of the training and yielded adequate segmentation results across all domains with a single model.

CONCLUSIONS

Results demonstrated the potential for adversarial-based domain adaptation with U-Net architectures for segmentation of breast tissue in mammograms coming from several devices and demonstrated that domain-adapted models could achieve a similar agreement with manual segmentations. It has also been found that combining adversarial and reconstruction-based methods can provide a simple and effective solution for training with multiple unlabelled target domains.

Algorithms and methods for computerized analysis of mammography images in breast cancer risk assessment

BACKGROUND AND OBJECTIVES

The computerized analysis of mammograms for the development of quantitative biomarkers is a growing field with applications in breast cancer risk assessment. Computerized image analysis offers the possibility of using different methods and algorithms to extract additional information from screening and diagnosis images to aid in the assessment of breast cancer risk. In this work, we review the algorithms and methods for the automated, computerized analysis of mammography images for the task mentioned, and discuss the main challenges that the development and improvement of these methods face today.

METHODS

We review the recent progress in two main branches of mammography-based risk assessment: parenchymal analysis and breast density estimation, including performance indicators of most of the studies considered. Parenchymal analysis methods are divided into feature-based methods and deep learning-based methods; breast density methods are grouped into area-based, volume-based, and breast categorization methods. Additionally, we identify the challenges that these study fields currently face.

RESULTS

Parenchymal analysis using deep learning algorithms are on the rise, with some studies showing high-performance indicators, such as an area under the receiver operating characteristic curve of up to 90. Methods for risk assessment using breast density report a wider variety of performance indicators; however, we can also identify that the approaches using deep learning methods yield high performance in each of the subdivisions considered.

CONCLUSIONS

Both breast density estimation and parenchymal analysis are promising tools for the task of breast cancer risk assessment; deep learning methods have shown performance comparable or superior to the other considered methods. All methods considered face challenges such as the lack of objective comparison between them and the lack of access to datasets from different populations.

Novel Texture Feature Descriptors Based on Multi-Fractal Analysis and LBP for Classifying Breast Density in Mammograms

This paper investigates the usefulness of multi-fractal analysis and local binary patterns (LBP) as texture descriptors for classifying mammogram images into different breast density categories. Multi-fractal analysis is also used in the pre-processing step to segment the region of interest (ROI). We use four multi-fractal measures and the LBP method to extract texture features, and to compare their classification performance in experiments. In addition, a feature descriptor combining multi-fractal features and multi-resolution LBP (MLBP) features is proposed and evaluated in this study to improve classification accuracy. An autoencoder network and principal component analysis (PCA) are used for reducing feature redundancy in the classification model. A full field digital mammogram (FFDM) dataset, INBreast, which contains 409 mammogram images, is used in our experiment. BI-RADS density labels given by radiologists are used as the ground truth to evaluate the classification results using the proposed methods. Experimental results show that the proposed feature descriptor based on multi-fractal features and LBP result in higher classification accuracy than using individual texture feature sets.

Breast glandularity and mean glandular dose assessment using a deep learning framework: Virtual patients study

PURPOSE

Breast dosimetry in mammography is an important aspect of radioprotection since women are exposed periodically to ionizing radiation due to breast cancer screening programs. Mean glandular dose (MGD) is the standard quantity employed for the establishment of dose reference levels in retrospective population studies. However, MGD calculations requires breast glandularity estimation. This work proposes a deep learning framework for volume glandular fraction (VGF) estimations based on mammography images, which in turn are converted to glandularity values for MGD calculations.

METHODS

208 virtual breast phantoms were generated and compressed computationally. The mammography images were obtained with Monte Carlo simulations (MC-GPU code) and a ray-tracing algorithm was employed for labeling the training data. The architectures of the neural networks are based on the XNet and multilayer perceptron, adapted for each task. The network predictions were compared with the ground truth using the coefficient of determination (r²).

RESULTS

The results have shown a good agreement for inner breast segmentation (r² = 0.999), breast volume prediction (r² = 0.982) and VGF prediction (r² = 0.935). Moreover, the DgN coefficients using the predicted VGF for the virtual population differ on average 1.3% from the ground truth values. Afterwards with the obtained DgN coefficients, the MGD values were estimated from exposure factors extracted from the DICOM header of a clinical cohort, with median(75 percentile) values of 1.91(2.45) mGy.

CONCLUSION

We successfully implemented a deep learning framework for VGF and MGD calculations for virtual breast phantoms.

Fully Automated Breast Density Segmentation and Classification Using Deep Learning

Breast density estimation with visual evaluation is still challenging due to low contrast and significant fluctuations in the mammograms’ fatty tissue background. The primary key to breast density classification is to detect the dense tissues in the mammographic images correctly. Many methods have been proposed for breast density estimation; nevertheless, most of them are not fully automated. Besides, they have been badly affected by low signal-to-noise ratio and variability of density in appearance and texture. This study intends to develop a fully automated and digitalized breast tissue segmentation and classification using advanced deep learning techniques. The conditional Generative Adversarial Networks (cGAN) network is applied to segment the dense tissues in mammograms. To have a complete system for breast density classification, we propose a Convolutional Neural Network (CNN) to classify mammograms based on the standardization of Breast Imaging-Reporting and Data System (BI-RADS). The classification network is fed by the segmented masks of dense tissues generated by the cGAN network. For screening mammography, 410 images of 115 patients from the INbreast dataset were used. The proposed framework can segment the dense regions with an accuracy, Dice coefficient, Jaccard index of 98%, 88%, and 78%, respectively. Furthermore, we obtained precision, sensitivity, and specificity of 97.85%, 97.85%, and 99.28%, respectively, for breast density classification. This study’s findings are promising and show that the proposed deep learning-based techniques can produce a clinically useful computer-aided tool for breast density analysis by digital mammography.

Computer Aided Detection of Clustered Microcalcification: A Survey

BACKGROUND

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.

DISCUSSION

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.

CONCLUSION

The techniques used for segmentation of PM, MC detection and classification in a digitized mammogram are reviewed.

Comparative Study on Local Binary Patterns for Mammographic Density and Risk Scoring

Breast density is considered to be one of the major risk factors in developing breast cancer. High breast density can also affect the accuracy of mammographic abnormality detection due to the breast tissue characteristics and patterns. We reviewed variants of local binary pattern descriptors to classify breast tissue which are widely used as texture descriptors for local feature extraction. In our study, we compared the classification results for the variants of local binary patterns such as classic LBP (Local Binary Pattern), ELBP (Elliptical Local Binary Pattern), Uniform ELBP, LDP (Local Directional Pattern) and M-ELBP (Mean-ELBP). A wider comparison with alternative texture analysis techniques was studied to investigate the potential of LBP variants in density classification. In addition, we investigated the effect on classification when using descriptors for the fibroglandular disk region and the whole breast region. We also studied the effect of the Region-of-Interest (ROI) size and location, the descriptor size, and the choice of classifier. The classification results were evaluated based on the MIAS database using a ten-run ten-fold cross validation approach. The experimental results showed that the Elliptical Local Binary Pattern descriptors and Local Directional Patterns extracted most relevant features for mammographic tissue classification indicating the relevance of directional filters. Similarly, the study showed that classification of features from ROIs of the fibroglandular disk region performed better than classification based on the whole breast region.

Comparative study on fractal analysis of interferometry images with application to tear film surface quality assessment

The purpose of this research was to evaluate the applicability of the fractal dimension (FD) estimators to assess lateral shearing interferometric (LSI) measurements of tear film surface quality. Retrospective recordings of tear film measured with LSI were used: 69 from healthy subjects and 41 from patients diagnosed with dry eye syndrome. Five surface quality descriptors were considered, four based on FD and a previously reported descriptor operating in a spatial frequency domain (M₂), presenting temporal kinetics of post-blink tear film. A set of 12 regression parameters has been extracted and analyzed for classification purposes. The classifiers are assessed in terms of receiver operating characteristics and areas under their curves (AUC). Also, the computational loads are estimated. The maximum AUC of 82.4% was achieved for M₂, closely followed by the binary box-counting (BBC) FD estimator with AUC=78.6%. For all descriptors, statistically significant differences between the subject groups were found (p<0.05). The BBC FD estimator was characterized with the highest empirical computational efficiency that was about 30% faster than that of M₂, while that based on the differential box-counting exhibited the lowest efficiency (4.5 times slower than the best one). Concluding, FD estimators can be utilized for quantitative assessment of tear film kinetics. They provide a viable alternative to previously used spectral counter parameters, and at the same time allow higher computational efficiency.

Radiomics based detection and characterization of suspicious lesions on full field digital mammograms

BACKGROUND AND OBJECTIVE

Early detection is the important key to reduce breast cancer mortality rate. Detecting the mammographic abnormality as a subtle sign of breast cancer is essential for the proper diagnosis and treatment. The aim of this preliminary study is to develop algorithms which detect suspicious lesions and characterize them to reduce the diagnostic errors regarding false positives and false negatives.

METHODS

The proposed hybrid mechanism detects suspicious lesions automatically using connected component labeling and adaptive fuzzy region growing algorithm. A novel neighboring pixel selection algorithm reduces the computational complexity of the seeded region growing algorithm used to finalize lesion contours. These lesions are characterized using radiomic features and then classified as benign mass or malignant tumor using k-NN and SVM classifiers. Two datasets of 460 full field digital mammograms (FFDM) utilized in this clinical study consists of 210 images with malignant tumors, 30 with benign masses and 220 normal breast images that are validated by radiologists expert in mammography.

RESULTS

The qualitative assessment of segmentation results by the expert radiologists shows 91.67% sensitivity and 58.33% specificity. The effects of seven geometric and 48 textural features on classification accuracy, false positives per image (FPsI), sensitivity and specificity are studied separately and together. The features together achieved the sensitivity of 84.44% and 85.56%, specificity of 91.11% and 91.67% with FPsI of 0.54 and 0.55 using k-NN and SVM classifiers respectively on local dataset.

CONCLUSIONS

The overall breast cancer detection performance of proposed scheme after combining geometric and textural features with both classifiers is improved in terms of sensitivity, specificity, and FPsI.

Detection of mass regions in mammograms by bilateral analysis adapted to breast density using similarity indexes and convolutional neural networks

BACKGROUND AND OBJECTIVE

The processing of medical image is an important tool to assist in minimizing the degree of uncertainty of the specialist, while providing specialists with an additional source of detect and diagnosis information. Breast cancer is the most common type of cancer that affects the female population around the world. It is also the most deadly type of cancer among women. It is the second most common type of cancer among all others. The most common examination to diagnose breast cancer early is mammography. In the last decades, computational techniques have been developed with the purpose of automatically detecting structures that maybe associated with tumors in mammography examination. This work presents a computational methodology to automatically detection of mass regions in mammography by using a convolutional neural network.

METHODS

The materials used in this work is the DDSM database. The method proposed consists of two phases: training phase and test phase. The training phase has 2 main steps: (1) create a model to classify breast tissue into dense and non-dense (2) create a model to classify regions of breast into mass and non-mass. The test phase has 7 step: (1) preprocessing; (2) registration; (3) segmentation; (4) first reduction of false positives; (5) preprocessing of regions segmented; (6) density tissue classification (7) second reduction of false positives where regions will be classified into mass and non-mass.

RESULTS

The proposed method achieved 95.6% of accuracy in classify non-dense breasts tissue and 97,72% accuracy in classify dense breasts. To detect regions of mass in non-dense breast, the method achieved a sensitivity value of 91.5%, and specificity value of 90.7%, with 91% accuracy. To detect regions in dense breasts, our method achieved 90.4% of sensitivity and 96.4% of specificity, with accuracy of 94.8%.

CONCLUSIONS

According to the results achieved by CNN, we demonstrate the feasibility of using convolutional neural networks on medical image processing techniques for classification of breast tissue and mass detection.

A hierarchical classifier based on human blood plasma fluorescence for non-invasive colorectal cancer screening

Colorectal cancer (CRC) a leading cause of death by cancer, and screening programs for its early identification are at the heart of the increasing survival rates. To motivate population participation, non-invasive, accurate, scalable and cost-effective diagnosis methods are required. Blood fluorescence spectroscopy provides rich information that can be used for cancer identification. The main challenges in analyzing blood fluorescence data for CRC classification are related to its high dimensionality and inherent variability, especially when analyzing a small number of samples. In this paper, we present a hierarchical classification method based on plasma fluorescence to identify not only CRC, but also adenomas and other non-malignant colorectal findings that may require further medical investigation. A feature selection algorithm is proposed to deal with the high dimensionality and select discriminant fluorescence wavelengths. These are used to train a binary support vector machine (SVM) in the first level to identify the CRC samples. The remaining samples are then presented to a one-class SVM trained on healthy subjects to detect deviant samples, and thus non-malignant findings. This hierarchical design, together with the one class-SVM, aims to reduce the effects of small samples and high variability. Using a dataset analyzed in previous studies comprised of 12,341 wavelengths, we achieved much superior results. Sensitivity and specificity are 0.87 and 0.95 for CRC detection, and 0.60 and 0.79 for non-malignant findings, respectively. Compared to related work, the proposed method presented a better accuracy, required fewer features, and provides a unified approach that expands CRC detection to non-malignant findings.

Fully automated breast boundary and pectoral muscle segmentation in mammograms

Breast and pectoral muscle segmentation is an essential pre-processing step for the subsequent processes in computer aided diagnosis (CAD) systems. Estimating the breast and pectoral boundaries is a difficult task especially in mammograms due to artifacts, homogeneity between the pectoral and breast regions, and low contrast along the skin-air boundary. In this paper, a breast boundary and pectoral muscle segmentation method in mammograms is proposed. For breast boundary estimation, we determine the initial breast boundary via thresholding and employ Active Contour Models without edges to search for the actual boundary. A post-processing technique is proposed to correct the overestimated boundary caused by artifacts. The pectoral muscle boundary is estimated using Canny edge detection and a pre-processing technique is proposed to remove noisy edges. Subsequently, we identify five edge features to find the edge that has the highest probability of being the initial pectoral contour and search for the actual boundary via contour growing. The segmentation results for the proposed method are compared with manual segmentations using 322, 208 and 100mammograms from the Mammographic Image Analysis Society (MIAS), INBreast and Breast Cancer Digital Repository (BCDR) databases, respectively. Experimental results show that the breast boundary and pectoral muscle estimation methods achieved dice similarity coefficients of 98.8% and 97.8% (MIAS), 98.9% and 89.6% (INBreast) and 99.2% and 91.9% (BCDR), respectively.

Towards localization of malignant sites of asymmetry across bilateral mammograms

BACKGROUND AND OBJECTIVES

The analysis of patterns of asymmetry between the left and right mammograms of a patient can provide meaningful insights into the presence of an underlying tumor in its early stage. However, the identification of breast cancer by investigating bilateral asymmetry is difficult to perform due to the indistinct and borderline nature of the asymmetric signs as they appear on mammograms.

METHODS

In this study, to increase the positive-predictive value of asymmetry in mammographic screening, a novel computerized approach for the automatic localization of malignant sites of asymmetry in mammograms is proposed. The sites of anatomical correspondence between the right and left regions of each radiographic projection were extracted by means of two bilateral masking procedures, inspired by radiologists' criteria in interpreting mammograms and based on the use of detected landmarking structures. Relative variations of spatial patterns of intensity values and of orientations of directional components within each site were quantified by combining multidirectional Gabor filters and indices of structural similarity. The localization of the sites of malignant asymmetry was performed by coupling two quadratic discriminant analysis classifiers, one for each masking procedure, that assigned the likelihood of malignancy to each site of correspondence.

RESULTS

The performance of the proposed method was assessed on 94 mammographic images from two publicly available databases and containing at least one asymmetric site. Sensitivity, specificity and balanced accuracy levels of 0.83 (0.09), 0.75 (0.06), and 0.79 (0.04), respectively were obtained in the classification of malignant asymmetric sites vs benign/normal sites using cross-validation. In addition, a further blind test on a dataset of Full Field Digital Mammograms achieved levels of sensitivity, specificity, and balanced accuracy of 0.86, 0.65, and 0.75, respectively.

CONCLUSIONS

The achieved performance indicates that the proposed system is effective in localizing sites of malignant asymmetry and it is expected to improve computer-aided diagnosis of breast cancer.

A Review on Automatic Mammographic Density and Parenchymal Segmentation

Breast cancer is the most frequently diagnosed cancer in women. However, the exact cause(s) of breast cancer still remains unknown. Early detection, precise identification of women at risk, and application of appropriate disease prevention measures are by far the most effective way to tackle breast cancer. There are more than 70 common genetic susceptibility factors included in the current non-image-based risk prediction models (e.g., the Gail and the Tyrer-Cuzick models). Image-based risk factors, such as mammographic densities and parenchymal patterns, have been established as biomarkers but have not been fully incorporated in the risk prediction models used for risk stratification in screening and/or measuring responsiveness to preventive approaches. Within computer aided mammography, automatic mammographic tissue segmentation methods have been developed for estimation of breast tissue composition to facilitate mammographic risk assessment. This paper presents a comprehensive review of automatic mammographic tissue segmentation methodologies developed over the past two decades and the evidence for risk assessment/density classification using segmentation. The aim of this review is to analyse how engineering advances have progressed and the impact automatic mammographic tissue segmentation has in a clinical environment, as well as to understand the current research gaps with respect to the incorporation of image-based risk factors in non-image-based risk prediction models.

A new approach to develop computer-aided detection schemes of digital mammograms

The purpose of this study is to develop a new global mammographic image feature analysis based computer-aided detection (CAD) scheme and evaluate its performance in detecting positive screening mammography examinations. A dataset that includes images acquired from 1896 full-field digital mammography (FFDM) screening examinations was used in this study. Among them, 812 cases were positive for cancer and 1084 were negative or benign. After segmenting the breast area, a computerized scheme was applied to compute 92 global mammographic tissue density based features on each of four mammograms of the craniocaudal (CC) and mediolateral oblique (MLO) views. After adding three existing popular risk factors (woman's age, subjectively rated mammographic density, and family breast cancer history) into the initial feature pool, we applied a sequential forward floating selection feature selection algorithm to select relevant features from the bilateral CC and MLO view images separately. The selected CC and MLO view image features were used to train two artificial neural networks (ANNs). The results were then fused by a third ANN to build a two-stage classifier to predict the likelihood of the FFDM screening examination being positive. CAD performance was tested using a ten-fold cross-validation method. The computed area under the receiver operating characteristic curve was AUC = 0.779   ±   0.025 and the odds ratio monotonically increased from 1 to 31.55 as CAD-generated detection scores increased. The study demonstrated that this new global image feature based CAD scheme had a relatively higher discriminatory power to cue the FFDM examinations with high risk of being positive, which may provide a new CAD-cueing method to assist radiologists in reading and interpreting screening mammograms.

Analysis of structural similarity in mammograms for detection of bilateral asymmetry

We hypothesize that quantification of structural similarity or dissimilarity between paired mammographic regions can be effective in detecting asymmetric signs of breast cancer. Bilateral masking procedures are applied for this purpose by using automatically detected anatomical landmarks. Changes in structural information of the extracted regions are investigated using spherical semivariogram descriptors and correlation-based structural similarity indices in the spatial and complex wavelet domains. The spatial distribution of grayscale values as well as of the magnitude and phase responses of multidirectional Gabor filters are used to represent the structure of mammographic density and of the directional components of breast tissue patterns, respectively. A total of 188 mammograms from the DDSM and mini-MIAS databases, consisting of 47 asymmetric cases and 47 normal cases, were analyzed. For the combined dataset of mammograms, areas under the receiver operating characteristic curves of 0.83, 0.77, and 0.87 were obtained, respectively, with linear discriminant analysis, the Bayesian classifier, and an artificial neural network with radial basis functions, using the features selected by stepwise logistic regression and leave-one-patient-out cross-validation. Two-view analysis provided accuracy up to 0.94, with sensitivity and specificity of 1 and 0.88, respectively.

Reduction of false-positive recalls using a computerized mammographic image feature analysis scheme

The high false-positive recall rate is one of the major dilemmas that significantly reduce the efficacy of screening mammography, which harms a large fraction of women and increases healthcare cost. This study aims to investigate the feasibility of helping reduce false-positive recalls by developing a new computer-aided diagnosis (CAD) scheme based on the analysis of global mammographic texture and density features computed from four-view images. Our database includes full-field digital mammography (FFDM) images acquired from 1052 recalled women (669 positive for cancer and 383 benign). Each case has four images: two craniocaudal (CC) and two mediolateral oblique (MLO) views. Our CAD scheme first computed global texture features related to the mammographic density distribution on the segmented breast regions of four images. Second, the computed features were given to two artificial neural network (ANN) classifiers that were separately trained and tested in a ten-fold cross-validation scheme on CC and MLO view images, respectively. Finally, two ANN classification scores were combined using a new adaptive scoring fusion method that automatically determined the optimal weights to assign to both views. CAD performance was tested using the area under a receiver operating characteristic curve (AUC). The AUC = 0.793  ±  0.026 was obtained for this four-view CAD scheme, which was significantly higher at the 5% significance level than the AUCs achieved when using only CC (p = 0.025) or MLO (p = 0.0004) view images, respectively. This study demonstrates that a quantitative assessment of global mammographic image texture and density features could provide useful and/or supplementary information to classify between malignant and benign cases among the recalled cases, which may eventually help reduce the false-positive recall rate in screening mammography.

Automatic detection of the nipple in screen-film and full-field digital mammograms using a novel Hessian-based method

Automatic detection of the nipple in mammograms is an important step in computerized systems that combine multiview information for accurate detection and diagnosis of breast cancer. Locating the nipple is a difficult task owing to variations in image quality, presence of noise, and distortion and displacement of the breast tissue due to compression. In this work, we propose a novel Hessian-based method to locate automatically the nipple in screen-film and full-field digital mammograms (FFDMs). The method includes detection of a plausible nipple/retroareolar area in a mammogram using geometrical constraints, analysis of the gradient vector field by mean and Gaussian curvature measurements, and local shape-based conditions. The proposed procedure was tested on 566 mammographic images consisting of 372 randomly selected scanned films from two public databases (mini-MIAS and DDSM), and 194 digital mammograms acquired with a GE Senographe 2000D FFDM system. A radiologist independently marked the centers of the nipples for evaluation of the results. The average error obtained was 6.7 mm (22 pixels) with reference to the center of the nipple as identified by the radiologist. Only two out of the 566 detected nipples (0.35 %) had an error larger than 50 mm. The method was also directly compared with two other techniques for the detection of the nipple. The results indicate that the proposed method outperforms other algorithms presented in the literature and can be used to identify accurately the nipple on various types of mammographic images.

A heuristic approach to automated nipple detection in digital mammograms

In this paper, a heuristic approach to automated nipple detection in digital mammograms is presented. A multithresholding algorithm is first applied to segment the mammogram and separate the breast region from the background region. Next, the problem is considered separately for craniocaudal (CC) and mediolateral-oblique (MLO) views. In the simplified algorithm, a search is performed on the segmented image along a band around the centroid and in a direction perpendicular to the pectoral muscle edge in the MLO view image. The direction defaults to the horizontal (perpendicular to the thoracic wall) in case of CC view images. The farthest pixel from the base found in this direction can be approximated as the nipple point. Further, an improved version of the simplified algorithm is proposed which can be considered as a subclass of the Branch and Bound algorithms. The mean Euclidean distance between the ground truth and calculated nipple position for 500 mammograms from the Digital Database for Screening Mammography (DDSM) database was found to be 11.03 mm and the average total time taken by the algorithm was 0.79 s. Results of the proposed algorithm demonstrate that even simple heuristics can achieve the desired result in nipple detection thus reducing the time and computational complexity.

Breast density classification to reduce false positives in CADe systems

This paper describes a novel weighted voting tree classification scheme for breast density classification. Breast parenchymal density is an important risk factor in breast cancer. Moreover, it is known that mammogram interpretation is more difficult when dense tissue is involved. Therefore, automated breast density classification may aid in breast lesion detection and analysis. Several classification methods have been compared and a novel hierarchical classification procedure of combined classifiers with linear discriminant analysis (LDA) is proposed as the best solution to classify the mammograms into the four BIRADS tissue classes. The classification scheme is based on 298 texture features. Statistical analysis to test the normality and homoscedasticity of the data was carried out for feature selection. Thus, only features that are influenced by the tissue type were considered. The novel classification techniques have been incorporated into a CADe system to drive the detection algorithms and tested with 1459 images. The results obtained on the 322 screen-film mammograms (SFM) of the mini-MIAS dataset show that 99.75% of samples were correctly classified. On the 1137 full-field digital mammograms (FFDM) dataset results show 91.58% agreement. The results of the lesion detection algorithms were obtained from modules integrated within the CADe system developed by the authors and show that using breast tissue classification prior to lesion detection leads to an improvement of the detection results. The tools enhance the detectability of lesions and they are able to distinguish their local attenuation without local tissue density constraints.

Prediction of near-term breast cancer risk based on bilateral mammographic feature asymmetry

RATIONALE AND OBJECTIVES

The objective of this study is to investigate the feasibility of predicting near-term risk of breast cancer development in women after a negative mammography screening examination. It is based on a statistical learning model that combines computerized image features related to bilateral mammographic tissue asymmetry and other clinical factors.

MATERIALS AND METHODS

A database of negative digital mammograms acquired from 994 women was retrospectively collected. In the next sequential screening examination (12 to 36 months later), 283 women were diagnosed positive for cancer, 349 were recalled for additional diagnostic workups and later proved to be benign, and 362 remain negative (not recalled). From an initial pool of 183 features, we applied a Sequential Forward Floating Selection feature selection method to search for effective features. Using 10 selected features, we developed and trained a support vector machine classification model to compute a cancer risk or probability score for each case. The area under the receiver operating characteristic curve and odds ratios (ORs) were used as the two performance assessment indices.

RESULTS

The area under the receiver operating characteristic curve = 0.725 ± 0.018 was obtained for positive and negative/benign case classification. The ORs showed an increasing risk trend with increasing model-generated risk scores (from 1.00 to 12.34, between positive and negative/benign case groups). Regression analysis of ORs also indicated a significant increase trend in slope (P = .006).

CONCLUSIONS

This study demonstrates that the risk scores computed by a new support vector machine model involving bilateral mammographic feature asymmetry have potential to assist the prediction of near-term risk of women for developing breast cancer.

A probabilistic approach for breast boundary extraction in mammograms

The extraction of the breast boundary is crucial to perform further analysis of mammogram. Methods to extract the breast boundary can be classified into two categories: methods based on image processing techniques and those based on models. The former use image transformation techniques such as thresholding, morphological operations, and region growing. In the second category, the boundary is extracted using more advanced techniques, such as the active contour model. The problem with thresholding methods is that it is a hard to automatically find the optimal threshold value by using histogram information. On the other hand, active contour models require defining a starting point close to the actual boundary to be able to successfully extract the boundary. In this paper, we propose a probabilistic approach to address the aforementioned problems. In our approach we use local binary patterns to describe the texture around each pixel. In addition, the smoothness of the boundary is handled by using a new probability model. Experimental results show that the proposed method reaches 38% and 50% improvement with respect to the results obtained by the active contour model and threshold-based methods respectively, and it increases the stability of the boundary extraction process up to 86%.

MULTI-CLUSTER SUPPORT VECTOR MACHINE CLASSIFIER FOR THE CLASSIFICATION OF SUSPICIOUS AREAS IN DIGITAL MAMMOGRAMS

This paper presents a novel technique for the classification of suspicious areas in digital mammograms. The proposed technique is based on clustering of input data into numerous clusters and amalgamating them with a Support Vector Machine (SVM) classifier. The technique is called multi-cluster support vector machine (MCSVM) and is designed to provide a fast converging technique with good generalization abilities leading to an improved classification as a benign or malignant class. The proposed MCSVM technique has been evaluated on data from the Digital Database of Screening Mammography (DDSM) benchmark database. The experimental results showed that the proposed MCSVM classifier achieves better results than standard SVM. A paired t-test and Anova analysis showed that the results are statistically significant.