Masses In Mammograms Research Articles

Mass detection in mammograms by bilateral analysis using convolution neural network

Background and objectiveAutomatic detection of the masses in mammograms is a big challenge and plays a crucial role to assist radiologists for accurate diagnosis. In this paper, a bilateral image analysis method based on Convolution Neural Network (CNN) is developed for mass detection in mammograms. MethodsThe proposed bilateral mass detection method consists of two networks: a registration network for registering bilateral mammograms and a Siamese-Faster-RCNN network for mass detection using a pair of registered mammograms. In the first step, self-supervised learning network is built to learn the spatial transformation between bilateral mammograms. This network can directly estimate spatial transformation by maximizing an image-wise similarity metric and corresponding points labeling is not needed. In the second step, an end-to-end network combining the Region Proposal Network (RPN) and a Siamese Fully Connected (Siamese-FC) network is designed. Different from existing methods, the designed network integrates mass detection on single image with registered bilateral images comparison. ResultsThe proposed method is evaluated on three datasets (publicly available dataset INbreast and private dataset BCPKUPH and TXMD). For INbreast dataset, the proposed method achieves 0.88 true positive rate (TPR) with 1.12 false positives per image (FPs/I). For BCPKUPH dataset, the proposed method achieves 0.85 TPR with 1.86 FPs/I. For TXMD dataset, the proposed method achieves 0.85 TPR with 2.70 FPs/I. ConclusionsRegistration experimental result shows that the proposed method is suitable for bilateral mass detection. Mass detection experimental results show that the proposed method performs better than unilateral mass detection method, different bilateral connection schemes and image level fusion bilateral schemes.

A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms.

Mammography remains the most prevalent imaging tool for early breast cancer screening. The language used to describe abnormalities in mammographic reports is based on the Breast Imaging Reporting and Data System (BI-RADS). Assigning a correct BI-RADS category to each examined mammogram is a strenuous and challenging task for even experts. This paper proposes a new and effective computer-aided diagnosis (CAD) system to classify mammographic masses into four assessment categories in BI-RADS. The mass regions are first enhanced by means of histogram equalization and then semiautomatically segmented based on the region growing technique. A total of 130 handcrafted BI-RADS features are then extracted from the shape, margin, and density of each mass, together with the mass size and the patient's age, as mentioned in BI-RADS mammography. Then, a modified feature selection method based on the genetic algorithm (GA) is proposed to select the most clinically significant BI-RADS features. Finally, a back-propagation neural network (BPN) is employed for classification, and its accuracy is used as the fitness in GA. A set of 500 mammogram images from the digital database for screening mammography (DDSM) is used for evaluation. Our system achieves classification accuracy, positive predictive value, negative predictive value, and Matthews correlation coefficient of 84.5%, 84.4%, 94.8%, and 79.3%, respectively. To our best knowledge, this is the best current result for BI-RADS classification of breast masses in mammography, which makes the proposed system promising to support radiologists for deciding proper patient management based on the automatically assigned BI-RADS categories.

Deep learning for mass detection in Full Field Digital Mammograms

In recent years, the use of Convolutional Neural Networks (CNNs) in medical imaging has shown improved performance in terms of mass detection and classification compared to current state-of-the-art methods. This paper proposes a fully automated framework to detect masses in Full-Field Digital Mammograms (FFDM). This is based on the Faster Region-based Convolutional Neural Network (Faster-RCNN) model and is applied for detecting masses in the large-scale OPTIMAM Mammography Image Database (OMI-DB), which consists of ∼80,000 FFDMs mainly from Hologic and General Electric (GE) scanners. This research is the first to benchmark the performance of deep learning on OMI-DB. The proposed framework obtained a True Positive Rate (TPR) of 0.93 at 0.78 False Positive per Image (FPI) on FFDMs from the Hologic scanner. Transfer learning is then used in the Faster R-CNN model trained on Hologic images to detect masses in smaller databases containing FFDMs from the GE scanner and another public dataset INbreast (Siemens scanner). The detection framework obtained a TPR of 0.91±0.06 at 1.69 FPI for images from the GE scanner and also showed higher performance compared to state-of-the-art methods on the INbreast dataset, obtaining a TPR of 0.99±0.03 at 1.17 FPI for malignant and 0.85±0.08 at 1.0 FPI for benign masses, showing the potential to be used as part of an advanced CAD system for breast cancer screening.

Towards an approach using grammars for automatic classification of masses in mammograms

AbstractApproximately 15% of all cancer deaths among women worldwide is due to breast cancer. Mammography is one of the most useful methods for the early detection of this disease. Over the last decade, several papers were published reporting the usage of different computer‐aided diagnosis systems using pattern recognition techniques as a second opinion to obtain a more accurate diagnosis. However, the theory of formal languages has not been explored in this field. In this context, the main contribution of this study is to present the usage of a new syntactic approach that is able to classify breast masses found in mammograms as benign or malignant. The experimental tests were performed using a dataset that contains 111 images from different sources. The grammar‐based classifiers achieved accuracy values ranging from 89% to 100% depending on the features and the model employed. Furthermore, to achieve a feature dimension reduction, a feature selection technique based on the Gini importance of each feature was employed. Additionally, we compared the obtained results with the grammar‐based classifiers to the more traditional classifiers used in this research area, such as artificial neural networks, support vector machines, k‐nearest neighbors, and random forest. The best result achieved by the grammar‐based classifiers was approximately 10% higher, in terms of accuracy, than the best results produced by the traditional classifiers, showing the strength of this grammatical approach.

Detection of partially overlapped masses in mammograms

<span>Breast cancer remains one of the major causes of cancer deaths among women. For decades, screening mammography has been one of the most common methods for early cancer detection and diagnosis. Digital mammography images are created by applying a small burst of x-rays that pass through the breast to a solid-state detector, which transmits the electronic signals to a computer to form a digital image. However, due to projection, some mass areas may be partially covered, which makes them difficult to be interprated. This paper addresses the issue of potential mass regions being distorted by other normal breast tissues, which will negatively affect some of the features being extracted from the mass and in turn deteriorate the classification accuracy. The goal was to estimate the overlapped parts of the mass border using Euclidean distance in order to give more accurate results in next stages. The presented method achieved 95.744% region sensitivity at 0.333 False Positive per Image (FPI), outperforming other researches in this branch of mammography analysis.</span>

Mammographic mass segmentation using multichannel and multiscale fully convolutional networks

AbstractBreast cancer is one of the leading causes of death among women worldwide. Mammographic mass segmentation is an important task in mammogram analysis. This process, however, poses a prominent challenge considering that masses can be obscured in images and appear with irregular shapes and low image contrast. In this study, a multichannel, multiscale fully convolutional network is proposed and evaluated for mass segmentation in mammograms. To reduce the impact of surrounding unrelated structures, preprocessed images with a salient mass appearance are obtained as the second input channel of the network. Furthermore, to jointly conduct fine boundary delineation and global mass localization, we incorporate more crucial context information by learning multiscale features from different resolution levels. The performance of our segmentation approach is compared with that of several traditional and deep‐learning‐based methods on the popular DDSM and INbreast datasets. The evaluation indices consist of the Dice similarity coefficient, area overlap measure, area undersegmentation measure, area oversegmentation measure, and Hausdorff distance. The mean values of the Dice similarity coefficient and Hausdorff distance of our proposed segmentation method are 0.915 ± 0.031 and 6.257 ± 3.380, respectively, on DDSM and 0.918 ± 0.038 and 2.572 ± 0.956, respectively, on INbreast, which are superior to those of the existing methods. The experimental results verify that our proposed multichannel, multiscale fully convolutional network can reliably segment masses in mammograms.

An evaluation and ranking of evolutionary algorithms in segmenting abnormal masses in digital mammograms

Breast cancer is the most common cancer in women worldwide and the second main cause of cancer mortality after lung cancer. Up to now, there still no prevention nor early symptoms of breast cancer. Early detection can decrease significantly the mortality rate as the disease can be treated at an early stage. X-Ray is the current screening method that helps in detecting the most two common abnormalities of the breast, masses and micro-calcifications. However, interpreting mammograms is challenging in dense breasts as the abnormal masses and the normal glandular tissue of the breast have similar characteristics. Recently, the evolutionary algorithms have been widely used in image segmentation. In this paper, we evaluate and compare the performance of six most used evolutionary algorithms, invasive weed optimization (IWO), genetic algorithm (GA), particle swarm optimization (PSO), electromagnetism-like optimization (EMO), ant colony optimization (ACO), and artificial bee colony (ABC) in terms of clustering abnormal masses in the breast, particularly dense and extremely dense breasts. This evaluation is conducted based on quantitative metrics including Cohen’s Kappa, correlation, and false positive and false negative rates. The evolutionary algorithms are then ranked based on two multi-criteria decision analysis methods, the Preference Ranking Organization Method for the Enrichment of Evaluations (PROMETHEE) and the Graphical Analysis for Interactive Aid (GAIA).

AUNet: attention-guided dense-upsampling networks for breast mass segmentation in whole mammograms

Mammography is one of the most commonly applied tools for early breast cancer screening. Automatic segmentation of breast masses in mammograms is essential but challenging due to the low signal-to-noise ratio and the wide variety of mass shapes and sizes. Existing methods deal with these challenges mainly by extracting mass-centered image patches manually or automatically. However, manual patch extraction is time-consuming and automatic patch extraction brings errors that could not be compensated in the following segmentation step. In this study, we propose a novel attention-guided dense-upsampling network (AUNet) for accurate breast mass segmentation in whole mammograms directly. In AUNet, we employ an asymmetrical encoder–decoder structure and propose an effective upsampling block, attention-guided dense-upsampling block (AU block). Especially, the AU block is designed to have three merits. Firstly, it compensates the information loss of bilinear upsampling by dense upsampling. Secondly, it designs a more effective method to fuse high- and low-level features. Thirdly, it includes a channel-attention function to highlight rich-information channels. We evaluated the proposed method on two publicly available datasets, CBIS-DDSM and INbreast. Compared to three state-of-the-art fully convolutional networks, AUNet achieved the best performances with an average Dice similarity coefficient of 81.8% for CBIS-DDSM and 79.1% for INbreast.

Mammographic Classification Based on XGBoost and DCNN With Multi Features

The classification of benign and malignant masses in mammograms by Computer-Aided Diagnosis (CAD) is one of the most difficult and important tasks in the development of CAD systems. This classification has commonly been automated by extracting a set of handcrafted features from mammograms and relating the responses to breast cancer. Recently, the application of Deep Learning (DL) technology in medical imaging informatics has been attracting extensive research interest. However, limited medical image datasets and feature expression often reduce the performance of DL-based schemes. Therefore, this study aims to develop a new combined feature CAD method based on DL for classifying mammographic masses into three classes: normal, benign and cancer (malignant) masses. Three kinds of breast masses were scored by using Deep Convolution Neural Network (DCNN) as a feature extractor. Then the scoring features are combined with the image texture features as input to the classifier. This features including the scoring features, Gray-Level Co-occurrence Matrix (GLCM) and Histogram of Oriented Gradient (HOT) were employed to extract the breast mass information in mammograms and the classifier of Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) were trained for the classification task. Accuracy (ACC), Precision (Pre), Recall (Rec), F1-score (F1), and Overall Accuracy (Overall ACC) are used to evaluate the performance of the proposed system and the results show that the proposed multi-features combination model performs the best results. The performance of the XGBoost classifier has proved to be better in comparison to the SVM classification algorithms. As a result, when XGBoost was used as a classifier, the correct identification rate of the Overall ACC was 92.80% and that of malignant tumors was 84%, with reasonable and best results. These results indicate that the proposed method may help in more accurately diagnosing cases that are difficult to classify on images.

A Novel Multi-Scale Adversarial Networks for Precise Segmentation of X-Ray Breast Mass

With the constant changes of people's lifestyle and living environment, the morbidity of breast cancer is increasing year by year. It is highly imperative to develop an effective breast mass segmentation method for early breast cancer diagnosis. However, segmenting breast masses in mammograms is still one hot issue with enormous challenges because of masses' irregular shapes and various sizes. In this study, we propose multi-adversarial learning to capture multi-scale image information for accurate breast mass segmentation. To effectively reinforce higher-order consistency in the segmentation results, the proposed network introduces the idea of adversarial networks, mainly consisting of a segmentation network and a discrimination network. An improved U-Net is introduced as the segmentation network to generate masks of the suspicious regions, while the discrimination network combines three convolutional critic networks that operate at different scales to discriminate the input masks. To weaken the unbalanced class problem and produce fine-grained segmentation results, weighted cross entropy loss and Earth-Mover distance are jointly used as an integrated loss function to guide the optimization process. Furthermore, the spectral normalization is adopted to the critics to alleviate the instability of training. The effectiveness of the proposed method is evaluated on two public datasets (INbreast and CBIS-DDSM). Experimental results empirically demonstrate that our method outperforms FCNs-based methods and the state-of-the-art method with dice of 81.64% for INbreast and 82.16% for CBIS-DDSM.

Segmentation of Fuzzy Enhanced Mammogram Mass Images by using K-Mean Clustering and Region Growing

Providing intention to encourage radiologist’s appraisal for distinguishing proof or order of mammogram images, different methods were suggested by specialists since past two decades. By means of this technical paper, we propose segmentation on advanced mammogram imaging with k-means clustering and locale developing systems tending to support specialists or radiologists to figure out cancerous areas with computer-aided techniques. The suggested task is further classified within two stages: Applied/implemented pre-processing, at primary stage. With the pre-processing stage, we carried a median filter to expel undesirable salt and pepper clamor. Further, we apply fuzzy intensification operator (INT) to upgrade the distinction of intake images. During subsequent stage, improved fuzzy imaging conduces as input for k-mean clustering. Secondly, the locale developing technique is employed with previously generated clustered imagery to partition mammogram into homogeneous areas indicated through force from pixels. With the end goal of the experiment, we utilized the smaller than normal MAIS dataset. The experiment’s end result shows that proposed strategy accomplishes higher precision.

Imaging & Machine Learning Techniques Used for Early Identification of Cancer in Breast Mammogram

Breast cancer has become a major concern of women health throughout the world and has an important cause of death among women. The important radiographic signs of cancer are the masses visible in the breast. In the initial stage, the masses in the women breast are very strenuous to detect. In many cases, it has been proven that a manual attempt of treatment methods are time consuming and inefficient. Hence there is a basic demand for well-planned methods for diagnosis of the cancerous cells with minimal human participation resulting high in precision. Mammography has been proven as an efficient technique for the identification of cancer in women breast. Automated detection of masses in breast mammogram is the major goal in the identification of cancer in women breast. Machine learning techniques can be used as an effective mechanism by the physician for the early detection of cancer in the breast. By early recognition of malignancy in the breast, patients will get treatment right from the initial stage of cancer which can save their lives.

Visibility improvement and mass segmentation of mammogram images using quantile separated histogram equalisation with local contrast enhancement

In this work, the authors develop a working software-based approach named ‘linearly quantile separated histogram equalisation-grey relational analysis’ for mammogram image (MI). This approach improves overall contrast (local and global) of given MI and segments breast-region with a specific end goal to acquire better visual elucidation, examination, and grouping of mammogram masses to help radiologists in settling on more precise choices. The fundamental commitment of this work is to demonstrate that results of good quality of breast-region segmentation can be accomplished from basic breast-region segmentation if the input image has good contrast and a better interpretation of hidden details. They have evaluated the proposed strategy for MIAS-MIs. Experimental results have shown that the proposed approach works better than state-of-the-art.

Feature extraction based on empirical mode decomposition for automatic mass classification of mammogram images

Breast cancer is one of the major health problems that leads to early mortality in women. To aid the radiologists, computer aided diagnosis provides a second opinion for the detection and classification of breast cancer. In this paper, two texture feature extraction methods using Empirical Mode Decomposition (EMD) have been proposed to classify the masses in mammogram images into benign or malignant. The first feature extraction method is based on Bi-dimensional Empirical Mode Decomposition (BEMD). On performing BEMD on Region of Interest (ROI) of mammogram image, the ROI is decomposed into a set of different frequency components called Bi-dimensional Intrinsic Mode Functions (BIMFs). Gray Level Co-occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRM) features are extracted from these BIMFs and are given as input to the classifier for classification into benign or malignant. Due to the mode mixing problem that exists in BEMD, BIMFs obtained from BEMD are less orthogonal to each other. To overcome this drawback, the second feature extraction method called Modified Bi-dimensional Empirical Mode Decomposition (MBEMD) is proposed. The BIMFs are extracted by employing the proposed MBEMD on mammogram ROI. Features are extracted in a similar way as BEMD method. Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) classifiers are used for the classification of mammogram mass. The classification accuracy of 88.8%, 96.2% and Area Under the Curve (AUC) of Receiver Operating Characteristics (ROC) of 0.9, 0.96 are obtained with SVM classifier for BEMD, proposed MBEMD based features respectively. The results show that the proposed method yields consistent performance when applied across different databases.

Adaptive hysteresis thresholding segmentation technique for localizing the breast masses in the curve stitching domain

Background and objectiveMassive work by distinguished researchers in the domain of breast segmentation has been proposed. However, no significant solution reduces the limitations of the false positive rate of cancerous cells in the breast body for probing the abnormalities of particular features. This problem is challenging in its nature and essential to be solved. It is needed to reach the optimal measurements of the breast parenchyma, the breast patchy regions of the mammogram, or the breast registration for searching of precise oddities. MethodsIn this work, we propose a novel approach for observing the abnormal breast cells identification with high sensitivity. A cancer tumor often produces a specific protein in the blood that serves as a marker for the cancer cells. These cells break off from the cancer and move into the blood stream. However, presence of pectoral muscle in breast mammogram highly affects the detection process of breast tumor. A novel aspect of the proposed method is that the curve stitching technique is developed for removing of pectoral muscle. Following this, an adaptive hysteresis thresholding is used for segmentation. This hybrid technique is used for segmenting a breast region of digital mammogram with suppression of pectoral muscle. ResultsThe proposed method attains a highest sensitivity rate of 96.6% for the MIAS dataset and 96.4% for the DDSM dataset as compared to existing methods. ConclusionThe main idea behind this is to improve the threshold based segmentation techniques to create an adaptive threshold and apposite templates, in order to conserve tumor salient features about suspicious regions to classify benign and malignant mass in mammogram. First, a spline based curve fitting is applied on edges of the breast parenchyma and fill the region with a very low intensity value and map on original image to preserve the original intensity of breast region free of pectoral muscle. The results of the experiments show that the proposed segmentation technique is efficient when tested on MIAS and DDSM dataset.

A wavelet and adaptive threshold-based contrast enhancement of masses in mammograms for visual screening

The screening of mammograms is a difficult task for the radiologist, due to variation in contrast and homogeneous structure of the masses and surrounding breast tissues. Therefore, an adaptive threshold-based contrast enhancement method is proposed in this paper for enhancement of suspicious masses in mammograms. Homomorphic filtering and wavelet-based denosing has been used prior to enhancement in the describe method. The approach contains, artefact suppression using pre-processing. Then wavelet transform is applied on the preprocessed mammogram, homomorphic filter is used to filter the approximate coefficient and wavelet shrinkage operator is applied on detail coefficients for denoising. Finally, contrast enhancement approach is used to enhance the suspicious region based on adaptive threshold technique. Two databases, namely Digital Database for Screening Mammography (DDSM) and Mammographic Image Analysis Society (MIAS), were used to test proposed method. The obtain results using proposed method gives better visibility for suspicious masses for all types of mammograms.

A wavelet and adaptive threshold-based contrast enhancement of masses in mammograms for visual screening

A wavelet and adaptive threshold-based contrast enhancement of masses in mammograms for visual screening

Detection of Masses in Mammograms using Bayesian Method and Machine learning

Every 100th cases in cancer we come across are of breasts cancer cases. It is becoming very common in woman of all ages. Correct detection of these lesions in breast is very important. With less of human intervention, the goal is to do the correct diagnosis. Not all the cases of breast masses are futile. If the cases are not dealt properly, they might create panic amongst people. Human detection without machine intervention is not hundred percent accurate. If machines can be deeply trained, they can do the same work of detection with much more accuracy. Bayesian method has a vast area of application in the field of medical image processing as well as in machine learning. This paper intends to use Bayesian probabilistic in image segmentation as well as in machine learning. Machine learning in image processing means application in pattern recognition. There are various machine learning algorithms that can classify an image at their best. In the proposed system, we will be firstly segment the image using Bayesian method. On the segmented parts of the image, we will be applying machine learning algorithm to diagnose the mass or the growth.

Automatic Detection of Masses in Mammograms Using Bi-Dimensional Empirical Mode Decomposition

Automatic Detection of Masses in Mammograms Using Bi-Dimensional Empirical Mode Decomposition

Mammographic mass classification using filter response patches

Considering the importance of early diagnosis of breast cancer, a supervised patch‐wise texton‐based approach has been developed for the classification of mass abnormalities in mammograms. The proposed method is based on texture‐based classification of masses in mammograms and does not require segmentation of the mass region. In this approach, patches from filter bank responses are utilised for generating the texton dictionary. The methodology is evaluated on the publicly available Digital Database for Screening Mammography database. Using a naive Bayes classifier, a classification accuracy of 83% with an area under the receiver operating characteristic curve of 0.89 was obtained. Experimental results demonstrated that the patch‐wise texton‐based approach in conjunction with the naive Bayes classifier constructs an efficient and alternative approach for automatic mammographic mass classification.