Classification Of Mammographic Images Research Articles

Deep Location Soft-Embedding-Based Network With Regional Scoring for Mammogram Classification.

Early detection and treatment of breast cancer can significantly reduce patient mortality, and mammogram is an effective method for early screening. Computer-aided diagnosis (CAD) of mammography based on deep learning can assist radiologists in making more objective and accurate judgments. However, existing methods often depend on datasets with manual segmentation annotations. In addition, due to the large image sizes and small lesion proportions, many methods that do not use region of interest (ROI) mostly rely on multi-scale and multi-feature fusion models. These shortcomings increase the labor, money, and computational overhead of applying the model. Therefore, a deep location soft-embedding-based network with regional scoring (DLSEN-RS) is proposed. DLSEN-RS is an end-to-end mammography image classification method containing only one feature extractor and relies on positional embedding (PE) and aggregation pooling (AP) modules to locate lesion areas without bounding boxes, transfer learning, or multi-stage training. In particular, the introduced PE and AP modules exhibit versatility across various CNN models and improve the model's tumor localization and diagnostic accuracy for mammography images. Experiments are conducted on published INbreast and CBIS-DDSM datasets, and compared to previous state-of-the-art mammographic image classification methods, DLSEN-RS performed satisfactorily.

BI-RADS categories and breast lesions classification of mammographic images using artificial intelligence diagnostic model

According to BI-RADS criteria, radiologists evaluate mammography images, and breast lesions are classified as malignant or benign. In this retrospective study, an evaluation was made on 264 mammogram images of 139 patients. First, data augmentation was applied, and then the total number of images was increased to 565. Two computer-aided models were then designed to classify breast lesions and BI-RADS categories. The first of these models is the support vector machine (SVM) based model, and the second is the convolutional neural network (CNN) based model. The SVM-based model could classify BI-RADS categories and malignant-benign discrimination with an accuracy rate of 86.42% and 92.59%, respectively. On the other hand, the CNN-based model showed 79.01% and 83.95% accuracy for BI-RADS categories and malignant benign discrimination, respectively. These results showed that a well-designed machine learning-based classification model can give better results than a deep learning model. Additionally, it can be used as a secondary system for radiologists to differentiate breast lesions and BI-RADS lesion categories.

Employing Atrous Pyramid Convolutional Deep Learning Approach for Detection to Diagnose Breast Cancer Tumors.

Breast cancer is among the most common diseases and one of the most common causes of death in the female population worldwide. Early identification of breast cancer improves survival. Therefore, radiologists will be able to make more accurate diagnoses if a computerized system is developed to detect breast cancer. Computer-aided design techniques have the potential to help medical professionals to determine the specific location of breast tumors and better manage this disease more rapidly and accurately. MIAS datasets were used in this study. The aim of this study is to evaluate a noise reduction for mammographic pictures and to identify salt and pepper, Gaussian, and Poisson so that precise mass detection operations can be estimated. As a result, it provides a method for noise reduction known as quantum wavelet transform (QWT) filtering and an image morphology operator for precise mass segmentation in mammographic images by utilizing an Atrous pyramid convolutional neural network as the deep learning model for classification of mammographic images. The hybrid methodology dubbed QWT-APCNN is compared to earlier methods in terms of peak signal-to-noise ratio (PSNR) and mean square error (MSE) in noise reduction and detection accuracy for mass area recognition. Compared to state-of-the-art approaches, the proposed method performed better at noise reduction and segmentation according to different evaluation criteria such as an accuracy rate of 98.57%, 92% sensitivity, 88% specificity, 90% DSS, and ROC and AUC rate of 88.77.

Deep ensemble transfer learning-based framework for mammographic image classification

Deep ensemble transfer learning-based framework for mammographic image classification

Two‐view attention‐guided convolutional neural network for mammographic image classification

AbstractDeep learning has been widely used in the field of mammographic image classification owing to its superiority in automatic feature extraction. However, general deep learning models cannot achieve very satisfactory classification results on mammographic images because these models are not specifically designed for mammographic images and do not take the specific traits of these images into account. To exploit the essential discriminant information of mammographic images, we propose a novel classification method based on a convolutional neural network. Specifically, the proposed method designs two branches to extract the discriminative features from mammographic images from the mediolateral oblique and craniocaudal (CC) mammographic views. The features extracted from the two‐view mammographic images contain complementary information that enables breast cancer to be more easily distinguished. Moreover, the attention block is introduced to capture the channel‐wise information by adjusting the weight of each feature map, which is beneficial to emphasising the important features of mammographic images. Furthermore, we add a penalty term based on the fuzzy cluster algorithm to the cross‐entropy function, which improves the generalisation ability of the classification model by maximising the interclass distance and minimising the intraclass distance of the samples. The experimental results on The Digital database for Screening Mammography INbreast and MIAS mammography databases illustrate that the proposed method achieves the best classification performance and is more robust than the compared state‐of‐the‐art classification methods.

Feature fusion and Ensemble learning-based CNN model for mammographic image classification

In recent times, the world has faced an alarming situation regarding breast cancer patients. The early diagnosis of this deadly disease can make the treatment more accessible and practical. In this regard, a Computer-Aided Diagnosis (CAD) system can assist the radiologists in distinguishing the normal and abnormal tissues and diagnosing the pathological stages. The classification task is challenging in CAD systems because of noisy and low contrast mammogram images, tumors' shape and location variations, and the high resemblance between the normal and tumor regions of interest (ROI). We propose a novel deep convolution neural network (DCNN) approach based on feature fusion and ensemble learning strategies to improve the detection and classification of abnormalities in mammographic scans. The feature fusion helps to detect discriminative features between the classes properly, while ensemble learning in the last block better classify the normal and tumor ROIs to get more authenticated results. Moreover, the role of spatial dropout and depthwise separable convolution is investigated for mammogram classification to better deal with overfitting and small dataset problems in medical images. The proposed model is evaluated on two publicly available datasets, MIAS and BCDR, getting high sensitivity, specificity, and accuracy of 0.995, 0.994, and 0.994, respectively, on the MIAS dataset.

WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification.

The early detection and timely treatment of breast cancer can save lives. Mammography is one of the most efficient approaches to screening early breast cancer. An automatic mammographic image classification method could improve the work efficiency of radiologists. Current deep learning-based methods typically use the traditional softmax loss to optimize the feature extraction part, which aims to learn the features of mammographic images. However, previous studies have shown that the feature extraction part cannot learn discriminative features from complex data using the standard softmax loss. In this paper, we design a new architecture and propose respective loss functions. Specifically, we develop a double-classifier network architecture that constrains the extracted features' distribution by changing the classifiers' decision boundaries. Then, we propose the double-classifier constraint loss function to constrain the decision boundaries so that the feature extraction part can learn discriminative features. Furthermore, by taking advantage of the architecture of two classifiers, the neural network can detect the difficult-to-classify samples. We propose a weighted double-classifier constraint method to make the feature extract part pay more attention to learning difficult-to-classify samples' features. Our proposed method can be easily applied to an existing convolutional neural network to improve mammographic image classification performance. We conducted extensive experiments to evaluate our methods on three public benchmark mammographic image datasets. The results showed that our methods outperformed many other similar methods and state-of-the-art methods on the three public medical benchmarks. Our code and weights can be found on GitHub.

Cognitive Computing-Based Mammographic Image Classification on an Internet of Medical

Recently, the Internet of Medical Things (IoMT) has become a research hotspot due to its various applicability in medical field. However, the data analysis and management in IoMT remain challenging owing to the existence of a massive number of devices linked to the server environment, generating a massive quantity of healthcare data. In such cases, cognitive computing can be employed that uses many intelligent technologies–machine learning (ML), deep learning (DL), artificial intelligence (AI), natural language processing (NLP) and others–to comprehend data expansively. Furthermore, breast cancer (BC) has been found to be a major cause of mortality among ladies globally. Earlier detection and classification of BC using digital mammograms can decrease the mortality rate. This paper presents a novel deep learning-enabled multi-objective mayfly optimization algorithm (DL-MOMFO) for BC diagnosis and classification in the IoMT environment. The goal of this paper is to integrate deep learning (DL) and cognitive computing-based techniques for e-healthcare applications as a part of IoMT technology to detect and classify BC. The proposed DL-MOMFO algorithm involved Adaptive Weighted Mean Filter (AWMF)-based noise removal and contrast-limited adaptive histogram equalisation (CLAHE)-based contrast improvement techniques to improve the quality of the digital mammograms. In addition, a U-Net architecture-based segmentation method was utilised to detect diseased regions in the mammograms. Moreover, a SqueezeNet-based feature extraction and a fuzzy support vector machine (FSVM) classifier were used in the presented technique. To enhance the diagnostic performance of the presented method, the MOMFO algorithm was used to effectively tune the parameters of the SqueezeNet and FSVM techniques. The DL-MOMFO technique was tested on the MIAS database, and the experimental outcomes revealed that the DL-MOMFO technique outperformed existing techniques.

Intelligent system for processing and analysis of mammograms

The article discusses the possibilities for the development of automated processing of mammographic images based on the principles of a systematic approach. A structural diagram of an intelligent system for processing and analyzing mammographic images is proposed, which contains three main modules: a module for forming cascading windows, a module for combining cascading windows, and a module for classification and decision making. The software was developed in MATLAB 2018b environment. The possibilities of functioning of each module are considered. Experimental testing of the software of the intelligent system for the classification of breast radiographs according to the classes “no area of interest” or “area of interest” was carried out. A criterion for evaluating the results of classification of mammographic images is selected. Experiments on control samples showed diagnostic efficiency for the classes of radiographs “no region of interest” - “region of interest” not less than 90%.

Mammographic Image Classification Using Deep Neural Network for Computer-Aided Diagnosis

Breast cancer detection is a crucial topic in the healthcare sector. Breast cancer is a major reason for the increased mortality rate in recent years among women, specifically in developed and underdeveloped countries around the world. The incidence rate is less in India than in developed countries, but awareness must be increased. This paper focuses on an efficient deep learning-based diagnosis and classification technique to detect breast cancer from mammograms. The model includes preprocessing, segmentation, feature extraction, and classification. At the initial level, Laplacian filtering is applied to identify the portions of edges in mammogram images that are highly sensitive to noise. Subsequently, segmentation is done using modified adaptively regularized kernel-based fuzzy C means (ARKFCM). Feature extraction is accomplished using the morphological, texture, and moment invariants. The corresponding feature values are provided as inputs to a deep neural network (DNN) model that classifies the normal and abnormal portions in the mammogram images. The performance of the proposed model is validated with the Mammographic Image Analysis Society (MIAS) database. The efficiency of the proposed classifier is experimentally proved by comparing the various classifiers with respect to their statistical performances. On an applied database, the proposed model offered a maximum classification with the highest accuracy level of 99.13%.

Local Features Based Deep Learning for Mammographic Image Classification: In Comparison to CNN Models

Abstract Convolutional neural networks (CNN) have achieved tremendous success in tackling various tasks of computer vision problems such as classification of images and recognition of objects. The general trend has been to make networks larger and more complex in order to achieve higher precision. In any case, these advances to improve precision are not really making the systems increasingly effective for size and speed. In this report, an attempt to overcome the aforementioned issues is described. Some well-known scale and rotation invariant local features such as SIFT, SURF, ORB, BRISK, and KAZE were first observed to check which of these having the strong potentiality to replace inclusively the convolutional layers of CNN models. To do this, while retaining the fully connected layers of the corresponding CNN model as the classifier, the convolutional parts of the model were inclusively taken out and assigned the high-level feature maps at the flatten layer with scale and rotation invariant local features. The computational experiments were carried out using the challenging mammographic images provided by MIAS (mammographic image analysis society). It contains 322 grayscale images from 2 different severity, each of which has 1024x1024 pixels. Employing only the fully connected layers of the VGG16 model as the classifier, it is found that SIFT and SURF based features offer much better training and testing accuracies compared to ORB, BRISK, and KAZE in classifying MIAS image datasets. Using SIFT and SURF local features and employing only VGG16 or MobileNetV2 fully connected layers as a classifier, it can be shown that SIFT and SURF based deep learning exhibit state-of-the-art performance on MIAS datasets. SIFT and SURF based deep learning are capable of outperforming the performance of the original VGG16 and MobileNetV2 configuration in terms of accuracy and training time needed on the same datasets.

Mammographic Classification Using Stacked Ensemble Learning with Bagging and Boosting Techniques

The classification of mammographic images is an important process in Computer-aided diagnosis (CADx) system for an automatic detection of breast cancer. CADx helps radiologists in providing a second opinion for an accurate diagnosis. Therefore, an intelligent classifier is required in classifying suspicious areas in digital mammograms. A number of breast cancer classification techniques have been proposed over years, however, these techniques suffered from limitations that impact its performance. This paper aims to investigate an approach using stacked ensemble method that can reduce total classification error by reducing the variance and integrating the outputs of several classifiers to obtain a better classification performance. The proposed stacked ensemble classifier uses three algorithms Classical Soft Independent Modelling by Class Analogy (CSimca), Generalized Linear Model (GLM), Gaussian Process with Radial Basis Function Kernel (gaussprRadial) at the bottom layer and Stochastic Gradient Boosting (GBM) at the top layer. It is observed that the ensemble approach performs better than all the other single classifiers across the experiments that has achieved an overall classification accuracy of 85%, with sensitivity 86.67%, precision 83.87% and specificity 83.33% in the testing stage. The stacked ensemble learning classification techniques can be widely used in CADx that have proved their efficiency in mammogram classification.

Mammographic image classification with deep fusion learning

To better address the recognition of abnormalities among mammographic images, in this study we apply the deep fusion learning approach based on Pre-trained models to discover the discriminative patterns between Normal and Tumor categories. We designed a deep fusion learning framework for mammographic image classification. This framework works in two main steps. After obtaining the regions of interest (ROIs) from original dataset, the first step is to train our proposed deep fusion models on those ROI patches which are randomly collected from all ROIs. We proposed the deep fusion model (Model1) to directly fuse the deep features to classify the Normal and Tumor ROI patches. To explore the association among channels of the same block, we propose another deep fusion model (Model2) to integrate the cross-channel deep features using 1 × 1 convolution. The second step is to obtain the final prediction by performing the majority voting on all patches' prediction of one ROI. The experimental results show that Model1 achieves the whole accuracy of 0.8906, recall rate of 0.913, and precision rate of 0.8077 for Tumor class. Accordingly, Model2 achieves the whole accuracy of 0.875, recall rate of 0.9565, and precision rate 0.7,586 for Tumor class. Finally, we open source our Python code at https://github.com/yxchspring/MIAS in order to share our tool with the research community.

Deep Neural Networks With Region-Based Pooling Structures for Mammographic Image Classification.

Breast cancer is one of the most frequently diagnosed solid cancers. Mammography is the most commonly used screening technology for detecting breast cancer. Traditional machine learning methods of mammographic image classification or segmentation using manual features require a great quantity of manual segmentation annotation data to train the model and test the results. But manual labeling is expensive, time-consuming, and laborious, and greatly increases the cost of system construction. To reduce this cost and the workload of radiologists, an end-to-end full-image mammogram classification method based on deep neural networks was proposed for classifier building, which can be constructed without bounding boxes or mask ground truth label of training data. The only label required in this method is the classification of mammographic images, which can be relatively easy to collect from diagnostic reports. Because breast lesions usually take up a fraction of the total area visualized in the mammographic image, we propose different pooling structures for convolutional neural networks(CNNs) instead of the common pooling methods, which divide the image into regions and select the few with high probability of malignancy as the representation of the whole mammographic image. The proposed pooling structures can be applied on most CNN-based models, which may greatly improve the models' performance on mammographic image data with the same input. Experimental results on the publicly available INbreast dataset and CBIS dataset indicate that the proposed pooling structures perform satisfactorily on mammographic image data compared with previous state-of-the-art mammographic image classifiers and detection algorithm using segmentation annotations.

Interpretable mammographic mass classification with fuzzy interpolative reasoning

Breast mass cancer remains a great challenge for developing advanced computer-aided diagnosis (CADx) systems, to assist medical professionals for the determination of benignancy or malignancy of masses. This paper presents a novel approach to building fuzzy rule-based CADx systems for mass classification of mammographic images, via the use of weighted fuzzy rule interpolation. It describes an integrated implementation of such a classification system that ensures interpretable classification of masses through firing the rules that match given observations, while having the capability of classifying unmatched observations through fuzzy rule interpolation (FRI). In particular, a feature weight-guided FRI scheme is exploited to enable such inference. The work is implemented through integrating feature weights with a popular scale and move transformation-based FRI, with the individual feature weights derived from feature selection as a preprocessing process. The efficacy of the proposed CADx system is systematically evaluated using two real-world mammographic image datasets, demonstrating its explicit interpretability and potential classification performance.

Automated Classification of Malignant and Benign Breast Cancer Lesions Using Neural Networks on Digitized Mammograms.

We propose a novel neural network approach for the classification of abnormal mammographic images into benign or malignant based on their texture representations. The proposed framework has the capability of mapping high dimensional feature space into a lower-dimension, in a supervised way. The main contribution of the proposed classifier is to introduce a new neuron structure for map representation and adopt a supervised learning technique for feature classification. This is achieved by making the weight updating procedure dependent on the class reliability of the neuron. We showed high accuracy (95.2%) for our proposed approach in the classification of abnormal real mammographic images when compared to other related methods.

Multi-View Convolutional Neural Networks for Mammographic Image Classification

In recent years, deep learning has been widely applied for mammographic image classification. However, most of the existing methods are based on a single mammography view and cannot sufficiently extract discriminative features, thereby resulting in an unsatisfactory classification accuracy. To solve this problem and improve the mammographic image classification performance, we propose a novel multi-view convolutional neural network (CNN) based on multiple mammography views in this paper. Considering that the images acquired from different perspectives contain different and complementary breast mass information, we modify the CNN architecture to exploit the complementary information from the various views of mammography. The new architecture can extract discriminative features from the mediolateral oblique (MLO) and craniocaudal (CC) views of the mammographic images and can effectively incorporate these features for mammographic images. The dilated convolutional layers enable the feature maps extracted from the multiple breast mass views to capture information from a large “field of vision”. Moreover, multi-scale features are obtained by using the convolutional and dilated convolutions. In addition, we incorporate a penalty term into the cross entropy loss function, which enables the model evolution to reduce the misclassification rate by enhancing the contributions of the samples misclassified in the training process. The proposed method was evaluated and compared with several state-of-the-art methods on the open Digital Database for Screening Mammography (DDSM) and Mammographic Image Analysis Society (MIAS) datasets. The experimental results show that the proposed method exhibits a better performance than those of the state-of-the-art methods.

A highly efficient system for Mammographic Image Classification Using NSVC Algorithm

Nowadays, classification is the most efficient method for breast cancer detection using mammography images. During the last two decades, researchers achieved very good results using different kinds of classification methods. In this context, we will focus in this work on the quality of mammography image classification by proposing a new approach that us compares with the state-of-art methods. Our method consists of two phases; a semi-supervised step based on SKDA and a second step based on SVM. As will be shown in the experiments section, results on Mammography data set show that the proposed algorithm can get very good results. The application of our algorithm on five well known real data sets allow us to validate our method and show its interest in the context of image based medical diagnosis. The best precision obtained by NSVC exceeded 99 %.

Convolutional neural network improvement for breast cancer classification

Traditionally, physicians need to manually delineate the suspected breast cancer area. Numerous studies have mentioned that manual segmentation takes time, and depends on the machine and the operator. The algorithm called Convolutional Neural Network Improvement for Breast Cancer Classification (CNNI-BCC) is presented to assist medical experts in breast cancer diagnosis in timely manner. The CNNI-BCC uses a convolutional neural network that improves the breast cancer lesion classification in order to help experts for breast cancer diagnosis. CNNI-BCC can classify incoming breast cancer medical images into malignant, benign, and healthy patients. The application of present algorithm can assist in classification of mammographic medical images into benign patient, malignant patient and healthy patient without prior information of the presence of a cancerous lesion. The presented method aims to help medical experts for the classification of breast cancer lesion through the implementation of convolutional neural network for the classification of breast cancer. CNNI-BCC can categorize incoming medical images as malignant, benign or normal patient with sensitivity, accuracy, area under the receiver operating characteristic curve (AUC) and specificity of 89.47%, 90.50%, 0.901 ± 0.0314 and 90.71% respectively.

Mammographic Image Classification System via Active Learning

Training an accurate prediction model for mammographic image classification is usually necessary to require a large number of labeled images. However, the manually acquiring rich and reliable annotations is known to be tedious and time-consuming process, especially for medical image. The advances in machine learning yielded a branch of technique, termed active learning (AL), which has been proposed for solving the problem of the limited training samples and expensive labeling cost, and has resulted in highly successful applications in many pattern recognition tasks such as image processing and speech recognition. In this article, a comparison is provided among the mammographic image classification systems, relying on traditional supervised learning, un-supervised learning and AL, aiming to obtain a system with low labeling cost. The experiments based on digital database for screening mammography demonstrate that the AL is able to minimize the labeling cost of mammographic image without sacrificing the accuracy of final classification system. In addition, some specific characteristics of mammographic image: file information and spatial feature, which are not available to the traditional AL methods, have been found to further decrease the labeling cost. In conclusion, we suggest that the AL is a reasonable alternative to supervised learning for the researchers in the field of medical image classification with limited experimental conditions.