Mammogram Image Classification Research Articles

Computer-aided diagnosis of breast cancer from mammogram images using deep learning algorithms

Even though accurate detection of dangerous malignancies from mammogram images is mostly dependent on radiologists' experience, specialists occasionally differ in their assessments. Computer-aided diagnosis provides a better solution for image diagnosis that can help experts make more reliable decisions. In medical applications for diagnosing cancerous growths from mammogram images, computerized and accurate classification of breast cancer mammogram images is critical. The deep learning approach has been widely applied in medical image processing and has had considerable success in biological image classification. The Convolutional Neural Network (CNN), Inception, and EfficientNet are proposed in this paper. The proposed models attain better performance compared to the conventional CNN. The models are used to automatically classify breast cancer mammogram images from Kaggle into benign and malignant. Simulation results demonstrated that EfficientNet, with an accuracy between 97.13 and 99.27%, and overall accuracy of 98.29%, perform better than the other models in this paper.

Computer-aided Detection and Diagnosis of Cancer Regions in Mammogram Images Using Resource-Efficient CNN Architecture.

The automatic computer-assisted mammogram classification system is important for women patients to detect and diagnose the cancer regions. In this work, the mammogram images are classified into three cases: healthy, benign and cancer, using the proposed Resource Efficient Convolutional Neural Network (RECNN architecture). The proposed mammogram image classification system consists of Data Augmentation (DA) module and Spatial transformation module and CNN architecture with a segmentation module. The DA methods are used to increase the mammogram image count and Spatial Gabor Transform is used as the spatial transformation module for transforming the spatial pixels into spatial-frequency pixels. Then, the proposed RECNN architecture is used to perform the classification of mammogram images into healthy, benign and cancer cases. Further, the cancer mammogram images are diagnosed as either 'Early' or 'Severe' using the proposed RECNN architecture in this work. The proposed MCDS obtains 98.65% SeDR, 98.93% SpDR and 98.84% ADR for benign case mammogram images on DDSM dataset and also obtains 98.84% SeDR, 98.7% SpDR and 98.92% ADR for benign case mammogram images on DDSM dataset. The proposed MCDS obtains 98.94% SeDR, 98.86% SpDR and 98.96% ADR for benign case mammogram images on DDSM dataset and also obtains 98.89% SeDR, 98.88% SpDR and 99.03% ADR for benign case mammogram images on MIAS dataset. This proposed method is tested on the mammogram images from DDSM and MIAS datasets and the experimental results are compared with other similar mammogram classification works in this paper. Based on several performance evaluation measures, the experimental results show that MCDS outperforms the state-of-the-art methods currently used for the diagnosis and detection of mammography cancer.

Breast Cancer Diagnosis Method Based on Cross-Mammogram Four-View Interactive Learning.

Computer-aided diagnosis systems play a crucial role in the diagnosis and early detection of breast cancer. However, most current methods focus primarily on the dual-view analysis of a single breast, thereby neglecting the potentially valuable information between bilateral mammograms. In this paper, we propose a Four-View Correlation and Contrastive Joint Learning Network (FV-Net) for the classification of bilateral mammogram images. Specifically, FV-Net focuses on extracting and matching features across the four views of bilateral mammograms while maximizing both their similarities and dissimilarities. Through the Cross-Mammogram Dual-Pathway Attention Module, feature matching between bilateral mammogram views is achieved, capturing the consistency and complementary features across mammograms and effectively reducing feature misalignment. In the reconstituted feature maps derived from bilateral mammograms, the Bilateral-Mammogram Contrastive Joint Learning module performs associative contrastive learning on positive and negative sample pairs within each local region. This aims to maximize the correlation between similar local features and enhance the differentiation between dissimilar features across the bilateral mammogram representations. Our experimental results on a test set comprising 20% of the combined Mini-DDSM and Vindr-mamo datasets, as well as on the INbreast dataset, show that our model exhibits superior performance in breast cancer classification compared to competing methods.

MAMMOGRAM DETECTION USING MACHINE LEARNING

Mammogram detection plays a critical role in early breast cancer diagnosis, and leveraging machine learning techniques can significantly enhance diagnostic accuracy. This project addresses the classification and segmentation of mammogram images to identify abnormalities. We employed a Convolutional Neural Network (CNN) algorithm for binary classification to categorize mammogram images as either ‘Normal’ or ‘Malignant’. For region-based segmentation of detected abnormalities, we utilized an Attention-based optimized UNET algorithm. The preprocessing phase included resizing, normalization, and shuffling of the dataset to prepare it for training. Due to the large size of comprehensive mask image datasets (166 GB), which are impractical to download or process with standard systems, we used a smaller subset of images for training. Consequently, while the classification model performs with reasonable accuracy, the segmentation results may exhibit limited precision due to the constrained training data. The trained model can be applied to test images, where malignant predictions trigger segmentation of the affected regions using the UNET algorithm. This approach demonstrates the feasibility of integrating CNN and UNET for mammogram analysis, though future work will benefit from access to larger datasets for improved segmentation accuracy.

English

Breast cancer is among the top causes of fatalities related to cancer in females. Radiologists commonly use mammogram images to detect breast tumors in their early stages. However, mammography can produce low-contrast images, making it difficult and time-consuming to segment abnormal regions. Deep convolutional neural networks (CNNs) are commonly used for image evaluations. This study used deep CNN models to develop a computer-aided diagnostic (CAD) system for feature extraction and classification. The proposed approach consists of three phases. In the first phase, a shallow, deep CNN model comprising five convolutional layers, five max-pooling layers, one batch normalization layer, and one dropout layer was developed and used to extract recombined images and novel features. In the second phase, the Inception-v3 model was used for label smoothing and classification due to its multiple filters with different sizes. In the third phase, features were extracted using shallow, deep CNN and Inception-v3 models. The Infallible Euclidean distance-based nonlinear dimensionality reduction approach was used to minimize dimensionality. Finally, the Gini-index-based C4.5 decision tree was used for the binary classification of mammogram images from the Digital Database for Screening Mammography (DDSM) + Curated Breast Imaging Subset of DDSM (CBIS-DDSM) and Mammographic Image Analysis Society (MIAS) datasets. The proposed hybrid shallow, deep CNN and Inception-v3 model achieved 99.52% accuracy, a 96% AUC on the DDSM + CBISDDSM dataset, and an accuracy of 97.53% and an AUC value of 97% on the MIAS dataset. Compared with other cutting-edge CAD systems, the proposed hybrid approach achieved higher accuracy by combining in-depth features across both datasets.

Exploiting Patch Sizes and Resolutions for Multi-Scale Deep Learning in Mammogram Image Classification.

Recent progress in deep learning (DL) has revived the interest on DL-based computer aided detection or diagnosis (CAD) systems for breast cancer screening. Patch-based approaches are one of the main state-of-the-art techniques for 2D mammogram image classification, but they are intrinsically limited by the choice of patch size, as there is no unique patch size that is adapted to all lesion sizes. In addition, the impact of input image resolution on performance is not yet fully understood. In this work, we study the impact of patch size and image resolution on the classifier performance for 2D mammograms. To leverage the advantages of different patch sizes and resolutions, a multi patch-size classifier and a multi-resolution classifier are proposed. These new architectures perform multi-scale classification by combining different patch sizes and input image resolutions. The AUC is increased by 3% on the public CBIS-DDSM dataset and by 5% on an internal dataset. Compared with a baseline single patch size and single resolution classifier, our multi-scale classifier reaches an AUC of 0.809 and 0.722 in each dataset.

A novel machine learning approach on texture analysis for automatic breast microcalcification diagnosis classification of mammogram images.

Screening programs use mammography as a diagnostic tool for the early detection of breast cancer. Mammogram enhancement is used to increase the local contrast of the mammogram so that the lesions are more visible in the advanced image. For accurate diagnosis in the early stage of breast cancer, the appearance of masses and microcalcification on the mammographic image are two important indicators. The objective of this study was to evaluate the feasibility of the automatic separation of images of breast tissue microcalcifications and also to evaluate its accuracy. The research was carried outby using two techniques of image enhancement and highlighting of breast tissue microcalcifications for the desired areas by regional ROI based on fuzzy system and also Gabor filtering method. After determining the clusters of breast tissue microcalcifications, the clusters are classified using the decision tree classification algorithm. Then, for segmentation, samples suspected of microcalcification are highlighted and masked, and in the last stage, tissue characteristics are extracted. Subsequently, with the help of an artificial neural network (ANN), determining the benign and malignant types of segmented ROI clusters was accomplished. The proposed system is trained with a Digital Database for Screening Mammography (DDSM) developed by the University of South Florida, USA, and the simulations are performed under MATLAB software and the results are compared with previous work. The results of this training performed under this work show an accuracy of 93% and an improvement of sensitivity above 95%. The resultindicates that the proposed approach can be applied to ensure breast cancer diagnosis.

Advanced DEEPCNN breast cancer mammogram image detection and classification with butterfly optimisation algorithm

Advanced DEEPCNN breast cancer mammogram image detection and classification with butterfly optimisation algorithm

Advanced DEEPCNN Breast Cancer Mammogram Image Detection and Classification with Butterfly Optimization Algorithm

Advanced DEEPCNN Breast Cancer Mammogram Image Detection and Classification with Butterfly Optimization Algorithm

Early detection of breast cancer in mammograms using the lightweight modification of efficientNet B3

Breast cancer is one of the leading causes of death in women worldwide and early detection is critical to improving survival rates. In this study, we present a modified deep learning method for automatic feature detection for breast mass classification on mammograms. We propose to use EfficientNet, a Convolutional Neural Network (CNN) architecture that requires minimal parameters. The main advantage of EfficientNet is the small number of parameters, which allows efficient and accurate classification of mammogram images. Our experiments show that EfficientNet, with an overall accuracy of 86.5%, has the potential to be the fundamental for a fully automated and effective breast cancer detection system in the future. Our results demonstrate the potential of EfficientNet to improve the accuracy and efficiency of breast cancer detection compared to other approaches.

Hybrid DLDT algorithm based tumor classification of mammogram images

Despite the fact that current classical image classification techniques have been widely used to address real-world problems, these applications are frequently hampered by problems including disappointing results, poor classification accuracy, and constrained adaptability. This method separates the mammography image tumour feature extraction and classification processes. The effective way to improve the accuracy of mammography image tumour classification is to integrate the feature extraction and classification processes using the potent deep learning model. The deep structural advantages of multilayer nonlinear mapping and the tumour representation of well-multidimensional data linear decomposition, however, are fully utilised in this paper, which also introduces the idea of tumour representation based on shape-based feature extraction into the architecture of the deep learning network.

Comparison of GLCM and First Order Feature Extraction Methods for Classification of Mammogram Images

Breast cancer is one of the main causes of death in women and ranks first in cancer cases in Indonesia. Therefore, an early detection and prevention of breast cancer is necessary, one of which is through mammography procedures. A machine learning classifier such as Support Vector Machines (SVM) could be used as an aid to the doctors and radiologist in diagnosing breast cancer from the mammogram images. The aim of this paper is to compare two feature extraction methods used in SVM, namely the Gray Level Co-Occurrence Matrix (GLCM) and first order with two kernels for each method, namely Gaussian and Polynomial. Classification using SVM method is carried out by testing several parameters such as the value of C, gamma, degree and varying the pixel spacing values ​​in GLCM, which usually in previous studies only used the default pixel spacing. The dataset consists of 500 mammogram images containing 250 benign and malignant images, respectively. This study is expected to find out the best method with the highest accuracy between these two texture feature extractions and and able to distinguish between benign and malignant classes correctly. The result achieved that Gray Level Co-Occurrence Matrix (GLCM) feature extraction method with both Gaussian and Polynomial kernel yields the best performance with an accuracy of 89%.

Classification of Mammogram Images by Using SVM and KNN

Breast cancer is a fairly diverse illness that affects a large percentage of women in the west. A mammogram is an X-ray-based evaluation of a woman's breasts to see if she has cancer. One of the earliest prescreening diagnostic procedures for breast cancer is mammography. It is well known that breast cancer recovery rates are significantly increased by early identification. Mammogram analysis is typically delegated to skilled radiologists at medical facilities. Human mistake, however, is always a possibility. Fatigue of the observer can commonly lead to errors, resulting in intraobserver and interobserver variances. The image quality affects the sensitivity of mammographic screening as well. The goal of developing automated techniques for detection and grading of breast cancer images is to reduce various types of variability and standardize diagnostic procedures. The classification of breast cancer images into benign (tumor increasing, but not harmful) and malignant (cannot be managed, it causes death) classes using a two-way classification algorithm is shown in this study. The two-way classification data mining algorithms are utilized because there are not many abnormal mammograms. The first classification algorithm, k-means, divides a given dataset into a predetermined number of clusters. Support Vector Machine (SVM), a second classification algorithm, is used to identify the optimal classification function to separate members of the two classes in the training data

Feature Selection Based on Multi-Filters for Classification of Mammogram Images to Look for Signs of Breast Cancer

The accuracy of classification results on mammogram images has a significant role in breast cancer diagnosis. Therefore, many stages consider finding the model has a high level of accuracy and minimizing the computing load, one of which is the accuracy in using the best feature. This needs to be prioritized considering that mammogram image has many features resulting from the mammogram extraction process. Our research has four stages: feature extraction, feature selection-multi filters, classification, and performance evaluation. Thus, in this research, we propose algorithms that can select the features by utilizing multiple filters simultaneously on the filter model for feature selection of mammogram images based on multi-filters/FSbMF. There are six feature selection algorithms with a filter approach (information gain, rule, relief, correlation, gini index, and chi-square) used in this research. Based on the testing result using 10-fold cross-validation, the features resulting from the FSbMF algorithm have the best performance based on the accuracy, recall, and precision from 72,63%, 70,38%, 75,01% to be 100%. Furthermore, the number of resulting features is the minimum because it results from intersection operation from the feature subsets resulting from the multi-filter.

A Computer Aided Breast Cancer Detection Using Unit-Linking Pulse Coupled Neural Network & Multiphase Level Set Method

Breast cancer is one of the lethal diseases with high mortality rates among women. An early detection and diagnosis of the disease can help increase the survival rate. Distinguishing a normal breast tissue from a cancerous one proves to be ambiguous for a Radiologist. A computer aided system can help a radiologist in better and efficient diagnosis. This paper aims at detection and classification of benign and malignant mammogram images with Unit-linking Pulse Coupled Neural Network combined with Multiphase level set Method. While Unit linking Pulse Coupled Neural Network (PCNN) helps in coarse feature extraction, Multi phase Level Set method helps in extracting minute details and hence, better classification. The proposed method is tested with images from MIAS open-source database. Performance of the proposed method is measured using sensitivity, accuracy, specificity and false positive rate. Experiments show that the proposed method gives satisfactory results when compared to the state-of-art methods. The sensitivity obtained by the proposed method is 95.16%, an accuracy of 96.76%, the False Positive Rate (FPR) is as less as 0.85% and specificity of 97.12%.

Investigating the effectiveness of supplemental breast cancer screening tests considering radiologists’ bias

Breast density is known to increase breast cancer risk and decrease mammography screening sensitivity. Breast density notification laws require physicians to inform women with high breast density of these potential risks. The laws usually require healthcare providers to notify patients of the possibility of using more sensitive supplemental screening tests (i.e., ultrasound and MRI). Since the enactment of the laws, there have been controversial debates over (i) their implementations due to the potential radiologists’ bias in breast density classification of mammogram images and (ii) the necessity of supplemental screenings for all patients with high breast density. In this study, we formulate a finite-horizon, discrete-time partially observable Markov chain to investigate the effectiveness of supplemental screening and the impact of radiologists’ misclassification bias on patients’ outcomes. We consider the conditional probability of eventually detecting breast cancer in early states given that the patient develops breast cancer in her lifetime as the primary and the expected number of supplemental tests as the secondary patient’s outcome. Our results indicate that referring patients to a supplemental test solely based on their breast density may not necessarily improve their health outcomes and other risk factors need to be considered when making such referrals. Additionally, average-skilled radiologists’ performances are shown to be comparable with the performance of a perfect radiologist (i.e., 100% accuracy in breast density classification). However, a significant bias in breast density classification (i.e., consistent upgrading or downgrading of breast density classes) can negatively impact a patient’s health outcomes.

Comprehensive Study for Breast Cancer Using Deep Learning and Traditional Machine Learning

Comprehensive Study for Breast Cancer Using Deep Learning and Traditional Machine Learning

A real use case of semi-supervised learning for mammogram classification in a local clinic of Costa Rica.

The implementation of deep learning-based computer-aided diagnosis systems for the classification of mammogram images can help in improving the accuracy, reliability, and cost of diagnosing patients. However, training a deep learning model requires a considerable amount of labelled images, which can be expensive to obtain as time and effort from clinical practitioners are required. To address this, a number of publicly available datasets have been built with data from different hospitals and clinics, which can be used to pre-train the model. However, using models trained on these datasets for later transfer learning and model fine-tuning with images sampled from a different hospital or clinic might result in lower performance. This is due to the distribution mismatch of the datasets, which include different patient populations and image acquisition protocols. In this work, a real-world scenario is evaluated where a novel target dataset sampled from a private Costa Rican clinic is used, with few labels and heavily imbalanced data. The use of two popular and publicly available datasets (INbreast and CBIS-DDSM) as source data, to train and test the models on the novel target dataset, is evaluated. A common approach to further improve the model’s performance under such small labelled target dataset setting is data augmentation. However, often cheaper unlabelled data is available from the target clinic. Therefore, semi-supervised deep learning, which leverages both labelled and unlabelled data, can be used in such conditions. In this work, we evaluate the semi-supervised deep learning approach known as MixMatch, to take advantage of unlabelled data from the target dataset, for whole mammogram image classification. We compare the usage of semi-supervised learning on its own, and combined with transfer learning (from a source mammogram dataset) with data augmentation, as also against regular supervised learning with transfer learning and data augmentation from source datasets. It is shown that the use of a semi-supervised deep learning combined with transfer learning and data augmentation can provide a meaningful advantage when using scarce labelled observations. Also, we found a strong influence of the source dataset, which suggests a more data-centric approach needed to tackle the challenge of scarcely labelled data. We used several different metrics to assess the performance gain of using semi-supervised learning, when dealing with very imbalanced test datasets (such as the G-mean and the F2-score), as mammogram datasets are often very imbalanced. Graphical Description of the test-bed implemented in this work. Two different source data distributions were used to fine-tune the different models tested in this work. The target dataset is the in-house CR-Chavarria-2020 dataset.Supplementary informationThe online version contains supplementary material available at 10.1007/s11517-021-02497-6.

Ensemble Boosted Tree based Mammogram image classification using Texture features and extracted smart features of Deep Neural Network


 
 
 
 
 This work proposes a technique of breast cancer detection from mammogram images. It is a multistage process which classifies the mammogram images into benign or malignant category. During preprocessing, images of Mammographic Image Analysis Society (MIAS) database are passed through a couple of filters for noise removal, thresholding and cropping techniques to extract the region of interest, followed by augmentation process on database to enhance its size. Features from Deep Convolution Neural Network (DCNN) are merged with texture features to form final feature vector. Using transfer learning, deep features are extracted from a modified DCNN, whose training is performed on 69% of randomly selected images of database from both categories. Features of Grey Level Co-Occurrence Matrix (GLCM) and Local Binary Pattern (LBP) are merged to form texture features. Mean and variance of four parameters (contrast, correlation, homogeneity and entropy) of GLCM are computed in four angular directions, at ten distances. Ensemble Boosted Tree classifier using five-fold cross-validation mode, achieved an accuracy, sensitivity, specificity of 98.8%, 100% and 92.55% respectively on this feature vector.
 
 
 

A new automated segmentation and classification of mammogram images

A new automated segmentation and classification of mammogram images