Deep feature–based automatic classification of mammograms

Arora, Ridhi; Kumar, P. Naresh; Raman, Balasubramanian

doi:10.1007/s11517-020-02150-8

Cited by 68 publications

(43 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first stage is to divide the images into normal and abnormal, the second stage is to divide the abnormal images into mass and calcification, and the third stage is to divide the lesions into benign and malignant. Arora et al [ 24 ] built an integrated neural network model to divide image patches into benign and malignant. The model integrated five popular neural network models, and connected the features extracted from these five networks through the fully connected layer, and output the final classification result.…”

Section: Introductionmentioning

confidence: 99%

New convolutional neural network model for screening and diagnosis of mammograms

et al. 2020

View full text Add to dashboard Cite

Breast cancer is the most common cancer in women and poses a great threat to women's life and health. Mammography is an effective method for the diagnosis of breast cancer, but the results are largely limited by the clinical experience of radiologists. Therefore, the main purpose of this study is to perform two-stage classification (Normal/Abnormal and Benign/ Malignancy) of two-view mammograms through convolutional neural network. In this study, we constructed a multi-view feature fusion network model for classification of mammograms from two views, and we proposed a multi-scale attention DenseNet as the backbone network for feature extraction. The model consists of two independent branches, which are used to extract the features of two mammograms from different views. Our work mainly focuses on the construction of multi-scale convolution module and attention module. The final experimental results show that the model has achieved good performance in both classification tasks. We used the DDSM database to evaluate the proposed method. The accuracy, sensitivity and AUC values of normal and abnormal mammograms classification were 94.92%, 96.52% and 94.72%, respectively. And the accuracy, sensitivity and AUC values of benign and malignant mammograms classification were 95.24%, 96.11% and 95.03%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

New convolutional neural network model for screening and diagnosis of mammograms

et al. 2020

View full text Add to dashboard Cite

show abstract

“…They named their experiment that used the frozen layers 0 fine-tuning strategy, which follows the definition of feature extraction in some other sources term [49]. On the other hand, R.Arora et al [141] did not perform re-training the architecture of their network as they believed they would face an overfitting problem.…”

Section: E Discussionmentioning

confidence: 99%

“…One of the most notable works that used ensemble learning rather than classifying the dataset was the study conducted by R.Arora et al [141] in 2020. After applying some visualization improvement techniques (image-guided filters and HE), the authors employed several models such as VGG-16, AlexNet, GoogleNet, InceptionResNet-v2, and ResNet-18 as the sub-architectures of their model.…”

Section: Ensemble Learning Reviewed Applicationsmentioning

confidence: 99%

Design Guidelines for Mammogram-Based Computer-Aided Systems Using Deep Learning Techniques

Azour

Boukerche

2022

IEEE Access

View full text Add to dashboard Cite

Breast cancer is the second fatal disease among cancers patients both in Canada and across the globe. However, when detected early, a patients' survival rate can be raised. Thus, researchers and scientists have been practicing to develop Computer-Aided Detection (CADe) and Computer-Aided Diagnosis (CADx) systems. Traditional CAD systems depend on manual feature extraction, which has provided radiologists with poor detection and diagnosis tools. Nevertheless, recently, the powerful application of Convolutional Neural Networks (CNN)s as one of the deep learning-based methods has revolutionized these systems' accuracy and development. This article proposes categorizing the current deep learning research on mammogram types based on researchers' techniques for their empirical studies. Also, we provide an overview of different publicly available data resources and available datasets for breast imaging. This critical review of the state-of-the-art techniques is presented, which we believe can serve as a valuable source for research scientists investigating deep learning-based breast mammogram classification.

show abstract

“…The class of an unknown pattern is predicted by passing it to each learner and fusing their predictions. This approach results in better classification performance than using a single classifier [ 21 , 22 , 23 , 24 , 25 , 26 ]. However, to adopt this approach for deep learning-based classifiers is very expensive from the point of view of computational and storage space complexity because to train many CNN models and store them is very expensive.…”

Section: Proposed Methodsmentioning

confidence: 99%

Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network

et al. 2021

View full text Add to dashboard Cite

Masses are one of the early signs of breast cancer, and the survival rate of women suffering from breast cancer can be improved if masses can be correctly identified as benign or malignant. However, their classification is challenging due to the similarity in texture patterns of both types of mass. The existing methods for this problem have low sensitivity and specificity. Based on the hypothesis that diverse contextual information of a mass region forms a strong indicator for discriminating benign and malignant masses and the idea of the ensemble classifier, we introduce a computer-aided system for this problem. The system uses multiple regions of interest (ROIs) encompassing a mass region for modeling diverse contextual information, a single ResNet-50 model (or its density-specific modification) as a backbone for local decisions, and stacking with SVM as a base model to predict the final decision. A data augmentation technique is introduced for fine-tuning the backbone model. The system was thoroughly evaluated on the benchmark CBIS-DDSM dataset using its provided data split protocol, and it achieved a sensitivity of 98.48% and a specificity of 92.31%. Furthermore, it was found that the system gives higher performance if it is trained and tested using the data from a specific breast density BI-RADS class. The system does not need to fine-tune/train multiple CNN models; it introduces diverse contextual information by multiple ROIs. The comparison shows that the method outperforms the state-of-the-art methods for classifying mass regions into benign and malignant. It will help radiologists reduce their burden and enhance their sensitivity in the prediction of malignant masses.

show abstract

Deep feature–based automatic classification of mammograms

Cited by 68 publications

References 38 publications

New convolutional neural network model for screening and diagnosis of mammograms

New convolutional neural network model for screening and diagnosis of mammograms

Design Guidelines for Mammogram-Based Computer-Aided Systems Using Deep Learning Techniques

Breast Mass Classification Using Diverse Contextual Information and Convolutional Neural Network

Contact Info

Product

Resources

About