Benign and malignant classification of mammogram images based on deep learning

Li, Hua; Zhuang, Shasha; Li, Dengao; Zhao, Jumin; Ma, Yanyun

doi:10.1016/j.bspc.2019.02.017

Cited by 156 publications

(83 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They trained the network using patches and whole mammograms, and used the DDSM database for pre-training. Li et al [42] proposed a DenseNet-II model for benign and malignant classification of whole mammograms. They added an Inception structure in front of the DenseNet model to extract the multi-scale features.…”

Section: Plos Onementioning

confidence: 99%

New convolutional neural network model for screening and diagnosis of mammograms

et al. 2020

Self Cite

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: Plos Onementioning

confidence: 99%

New convolutional neural network model for screening and diagnosis of mammograms

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Disease diagnosis tests based on deep learning models are also widely used. [26] LiHua et al The DenseNet neural network model was proposed to classify benign and malignant mammography images, improve the DenseNet neural network model, and invent a new DenseNet-II neural network model. [27]Xu Yiwen, Wen Ni et al To predict clinical outcomes by analyzing time-series CT images of patients with locally advanced non-small cell lung cancer (NSCLC), a deep learning prediction of lung cancer treatment response to a series of medical images was proposed.…”

Section: Research On Cancer Based On Machine Learningmentioning

confidence: 99%

An intelligent decision-making support system for the detection and staging of prostate cancer in developing countries

Zhang

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

Background Most developing countries face great problems in the medical, and the threat posed by large populations, scarce medical resources and inadequate medical personnel will affect the development and stability of the society. Therefore, for most developing countries, the development of intelligent medical systems can greatly alleviate the social contradictions arising from this problem. Intelligent Medical System is a system to assist doctors to make decisions. Through effective input, the system makes corresponding decisions and provides doctors with corresponding auxiliary diagnosis and relevant treatment plans. Methods The experimental team collected and compiled about 2,156,528 data items based on the hospitalization information of more than 8,000 prostate patients in three hospitals of Xiangya. The ratio of experimental data to test data was about 7: 3. Combining prostate cancer images and physical indicators to assist diagnosis and make decisions, from the extraction of corresponding image feature data to the final diagnosis decision, a new intelligent system for prostate cancer data decision-making based on Perceptron neural network is proposed. In the comprehensive decision-making, the final decision is made by using the rule-reasoning model. Through data collection, medical data analysis and integration, image processing and analysis, and disease detection and decision-making processes, patients are assisted in diagnosis and treatment to solve the problems and social contradictions facing most developing countries. Results Through the study of hospitalization information of more than 8,000 prostate patients in three hospitals, about 2,156,528 data items were collected and compiled for experiment purposes. Experimental data shows that when the patient base increases from 200 to 8,000, the accuracy of the machine-assisted diagnostic system will increase from 61% to 87%, and the doctor's diagnosis rate will be reduced to 81%. Conclusions From the study, it is concluded that when the patient base reaches a certain number, the diagnostic accuracy of the machine-assisted diagnosis system will exceed the doctor's expertise. So the smart medical system can help doctors and Medical experts make suggest more effective treatments.

show abstract

“…Since we use the whole image as input to our CNN model and to avoid producing unrealistic images, we avoid rotating images in the data augmentation as used in the literature [9][10][11][12]17].…”

Section: Augmented Databasementioning

confidence: 99%

“…Li et al [9], proposed an improved DenseNet neural network model by replacing the first convolutional layer with the Inception structure. They experiment their model on a set of images counting a 2042 case (i.e.…”

Section: Introductionmentioning

confidence: 99%

A New Triplet Convolutional Neural Network for Classification of Lesions on Mammograms

Medjeded¹,

Mahmoudi²,

Chenine³

et al. 2019

RIA

View full text Add to dashboard Cite

Mammography provides a useful tool for breast cancer detection. However, many doctors have difficulty in making the right decision based on mammograms. This paper aims to set up a deep learning (DL) architecture that can effectively differentiate between benign and malignant tumors. Specifically, a new triplet convolutional neural network (CNN) was established with three subnetworks, each of which contains a succession of layer blocks. Each block consists of two convolutional layers, a dropout layer and a max-pooling layer. During operation, the region of interest (ROI) extracted from the mammogram is imputed to the first subnetwork, and processed by the Canny filter. The filtered results become the input of the second subnetwork, while the third subnetwork takes the whole image as input. To verify the effectiveness of our architecture, a set of 500 images from 301 patients was extracted from the DDSM database and augmented to 4,000 images, and divided into a training set (80 %) and a testing set (20 %). The results show that our architecture achieved an accuracy of 93.13 %, a sensitivity of 96 % and a specificity of 90.25 %. This research provides a desirable way to identify breast cancer based on mammography.

show abstract

Benign and malignant classification of mammogram images based on deep learning

Cited by 156 publications

References 16 publications

New convolutional neural network model for screening and diagnosis of mammograms

New convolutional neural network model for screening and diagnosis of mammograms

An intelligent decision-making support system for the detection and staging of prostate cancer in developing countries

A New Triplet Convolutional Neural Network for Classification of Lesions on Mammograms

Contact Info

Product

Resources

About