Convolutional Neural Networks for mammogram classification in BIRADS standard: development and preliminary tests
Francesca LizziPaolo BoscoDavide CaramellaCarolina MariniAlessandra ReticoClaudio TrainoM.E. Fantacci
1
Citation
0
Reference
20
Related Paper
Citation Trend
Topics:
Cite
Artificial intelligence plays an important role in the classification of medical images for computerized diagnosis of the disease. The computer-aided medical imaging analysis system is developed for breast tissue density classification in mammogram images. Mammogram density is considered as significant predictive markers for breast cancer detection, treatment and management. Recently, deep learning techniques achieved impressive results in computer-assisted disease diagnosis. The deep learning technique such as the convolution neural network (CNN) is used for automated classification of mammogram density as fatty, dense and glandular. This study investigates how computer-aided medical imaging analysis system provides a reliable classification of mammogram density. The proposed methodology is evaluated using a mini-MIAS (Mammogram Image Analysis Society) database. We obtained an average accuracy of 98.5%. So, the proposed CAD system aids the clinicians in the classification of mammogram density.
Cite
Citations (4)
Limited by various conditions, the features of mammography images are difficult to extract, so it is hard to classify them.The paper proposed a method based on deep learning method to classify benign and malignant mammography images.The convolutional neural network concludes four convolution layers, four pool layers, and two full-connection layers, and a Softmax layer.The paper designed a new network architecture to improve the traditional one.As a result, we have done an experiment on the DDSM database.Compared with other classification methods, it shows that the method proposed in this paper is more effective than other methods.
Cite
Citations (0)
Computer-Aided Diagnosis
Breast tissue
Feature (linguistics)
Cite
Citations (79)
Digital Mammography
Breast tissue
Cite
Citations (4)
The presence of round cystic and solid mass lesions identified at mammogram screenings account for a large number of recalls. These recalls can cause undue patient anxiety and increased healthcare costs. Since cystic masses are nearly always benign, accurate classification of these lesions would be allow a significant reduction in recalls. This classification is very difficult using conventional mammogram screening data, but this study explores the possibility of performing the task on dual-energy full field digital mammography (FFDM) data. Since clinical data of this type is not readily available, realistic simulated data with different sources of variation are used. With this data, a deep convolutional neural network (CNN) was trained and evaluated. It achieved an AUC of 0.980 and 42% specificity at the 99% sensitivity level. These promising results should motivate further development of such imaging systems.
Digital Mammography
Cite
Citations (0)
Breast tissue
Digital Mammography
Mammographic Density
Cite
Citations (1)
Mammogram tissue density has been found to be a strong indicator for breast cancer risk. Efforts in computer vision of breast parenchymal pattern have been made in order to improve the diagnostic accuracy by radiologists. Motivated by recent results in mammogram tissue density classification, a novel methodology for automatic American College of Radiology Breast Imaging Reporting and Data System classification using local binary pattern variance descriptor is presented in this article. The proposed approach characterizes the local density in different types of breast tissue patterns information into the LBP histogram. The performance of macro-calcification detection methods is developed using FARABI database. Performance results are given in terms of receiver operating characteristic. The area under curve of the corresponding approach has been found to be 79%.
Local Binary Patterns
Breast density
Breast tissue
Cite
Citations (20)
Breast cancer is one of the most common cancers among female diseases all over the world.Early diagnosis and treatment is particularly important in reducing the mortality rate.This research is focused on the prevention of breast cancer, therefore it is important to detect micro-calcifications (MCs) which are a sign of early stage breast cancer.Microcalcifications are tiny deposits of calcium which are visible on mammograms as they present as tiny white spots.A computer-aided diagnosis system (CAD) is created with the development of computer technology that way radiologists are aided improving their diagnostics while using CAD as a second reader.We are aiming to classify into BIRADS 2, 3 and 4 which are the stages when the cancer can be prevented and a fourth category called No lesion which are veins and tissue that our high pass Gaussian filter detects.This research focuses on classification using ANN (Artificial Neural Network).Experimenting with the categories to classify into using ANN, the results were the following: into the four mentioned before an overall accuracy of 71% was obtained, then joining categories BIRADS 2 and 3 into one and classifying into 3 categories gave an 80% of accuracy.Joining this two categories was the result of analizing the ROC curve and observation of the ROI images of the MCs as the regions measured are very alike in this two categories and variation is that MCs are more present in BIRADS 3 than in BIRADS 2. Data matrix was reduced using PCA (Principal Component Analysis) but it did not gave better results so it was discarded as the ANN accuracy to classify was reduced to a 69.8%.
Cite
Citations (4)
The Breast Imaging Reporting and Data System (BIRADS) was developed by the American College of Radiologists as a standard of comparison for rating mammograms and breast ultrasound images. It sets up a classification for the Level of Suspicion (LOS) of the possibility of a breast cancer. In this paper we present an automated image analyzing system that finds calcifications based on the standard BIRADS 1 and 2. For our goal, we studied the digital mammography database in DICOM format provided by the Department of Radiology of the Hospital Universitario de Puebla. We used The Difference of Gaussian (DOG) filter to find edges of the forms of the different calcifications and a back-propagation Artificial Neural Network (ANN) for the pattern recognition of the BIRADS 1 and 2 cases. This method allowed us to automate the segmentation of the calcifications with a low computational cost. We achieved the pattern recognition with a high level of sensitivity of 0.9629 and specificity of 0.9920.
DICOM
Breast imaging
Gaussian filter
Cite
Citations (2)