Digital breast tomosynthesis denoising using deep convolutional neural network: effects of dose level of training target images

2021 ◽  
Author(s):  
Mingjie Gao ◽  
Jeffrey A. Fessler ◽  
Heang-Ping Chan
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Dose Level ◽  
Network Effects ◽  
Digital Breast Tomosynthesis ◽  
Deep Convolutional Neural Network ◽  
Breast Tomosynthesis ◽  
Level Of Training

scholarly journals Mass detection in digital breast tomosynthesis: Deep convolutional neural network with transfer learning from mammography

2016 ◽  
Vol 43 (12) ◽  
pp. 6654-6666 ◽  
Author(s):  
Ravi K. Samala ◽  
Heang-Ping Chan ◽  
Lubomir Hadjiiski ◽  
Mark A. Helvie ◽  
Jun Wei ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Digital Breast Tomosynthesis ◽  
Deep Convolutional Neural Network ◽  
Mass Detection ◽  
Breast Tomosynthesis

scholarly journals Comparison Between Feature-Based and Convolutional Neural Network–Based Computer-Aided Diagnosis for Breast Cancer Classification in Digital Breast Tomosynthesis

2019 ◽  
pp. 1-18
Author(s):  
Siwa Chan ◽  
Jinn-Yi Yeh
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Convolutional Neural Network ◽  
Digital Breast Tomosynthesis ◽  
Cancer Classification ◽  
Breast Tomosynthesis ◽  
Breast Cancer Classification ◽  
Computer Aided ◽  
Feature Based ◽  
Aided Diagnosis

Digital breast tomosynthesis (DBT) is a promising new technique for breast cancer diagnosis. DBT has the potential to overcome the tissue superimposition problems that occur on traditional mammograms for tumor detection. However, DBT generates numerous images, thereby creating a heavy workload for radiologists. Therefore, constructing an automatic computer-aided diagnosis (CAD) system for DBT image analysis is necessary. This study compared feature-based CAD and convolutional neural network (CNN)-based CAD for breast cancer classification from DBT images. The research methods included image preprocessing, candidate tumor identification, three-dimensional feature generation, classification, image cropping, augmentation, CNN model design, and deep learning. The precision rates (standard deviation) of the LeNet-based CNN CAD and the feature-based CAD for breast cancer classification were 89.84 (0.013) and 84.46 (0.082), respectively. The T value was -4.091 and the P value was 0.00 < 0.05, which indicate that the LeNet-based CNN CAD significantly outperform the feature-based CAD. However, there is no significantly differences between the LeNet-based CNN CAD and the feature-based CAD on other criteria. The results can be applied to clinical medicine and assist radiologists in breast cancer identification.

Sign in / Sign up

Export Citation Format

Share Document