End-to-End Convolutional Neural Network Framework for Breast Ultrasound Analysis Using Multiple Parametric Images Generated from Radiofrequency Signals

被引:6
作者
Kim, Soohyun [1 ]
Park, Juyoung [2 ]
Yi, Joonhwan [1 ]
Kim, Hyungsuk [2 ]
机构
[1] Kwangwoon Univ, Dept Comp Engn, Seoul 01897, South Korea
[2] Kwangwoon Univ, Dept Elect Engn, Seoul 01897, South Korea
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 10期
基金
新加坡国家研究基金会;
关键词
medical ultrasound imaging; breast ultrasound; deep learning techniques; convolutional neural network; quantitative ultrasound; B-mode image; entropy image; phase image; attenuation image; ATTENUATION MEASUREMENT; SEGMENTATION; DISPERSION; PHASE;
D O I
10.3390/app12104942
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Breast ultrasound (BUS) is an effective clinical modality for diagnosing breast abnormalities in women. Deep-learning techniques based on convolutional neural networks (CNN) have been widely used to analyze BUS images. However, the low quality of B-mode images owing to speckle noise and a lack of training datasets makes BUS analysis challenging in clinical applications. In this study, we proposed an end-to-end CNN framework for BUS analysis using multiple parametric images generated from radiofrequency (RF) signals. The entropy and phase images, which represent the microstructural and anatomical information, respectively, and the traditional B-mode images were used as parametric images in the time domain. In addition, the attenuation image, estimated from the frequency domain using RF signals, was used for the spectral features. Because one set of RF signals from one patient produced multiple images as CNN inputs, the proposed framework overcame the limitation of datasets in a broad sense of data augmentation while providing complementary information to compensate for the low quality of the B-mode images. The experimental results showed that the proposed architecture improved the classification accuracy and recall by 5.5% and 11.6%, respectively, compared with the traditional approach using only B-mode images. The proposed framework can be extended to various other parametric images in both the time and frequency domains using deep neural networks to improve its performance.
引用
收藏
页数:17
相关论文
共 45 条
[1]   Operator dependence of physician-performed whole-breast US: Lesion detection and characterization [J].
Berg, Wendie A. ;
Blume, Jeffrey D. ;
Cormack, Jean B. ;
Mendelson, Ellen B. .
RADIOLOGY, 2006, 241 (02) :355-365
[2]  
Brochu E., 2010, A tutorial on Bayesian optimization of expensive cost functions, DOI DOI 10.48550/ARXIV.1012.2599
[3]   An ultrasound research interface for a clinical system (vol 53, pg 1759, 2006) [J].
Brunke, Shelby S. ;
Insana, Michael F. ;
Dahl, Jeremy J. ;
Hansen, Christian ;
Ashfaq, Mohammad ;
Ermert, Helmut .
IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL, 2007, 54 (01) :198-210
[4]   Breast mass classification in sonography with transfer learning using a deep convolutional neural network and color conversion [J].
Byra, Michel ;
Galperin, Michael ;
Ojeda-Fournier, Haydee ;
Olson, Linda ;
O'Boyle, Mary ;
Comstock, Christopher ;
Andre, Michael .
MEDICAL PHYSICS, 2019, 46 (02) :746-755
[5]   Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors [J].
Chang, RF ;
Wu, WJ ;
Moon, WK ;
Chen, DR .
BREAST CANCER RESEARCH AND TREATMENT, 2005, 89 (02) :179-185
[6]   An Ensemble Model using CNNs on Different Domains for ALASKA2 Image Steganalysis [J].
Chubachi, Kaizaburo .
2020 IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY (WIFS), 2020,
[7]   Quantitative Ultrasound in Cancer Imaging [J].
Feleppa, Ernest J. ;
Mamou, Jonathan ;
Porter, Christopher R. ;
Machi, Junji .
SEMINARS IN ONCOLOGY, 2011, 38 (01) :136-150
[8]   ULTRASONIC SIGNAL-PROCESSING FOR INVIVO ATTENUATION MEASUREMENT - SHORT-TIME FOURIER-ANALYSIS [J].
FINK, M ;
HOTTIER, F ;
CARDOSO, JF .
ULTRASONIC IMAGING, 1983, 5 (02) :117-135
[9]   SPECTRAL CHARACTERIZATION AND ATTENUATION MEASUREMENTS IN ULTRASOUND [J].
FLAX, SW ;
PELC, NJ ;
GLOVER, GH ;
GUTMANN, FD ;
MCLACHLAN, M .
ULTRASONIC IMAGING, 1983, 5 (02) :95-116
[10]  
Ghoshal G., 2013, Quantitative Ultrasound in Soft Tissues