Design and analysis of a robust breast cancer diagnostic system based on multimode MR images
In this paper, we propose a Robust Breast Cancer Diagnostic System (RBCDS) based on multimode Magnetic Resonance (MR) images. Firstly, we design a four-mode convolutional neural network (FMS-PCNN) model to detect whether an image contains a tumor. The features of the images generated by different im...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
AIMS Press
2021-05-01
|
Series: | Mathematical Biosciences and Engineering |
Subjects: | |
Online Access: | http://www.aimspress.com/article/doi/10.3934/mbe.2021180?viewType=HTML |
id |
doaj-91abf18f5f274af098f4271ba8d5a19a |
---|---|
record_format |
Article |
spelling |
doaj-91abf18f5f274af098f4271ba8d5a19a2021-06-02T01:42:00ZengAIMS PressMathematical Biosciences and Engineering1551-00182021-05-011843578359710.3934/mbe.2021180Design and analysis of a robust breast cancer diagnostic system based on multimode MR imagesHong Yu0Wenhuan Lu1Qilong Sun2Haiqiang Shi 3Jianguo Wei4Zhe Wang5Xiaoman Wang6Naixue Xiong71. Center Obstetrics and Gynecology Hospital, Tianjin 300100, China2. College of Intelligence and Computing, Tianjin University, Tianjin 300350, China3. School of Computer Science, Qinghai Nationalities University, Xining Qinghai, 810007, China4. Qinghai Provincial Party School, Xining Qinghai, 810007, China2. College of Intelligence and Computing, Tianjin University, Tianjin 300350, China 3. School of Computer Science, Qinghai Nationalities University, Xining Qinghai, 810007, China5. IBM China Company Limited, Beijing 100193, China2. College of Intelligence and Computing, Tianjin University, Tianjin 300350, China2. College of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaIn this paper, we propose a Robust Breast Cancer Diagnostic System (RBCDS) based on multimode Magnetic Resonance (MR) images. Firstly, we design a four-mode convolutional neural network (FMS-PCNN) model to detect whether an image contains a tumor. The features of the images generated by different imaging modes are extracted and fused to form the basis of classification. This classification model utilizes both spatial pyramid pooling (SPP) and principal components analysis (PCA). SPP enables the network to process images of different sizes and avoids the loss due to image resizing. PCA can remove redundant information in the fused features of multi-sequence images. The best accuracy of this model achieves 94.6%. After that, we use our optimized U-Net (SU-Net) to segment the tumor from the entire image. The SU-Net achieves a mean dice coefficient (DC) value of 0.867. Finally, the performance of the system is analyzed to prove that this system is superior to the existing schemes.http://www.aimspress.com/article/doi/10.3934/mbe.2021180?viewType=HTMLclassificationconvolutional neural networksmagnetic resonance imagingmultiple modessegmentation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hong Yu Wenhuan Lu Qilong Sun Haiqiang Shi Jianguo Wei Zhe Wang Xiaoman Wang Naixue Xiong |
spellingShingle |
Hong Yu Wenhuan Lu Qilong Sun Haiqiang Shi Jianguo Wei Zhe Wang Xiaoman Wang Naixue Xiong Design and analysis of a robust breast cancer diagnostic system based on multimode MR images Mathematical Biosciences and Engineering classification convolutional neural networks magnetic resonance imaging multiple modes segmentation |
author_facet |
Hong Yu Wenhuan Lu Qilong Sun Haiqiang Shi Jianguo Wei Zhe Wang Xiaoman Wang Naixue Xiong |
author_sort |
Hong Yu |
title |
Design and analysis of a robust breast cancer diagnostic system based on multimode MR images |
title_short |
Design and analysis of a robust breast cancer diagnostic system based on multimode MR images |
title_full |
Design and analysis of a robust breast cancer diagnostic system based on multimode MR images |
title_fullStr |
Design and analysis of a robust breast cancer diagnostic system based on multimode MR images |
title_full_unstemmed |
Design and analysis of a robust breast cancer diagnostic system based on multimode MR images |
title_sort |
design and analysis of a robust breast cancer diagnostic system based on multimode mr images |
publisher |
AIMS Press |
series |
Mathematical Biosciences and Engineering |
issn |
1551-0018 |
publishDate |
2021-05-01 |
description |
In this paper, we propose a Robust Breast Cancer Diagnostic System (RBCDS) based on multimode Magnetic Resonance (MR) images. Firstly, we design a four-mode convolutional neural network (FMS-PCNN) model to detect whether an image contains a tumor. The features of the images generated by different imaging modes are extracted and fused to form the basis of classification. This classification model utilizes both spatial pyramid pooling (SPP) and principal components analysis (PCA). SPP enables the network to process images of different sizes and avoids the loss due to image resizing. PCA can remove redundant information in the fused features of multi-sequence images. The best accuracy of this model achieves 94.6%. After that, we use our optimized U-Net (SU-Net) to segment the tumor from the entire image. The SU-Net achieves a mean dice coefficient (DC) value of 0.867. Finally, the performance of the system is analyzed to prove that this system is superior to the existing schemes. |
topic |
classification convolutional neural networks magnetic resonance imaging multiple modes segmentation |
url |
http://www.aimspress.com/article/doi/10.3934/mbe.2021180?viewType=HTML |
work_keys_str_mv |
AT hongyu designandanalysisofarobustbreastcancerdiagnosticsystembasedonmultimodemrimages AT wenhuanlu designandanalysisofarobustbreastcancerdiagnosticsystembasedonmultimodemrimages AT qilongsun designandanalysisofarobustbreastcancerdiagnosticsystembasedonmultimodemrimages AT haiqiangshi designandanalysisofarobustbreastcancerdiagnosticsystembasedonmultimodemrimages AT jianguowei designandanalysisofarobustbreastcancerdiagnosticsystembasedonmultimodemrimages AT zhewang designandanalysisofarobustbreastcancerdiagnosticsystembasedonmultimodemrimages AT xiaomanwang designandanalysisofarobustbreastcancerdiagnosticsystembasedonmultimodemrimages AT naixuexiong designandanalysisofarobustbreastcancerdiagnosticsystembasedonmultimodemrimages |
_version_ |
1721409530359709696 |