Multispectral Heterogeneity Detection Based on Frame Accumulation and Deep Learning
Hyperspectral transmission imaging may provide a means for rapid screening of breast tumors, but tissue has a strong nature of scattering, thus causing a great difficulty in identifying heterogeneity. In this paper, a combination of frame accumulation and deep learning was proposed to detect heterog...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8660494/ |
id |
doaj-ef197a7126164f4e8b9e0c81faadb2a3 |
---|---|
record_format |
Article |
spelling |
doaj-ef197a7126164f4e8b9e0c81faadb2a32021-03-29T22:16:27ZengIEEEIEEE Access2169-35362019-01-017292772928410.1109/ACCESS.2019.28977378660494Multispectral Heterogeneity Detection Based on Frame Accumulation and Deep LearningBaoju Zhang0https://orcid.org/0000-0002-1435-7401Chengcheng Zhang1https://orcid.org/0000-0003-0505-7607Gang Li2Ling Lin3Cuiping Zhang4Fengjuan Wang5Wenrui Yan6Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin, ChinaTianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin, ChinaState Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University, Tianjin, ChinaState Key Laboratory of Precision Measurement Technology and Instruments, Tianjin University, Tianjin, ChinaTianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin, ChinaTianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin, ChinaTianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin, ChinaHyperspectral transmission imaging may provide a means for rapid screening of breast tumors, but tissue has a strong nature of scattering, thus causing a great difficulty in identifying heterogeneity. In this paper, a combination of frame accumulation and deep learning was proposed to detect heterogeneity, and we designed the simulation experiment of collecting phantom images. On the basis of frame accumulation preprocessing, the heterogeneous detection is performed on multispectral images by using faster regions with convolutional neural networks (R-CNN) features and a single shot multibox detector (SSD), two typical detection frameworks of deep learning. The results show that the mean average precision (mAP) of faster R-CNN and SSD reach 90.8% and 95.1%, respectively, when three classes (including background) are detected with the help of the dataset provided in this paper, and the mAP of two frameworks both reach 99.9% when two classes (including background) are detected. The detection efficiency of the SSD is higher than faster, SSD's detection speed can reach 50 fps, and the detection accuracy of the images after frame accumulation preprocessing is higher than that without frame accumulation processing. In summary, we validate the possibility of employing faster R-CNN and SSD to detect heterogeneity in multispectral images based on frame accumulation that improves image grayscale resolution, and it has a certain degree of reference significance for the application of deep learning in multispectral image detection.https://ieeexplore.ieee.org/document/8660494/Deep learningframe accumulationheterogeneity detectionmultispectral image |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Baoju Zhang Chengcheng Zhang Gang Li Ling Lin Cuiping Zhang Fengjuan Wang Wenrui Yan |
spellingShingle |
Baoju Zhang Chengcheng Zhang Gang Li Ling Lin Cuiping Zhang Fengjuan Wang Wenrui Yan Multispectral Heterogeneity Detection Based on Frame Accumulation and Deep Learning IEEE Access Deep learning frame accumulation heterogeneity detection multispectral image |
author_facet |
Baoju Zhang Chengcheng Zhang Gang Li Ling Lin Cuiping Zhang Fengjuan Wang Wenrui Yan |
author_sort |
Baoju Zhang |
title |
Multispectral Heterogeneity Detection Based on Frame Accumulation and Deep Learning |
title_short |
Multispectral Heterogeneity Detection Based on Frame Accumulation and Deep Learning |
title_full |
Multispectral Heterogeneity Detection Based on Frame Accumulation and Deep Learning |
title_fullStr |
Multispectral Heterogeneity Detection Based on Frame Accumulation and Deep Learning |
title_full_unstemmed |
Multispectral Heterogeneity Detection Based on Frame Accumulation and Deep Learning |
title_sort |
multispectral heterogeneity detection based on frame accumulation and deep learning |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
Hyperspectral transmission imaging may provide a means for rapid screening of breast tumors, but tissue has a strong nature of scattering, thus causing a great difficulty in identifying heterogeneity. In this paper, a combination of frame accumulation and deep learning was proposed to detect heterogeneity, and we designed the simulation experiment of collecting phantom images. On the basis of frame accumulation preprocessing, the heterogeneous detection is performed on multispectral images by using faster regions with convolutional neural networks (R-CNN) features and a single shot multibox detector (SSD), two typical detection frameworks of deep learning. The results show that the mean average precision (mAP) of faster R-CNN and SSD reach 90.8% and 95.1%, respectively, when three classes (including background) are detected with the help of the dataset provided in this paper, and the mAP of two frameworks both reach 99.9% when two classes (including background) are detected. The detection efficiency of the SSD is higher than faster, SSD's detection speed can reach 50 fps, and the detection accuracy of the images after frame accumulation preprocessing is higher than that without frame accumulation processing. In summary, we validate the possibility of employing faster R-CNN and SSD to detect heterogeneity in multispectral images based on frame accumulation that improves image grayscale resolution, and it has a certain degree of reference significance for the application of deep learning in multispectral image detection. |
topic |
Deep learning frame accumulation heterogeneity detection multispectral image |
url |
https://ieeexplore.ieee.org/document/8660494/ |
work_keys_str_mv |
AT baojuzhang multispectralheterogeneitydetectionbasedonframeaccumulationanddeeplearning AT chengchengzhang multispectralheterogeneitydetectionbasedonframeaccumulationanddeeplearning AT gangli multispectralheterogeneitydetectionbasedonframeaccumulationanddeeplearning AT linglin multispectralheterogeneitydetectionbasedonframeaccumulationanddeeplearning AT cuipingzhang multispectralheterogeneitydetectionbasedonframeaccumulationanddeeplearning AT fengjuanwang multispectralheterogeneitydetectionbasedonframeaccumulationanddeeplearning AT wenruiyan multispectralheterogeneitydetectionbasedonframeaccumulationanddeeplearning |
_version_ |
1724192015119286272 |