Lung Nodule Image Retrieval Based on Convolutional Neural Networks and Hashing
|
摘要
Lung medical image retrieval based on content similarity plays an important role in computer-aided diagnosis of lung cancer.In recent years,binary hashing has become a hot topic in this field due to its compressed storage and fast query speed.Traditional hashing methods often rely on highdimensional features based hand-crafted methods,which might not be optimally compatible with lung nodule images.Also,different hashing bits contribute to the image retrieval differently,and therefore treating the hashing bits equally affects the retrieval accuracy.Hence,an image retrieval method of lung nodule images is proposed with the basis on convolutional neural networks and hashing.First,apre-trained and fine-tuned convolutional neural network is employed to learn multilevel semantic features of the lung nodules.Principal components analysis is utilized to remove redundant information and preserve informative semantic features of the lung nodules.Second,the proposed method relies on nine sign labels of lung nodules for the training set,and the semantic feature is combined to construct hashing functions.Finally,returned lung nodule images can be easily ranked with the query-adaptive search method based on weighted Hamming distance.Extensive experiments and evaluations on the dataset demonstrate that the proposed method can significantly improve the expression ability of lung nodule images,which further validates the effectiveness of the proposed method.
Lung medical image retrieval based on content similarity plays an important role in computer-aided diagnosis of lung cancer.In recent years,binary hashing has become a hot topic in this field due to its compressed storage and fast query speed.Traditional hashing methods often rely on highdimensional features based hand-crafted methods,which might not be optimally compatible with lung nodule images.Also,different hashing bits contribute to the image retrieval differently,and therefore treating the hashing bits equally affects the retrieval accuracy.Hence,an image retrieval method of lung nodule images is proposed with the basis on convolutional neural networks and hashing.First,apre-trained and fine-tuned convolutional neural network is employed to learn multilevel semantic features of the lung nodules.Principal components analysis is utilized to remove redundant information and preserve informative semantic features of the lung nodules.Second,the proposed method relies on nine sign labels of lung nodules for the training set,and the semantic feature is combined to construct hashing functions.Finally,returned lung nodule images can be easily ranked with the query-adaptive search method based on weighted Hamming distance.Extensive experiments and evaluations on the dataset demonstrate that the proposed method can significantly improve the expression ability of lung nodule images,which further validates the effectiveness of the proposed method.
Lung medical image retrieval based on content similarity plays an important role in computer-aided diagnosis of lung cancer.In recent years,binary hashing has become a hot topic in this field due to its compressed storage and fast query speed.Traditional hashing methods often rely on highdimensional features based hand-crafted methods,which might not be optimally compatible with lung nodule images.Also,different hashing bits contribute to the image retrieval differently,and therefore treating the hashing bits equally affects the retrieval accuracy.Hence,an image retrieval method of lung nodule images is proposed with the basis on convolutional neural networks and hashing.First,apre-trained and fine-tuned convolutional neural network is employed to learn multilevel semantic features of the lung nodules.Principal components analysis is utilized to remove redundant information and preserve informative semantic features of the lung nodules.Second,the proposed method relies on nine sign labels of lung nodules for the training set,and the semantic feature is combined to construct hashing functions.Finally,returned lung nodule images can be easily ranked with the query-adaptive search method based on weighted Hamming distance.Extensive experiments and evaluations on the dataset demonstrate that the proposed method can significantly improve the expression ability of lung nodule images,which further validates the effectiveness of the proposed method.
引文
[1]Siegel R L,Miller K D,Fedewa S A,et al.Colorectal cancer statistics,2017[J].Ca A Cancer Journal for Clinicians,2017,67(3):177.
[2]Han H,Li L,Han F,et al.Fast and adaptive detection of pulmonary nodules in thoracic CT images using a hierarchical vector quantization scheme[J].IEEEJournal of Biomedical&Health Informatics,2015,19(2):648.
[3]Ma L,Liu X,Gao Y,et al.A new method of content based medical image retrieval and its applications to CT imaging sign retrieval[J].Journal of Biomedical Informatics,2017,66(C):148-158.
[4]Setio A A,Ciompi F,Litjens G,et al.Pulmonary nodule detection in CT images:false positive reduction using multi-view convolutional networks[J].IEEETransactions on Medical Imaging,2016,35(5):1160.
[5]Dilauro M,Mcinnes M D,Schieda N,et al.Internal hernia after laparoscopic Roux-en-Y gastric bypass:optimal CT signs for diagnosis and clinical decision making[J].Radiology,2016,282(3):160956.
[6]Firmino M,Angelo G,Morais H,et al.Computer-aided detection(CADe)and diagnosis(CADx)system for lung cancer with likelihood of malignancy[J].Biomedical Engineering Online,2016,15(1):2.
[7]Arya S,Mount D M,Netanyahu N S,et al.An optimal algorithm for approximate nearest neighbor searching[C]∥ACM-SIAM Symposium on Discrete Algorithms,Society for Industrial and Applied Mathematics,1994:573-582.
[8]Swaminathan A,Mao Y,Wu M.Robust and secure image hashing[J].IEEE Transactions on Information Forensics&Security,2006,1(2):215-230.
[9]Gionis A,Indyk P,Motwani R.Similarity search in high dimensions via hashing[C]∥International Conference on Very Large Data Bases,Morgan Kaufmann Publishers Inc,1999:518-529.
[10]Bai X,Yang H,Zhou J,et al.Data-dependent hashing based on p-stable distribution[J].IEEE Transactions on Image Processing a Publication of the IEEESignal Processing Society,2014,23(12):5033.
[11]Gu X,Zhang L,Zhang D,et al.Data independent method of constructing distributed LSH for largescale dynamic high-dimensional indexing[C]∥IEEE,International Conference on High Performance Computing and Communication&2012IEEE,International Conference on Embedded Software and Systems,IEEE Computer Society,2012:564-571.
[12]Li W,Zhou Z.Learning to hash for big data:Current status and future trends[J].Chinese Science Bulletin,2015,60(5-6):485.
[13]Gong Y,Lazebnik S,Gordo A,et al.Iterative quantization:aprocrustean approach to learning binary codes for large-scale image retrieval[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2013,35(12):2916.
[14]Weiss Y,Torralba A,Fergus R.Spectral hashing[C]∥International Conference on Neural Information Processing Systems,Curran Associates Inc,2008:1753-1760.
[15]Zhou X,Huang Z,Ng W W Y.Weighted grid principal component analysis hashing[C]∥International Conference on Machine Learning and Cybernetics,IEEE,2015:200-205.
[16]Wang J,Kumar S,Chang S F.Semi-supervised hashing for large-scale search[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2012,34(12):2393.
[17]Zhou J,Fu H,Kong X.A balanced semi-supervised hashing method for CBIR[C]∥IEEE International Conference on Image Processing,IEEE,2011:2481-2484.
[18]Liu W,Wang J,Ji R,et al.Supervised hashing with kernels[C]∥IEEE Conference on Computer Vision and Pattern Recognition,IEEE Computer Society,2012:2074-2081.
[19]Zhang S,Li J,Guo J,et al.Scalable discrete supervised hash learning with asymmetric matrix factorization[C]∥2016IEEE 16th International Conference on Data Mining(ICDM),Barcelona,2016:1347-1352.
[20]Gui J,Liu T,Sun Z,et al.Supervised discrete hashing with relaxation.[J].IEEE Transactions on Neural Networks&Learning Systems,2016(99):1-10.
[21]Wu Guorong,Shen Dinggang,Sabunce M R.Machine learning and medical imaging[M].Pittsburgh:Academic Press,2016:237-255.
[22]Liu J,Zhang S,Liu W,et al.Scalable mammogram retrieval using anchor graph hashing[C]∥2014IEEE11th International Symposium on Biomedical Imaging(ISBI),Beijing,2014:898-901.
[23]Yu X,Zhang S,Liu B,et al.Large scale medical image search via unsupervised PCA hashing[C]∥Computer Vision and Pattern Recognition Workshops,IEEE,2013:393-398.
[24]Xu Y,Mo T,Feng Q,et al.Deep learning of feature representation with multiple instance learning for medical image analysis[C]∥IEEE International Conference on Acoustics,Speech and Signal Processing,IEEE,2014:1626-1630.
[25]Suzani A,Seitel A,Liu Y,et al.Fast automatic vertebrae detection and localization in pathological CTScans-a deep learning approach[C]∥Medical Image Computing and Computer-Assisted Intervention(MICCAI),2015:678-686.
[26]Roth H R,Farag A,Lu L,et al.Deep convolutional networks for pancreas segmentation in CT imaging[C]∥SPIE Medical Imaging.International Society for Optics and Photonics,2015.
[27]Armato S,Mclennan G,Mcnitt-Gray M,et al.WE-B-201B-02:the lung image database consortium(LIDC)and image database resource initiative(ID-RI):a completed public database of CT scans for lung nodule analysis[J].Medical Physics,2010,37(6):3416-3417.
[28]Yang X,Cheng K T T.Local difference binary for ultrafast and distinctive feature description[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2014,36(1):188.
[29]Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[C]∥International Conference on Neural Information Processing Systems,Curran Associates Inc,2012:1097-1105.
[30]Babenko A,Slesarev A,Chigorin A,et al.Neural codes for image retrieval[C]∥Computer Vision-EC-CV,2014,8689:584-599.
[31]Gionis A,Indyk P,Motwani R.Similarity search in high dimensions via hashing[C]∥International Conference on Very Large Data Bases,Morgan Kaufmann Publishers Inc,1999:518-529.
[32]Ng W W Y,Lv Y,Yeung D S,et al.Two-phase mapping hashing[J].Neurocomputing,2015,151(3):1423-1429.
[33]Zhao J,Ji G,Xia Y,et al.Cavitary nodule segmentation in computed tomography images based on selfgenerating neural networks and particle swarm optimization[J].International Journal of Bio-Inspired Computation,2015,7(1):62-67.
[2]Han H,Li L,Han F,et al.Fast and adaptive detection of pulmonary nodules in thoracic CT images using a hierarchical vector quantization scheme[J].IEEEJournal of Biomedical&Health Informatics,2015,19(2):648.
[3]Ma L,Liu X,Gao Y,et al.A new method of content based medical image retrieval and its applications to CT imaging sign retrieval[J].Journal of Biomedical Informatics,2017,66(C):148-158.
[4]Setio A A,Ciompi F,Litjens G,et al.Pulmonary nodule detection in CT images:false positive reduction using multi-view convolutional networks[J].IEEETransactions on Medical Imaging,2016,35(5):1160.
[5]Dilauro M,Mcinnes M D,Schieda N,et al.Internal hernia after laparoscopic Roux-en-Y gastric bypass:optimal CT signs for diagnosis and clinical decision making[J].Radiology,2016,282(3):160956.
[6]Firmino M,Angelo G,Morais H,et al.Computer-aided detection(CADe)and diagnosis(CADx)system for lung cancer with likelihood of malignancy[J].Biomedical Engineering Online,2016,15(1):2.
[7]Arya S,Mount D M,Netanyahu N S,et al.An optimal algorithm for approximate nearest neighbor searching[C]∥ACM-SIAM Symposium on Discrete Algorithms,Society for Industrial and Applied Mathematics,1994:573-582.
[8]Swaminathan A,Mao Y,Wu M.Robust and secure image hashing[J].IEEE Transactions on Information Forensics&Security,2006,1(2):215-230.
[9]Gionis A,Indyk P,Motwani R.Similarity search in high dimensions via hashing[C]∥International Conference on Very Large Data Bases,Morgan Kaufmann Publishers Inc,1999:518-529.
[10]Bai X,Yang H,Zhou J,et al.Data-dependent hashing based on p-stable distribution[J].IEEE Transactions on Image Processing a Publication of the IEEESignal Processing Society,2014,23(12):5033.
[11]Gu X,Zhang L,Zhang D,et al.Data independent method of constructing distributed LSH for largescale dynamic high-dimensional indexing[C]∥IEEE,International Conference on High Performance Computing and Communication&2012IEEE,International Conference on Embedded Software and Systems,IEEE Computer Society,2012:564-571.
[12]Li W,Zhou Z.Learning to hash for big data:Current status and future trends[J].Chinese Science Bulletin,2015,60(5-6):485.
[13]Gong Y,Lazebnik S,Gordo A,et al.Iterative quantization:aprocrustean approach to learning binary codes for large-scale image retrieval[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2013,35(12):2916.
[14]Weiss Y,Torralba A,Fergus R.Spectral hashing[C]∥International Conference on Neural Information Processing Systems,Curran Associates Inc,2008:1753-1760.
[15]Zhou X,Huang Z,Ng W W Y.Weighted grid principal component analysis hashing[C]∥International Conference on Machine Learning and Cybernetics,IEEE,2015:200-205.
[16]Wang J,Kumar S,Chang S F.Semi-supervised hashing for large-scale search[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2012,34(12):2393.
[17]Zhou J,Fu H,Kong X.A balanced semi-supervised hashing method for CBIR[C]∥IEEE International Conference on Image Processing,IEEE,2011:2481-2484.
[18]Liu W,Wang J,Ji R,et al.Supervised hashing with kernels[C]∥IEEE Conference on Computer Vision and Pattern Recognition,IEEE Computer Society,2012:2074-2081.
[19]Zhang S,Li J,Guo J,et al.Scalable discrete supervised hash learning with asymmetric matrix factorization[C]∥2016IEEE 16th International Conference on Data Mining(ICDM),Barcelona,2016:1347-1352.
[20]Gui J,Liu T,Sun Z,et al.Supervised discrete hashing with relaxation.[J].IEEE Transactions on Neural Networks&Learning Systems,2016(99):1-10.
[21]Wu Guorong,Shen Dinggang,Sabunce M R.Machine learning and medical imaging[M].Pittsburgh:Academic Press,2016:237-255.
[22]Liu J,Zhang S,Liu W,et al.Scalable mammogram retrieval using anchor graph hashing[C]∥2014IEEE11th International Symposium on Biomedical Imaging(ISBI),Beijing,2014:898-901.
[23]Yu X,Zhang S,Liu B,et al.Large scale medical image search via unsupervised PCA hashing[C]∥Computer Vision and Pattern Recognition Workshops,IEEE,2013:393-398.
[24]Xu Y,Mo T,Feng Q,et al.Deep learning of feature representation with multiple instance learning for medical image analysis[C]∥IEEE International Conference on Acoustics,Speech and Signal Processing,IEEE,2014:1626-1630.
[25]Suzani A,Seitel A,Liu Y,et al.Fast automatic vertebrae detection and localization in pathological CTScans-a deep learning approach[C]∥Medical Image Computing and Computer-Assisted Intervention(MICCAI),2015:678-686.
[26]Roth H R,Farag A,Lu L,et al.Deep convolutional networks for pancreas segmentation in CT imaging[C]∥SPIE Medical Imaging.International Society for Optics and Photonics,2015.
[27]Armato S,Mclennan G,Mcnitt-Gray M,et al.WE-B-201B-02:the lung image database consortium(LIDC)and image database resource initiative(ID-RI):a completed public database of CT scans for lung nodule analysis[J].Medical Physics,2010,37(6):3416-3417.
[28]Yang X,Cheng K T T.Local difference binary for ultrafast and distinctive feature description[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2014,36(1):188.
[29]Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[C]∥International Conference on Neural Information Processing Systems,Curran Associates Inc,2012:1097-1105.
[30]Babenko A,Slesarev A,Chigorin A,et al.Neural codes for image retrieval[C]∥Computer Vision-EC-CV,2014,8689:584-599.
[31]Gionis A,Indyk P,Motwani R.Similarity search in high dimensions via hashing[C]∥International Conference on Very Large Data Bases,Morgan Kaufmann Publishers Inc,1999:518-529.
[32]Ng W W Y,Lv Y,Yeung D S,et al.Two-phase mapping hashing[J].Neurocomputing,2015,151(3):1423-1429.
[33]Zhao J,Ji G,Xia Y,et al.Cavitary nodule segmentation in computed tomography images based on selfgenerating neural networks and particle swarm optimization[J].International Journal of Bio-Inspired Computation,2015,7(1):62-67.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |