结合降维与LBP特征的癌细胞识别研究
|
摘要
活检过程中,有资质的医生需要根据细胞形态结构对数千活检玻片分析判读,耗时长、误诊率高。针对乳腺癌细胞,采用LBP(Local Binary Patterns)描述乳腺癌细胞特征,并且利用MDS(Multidimensional Scaling),LLE(Locally Linear Embedding)等矩阵降维,以BP神经网络算法实现癌细胞辅助判读。实验结果表明,采用LBP-LLE-BP结合的方法,数据规模降维至5×252时,准确率高达89.61%,可为医生诊断提供重要参考。
During the biopsy process,qualified doctors need to analyze and interpret thousands of biopsy slides according to their morphological structure,which takes long time and high misdiagnosis rate. In this paper,breast cancer cells were characterized by LBP(Local Binary Patterns) to describe the characteristics of breast cancer cells;and using matrix reduction methods such as MDS(Multidimensional Scaling) and LLE(Locally Linear Embedding), the BP neural network algorithm was used to assist in the interpretation of cancer cells. The experimental results show that using the LBP-LLE-BP method,the recognition rate was as high as 89.61% when the data size was reduced to 5×252,which could provide important reference for physicians.
During the biopsy process,qualified doctors need to analyze and interpret thousands of biopsy slides according to their morphological structure,which takes long time and high misdiagnosis rate. In this paper,breast cancer cells were characterized by LBP(Local Binary Patterns) to describe the characteristics of breast cancer cells;and using matrix reduction methods such as MDS(Multidimensional Scaling) and LLE(Locally Linear Embedding), the BP neural network algorithm was used to assist in the interpretation of cancer cells. The experimental results show that using the LBP-LLE-BP method,the recognition rate was as high as 89.61% when the data size was reduced to 5×252,which could provide important reference for physicians.
引文
[1]Jun S H,Park B H,Seo J B,et al.Development of a computer-aided differential diagnosis system to distinguish between usual interstitial pneumonia and non-specific interstitial pneumonia using textureand shape-based hierarchical classifiers on HRCTimages[J].Journal of Digital Imaging,2018,31(2):235-244.
[2]Rendon-Gonzalez E,Ponomaryov V.Automatic Lung nodule segmentation and classification in CT images based on SVM[C].International Kharkiv Symposium on Physics and Engineering of Microwaves,Millimeter and Submillimeter Waves.IEEE,2016:1-4.
[3]Saha M,Mukherjee R,Chakraborty C.Computer-aided diagnosis of breast cancer using cytological images:a systematic review[J].Tissue&Cell,2016,48(5):461-474.
[4]陆新泉,李宁,陈世福.形态、颜色特征及神经网络在肺癌细胞识别中的应用研究[J].计算机辅助设计与图形学学报,2001(1):87-92.
[5]Niwas S I,Palanisamy P,Chibbar R,et al.An expert support system for breast cancer diagnosis using color wavelet features[J].Journal of Medical Systems,2012,36(5):3091-3102.
[6]Kaymak S,Helwan A,Uzun D.Breast cancer image classification using artificial neural networks[J].Procedia Computer Science,2017(120):126-131.
[7]Sharma H,Zerbe N,Klempert I,et al.Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology[J].Computerized Medical Imaging&Graphics,2017,61(Supplement C):2-13.
[8]Kawahara J,Brown C J,Miller S P,et al.BrainNetCNN:convolutional neural networks for brain networks;towards predicting neurodevelopment[J].Neuroimage,2017,146:1038-1049.
[9]He W,Member S,IEEE,et al.Weighted sparse graph based dimensionality reduction for hyperspectral images[J].IEEE Geoscience&Remote Sensing Letters,2017,13(5):686-690.
[10]Ojala T,Pietikainen M,Maenpaa T.Multiresolution gray scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[11]Zhao G,Ahonen T,Matas J,et al.Rotation-invariant image and video description with local binary pattern features[J].IEEE Transactions on Image Processing,2012,21(4):1465-1477.
[12]Ahonen T,Hadid A,Pietikainen M.Face description with local binary patterns:application to face recognition[J].IEEE Trans Pattern Anal Mach Intell,2006,28(12):2037-2041.
[13]Binol H,Ochilov S,Alam M S,et al.Target oriented dimensionality reduction of hyperspectral data by kernel fukunaga-koontz transform[J].Optics&Lasers in Engineering,2017,89:123-130.
[14]Binol H,Bal A.Supervised target detection in hyperspectral images using one-class fukunaga-koontz transform[C].Signal Processing,Sensor/information Fusion,&Target Recognition XXV.SPIE,2016.
[15]Binol H,Uslu F S,Bal A.Unsupervised nonlinear feature extraction method and its effects on target detection in highdimensional data[J].International Journal of Electrical,Electronics and Data Communication,2015,3(8):43-46.
[16]Suckling J,Parker J,Dance D R,et al.The Mammographic image analysis society digital mammogram database[DB/OL].https://www.repository.com.ac.uk/handle/1810/2503941,2015.
[17]Bergstra J,Bengio Y.Random search for hyper-parameter optimization[J].Journal of Machine Learning Research,2012,13(1):281-305.
[2]Rendon-Gonzalez E,Ponomaryov V.Automatic Lung nodule segmentation and classification in CT images based on SVM[C].International Kharkiv Symposium on Physics and Engineering of Microwaves,Millimeter and Submillimeter Waves.IEEE,2016:1-4.
[3]Saha M,Mukherjee R,Chakraborty C.Computer-aided diagnosis of breast cancer using cytological images:a systematic review[J].Tissue&Cell,2016,48(5):461-474.
[4]陆新泉,李宁,陈世福.形态、颜色特征及神经网络在肺癌细胞识别中的应用研究[J].计算机辅助设计与图形学学报,2001(1):87-92.
[5]Niwas S I,Palanisamy P,Chibbar R,et al.An expert support system for breast cancer diagnosis using color wavelet features[J].Journal of Medical Systems,2012,36(5):3091-3102.
[6]Kaymak S,Helwan A,Uzun D.Breast cancer image classification using artificial neural networks[J].Procedia Computer Science,2017(120):126-131.
[7]Sharma H,Zerbe N,Klempert I,et al.Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology[J].Computerized Medical Imaging&Graphics,2017,61(Supplement C):2-13.
[8]Kawahara J,Brown C J,Miller S P,et al.BrainNetCNN:convolutional neural networks for brain networks;towards predicting neurodevelopment[J].Neuroimage,2017,146:1038-1049.
[9]He W,Member S,IEEE,et al.Weighted sparse graph based dimensionality reduction for hyperspectral images[J].IEEE Geoscience&Remote Sensing Letters,2017,13(5):686-690.
[10]Ojala T,Pietikainen M,Maenpaa T.Multiresolution gray scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[11]Zhao G,Ahonen T,Matas J,et al.Rotation-invariant image and video description with local binary pattern features[J].IEEE Transactions on Image Processing,2012,21(4):1465-1477.
[12]Ahonen T,Hadid A,Pietikainen M.Face description with local binary patterns:application to face recognition[J].IEEE Trans Pattern Anal Mach Intell,2006,28(12):2037-2041.
[13]Binol H,Ochilov S,Alam M S,et al.Target oriented dimensionality reduction of hyperspectral data by kernel fukunaga-koontz transform[J].Optics&Lasers in Engineering,2017,89:123-130.
[14]Binol H,Bal A.Supervised target detection in hyperspectral images using one-class fukunaga-koontz transform[C].Signal Processing,Sensor/information Fusion,&Target Recognition XXV.SPIE,2016.
[15]Binol H,Uslu F S,Bal A.Unsupervised nonlinear feature extraction method and its effects on target detection in highdimensional data[J].International Journal of Electrical,Electronics and Data Communication,2015,3(8):43-46.
[16]Suckling J,Parker J,Dance D R,et al.The Mammographic image analysis society digital mammogram database[DB/OL].https://www.repository.com.ac.uk/handle/1810/2503941,2015.
[17]Bergstra J,Bengio Y.Random search for hyper-parameter optimization[J].Journal of Machine Learning Research,2012,13(1):281-305.