基于纹理特征的糖网临床前期眼底自发荧光图像识别
|
摘要
及时发现和干预潜在的糖尿病视网膜病变患者,对帮助提升糖尿病患者的整体视觉质量和降低医疗成本具有十分积极的意义.由于糖尿病视网膜病变临床前期和正常人的眼底荧光图像在视觉感观基本上没有差别,为此本文通过目前应用较广的纹理特征算法和支持向量机对这两组图像进行了模式识别.通过将185张眼底荧光图片十折交叉检验发现, LBP算法对其具有很好的识别效果.等价模式下的59维LBP算子的十折交叉准确率达到了91.89%,同时在测试集和训练集以1:1随机划分的情况下,由训练集数据所生成的模型对测试集中92张眼底荧光图像的识别准确率达到了88.12%, AUC值为0.943.
Timely diagnosis and intervention for potential diabetic retinopathy patients is very positive in improving the overall visual quality of diabetic patients and reducing medical costs.Because the fundus fluorescence images of preclinical diabetic retinopathy and normal people have no obvious difference in visual perception,this study recognizes the two groups of images through the widely used texture feature algorithm and support vector machine.Through the 10-fold cross validation of 185 fundus autofluorescence images,the LBP algorithm has a sound recognition effect.The 10-fold cross-validation accuracy of the 59-dimensional LBP operator with"Uniform"patterns reaches 91.89%.And in the case that the test set and the training set are randomly divided by 1:1,the recognition accuracy of 92 fundus fluorescence images in the test set reaches 88.12%,and the AUC is 0.943.
Timely diagnosis and intervention for potential diabetic retinopathy patients is very positive in improving the overall visual quality of diabetic patients and reducing medical costs.Because the fundus fluorescence images of preclinical diabetic retinopathy and normal people have no obvious difference in visual perception,this study recognizes the two groups of images through the widely used texture feature algorithm and support vector machine.Through the 10-fold cross validation of 185 fundus autofluorescence images,the LBP algorithm has a sound recognition effect.The 10-fold cross-validation accuracy of the 59-dimensional LBP operator with"Uniform"patterns reaches 91.89%.And in the case that the test set and the training set are randomly divided by 1:1,the recognition accuracy of 92 fundus fluorescence images in the test set reaches 88.12%,and the AUC is 0.943.
引文
1冀向宁.糖尿病视网膜病变临床前期的观察[硕士学位论文].石家庄:河北医科大学,2013.
2 Ozdek S, Lonneville YH, Onol M, et al. Assessment of nerve fiber layer in diabetic patients with scanning laser polarimetry. Eye, 2002, 16(6):761-765.[doi:10.1038/sj.eye.6700207]
3王国德,张培林,任国全,等.融合LBP和GLCM的纹理特征提取方法.计算机工程,2012, 38(11):199-201.[doi:10.3969/j.issn. 1000-3428.2012.11.061]
4 Camlica Z,Tizhoosh HR, Khalvati F. Medical image classification via SVM Using LBP features from saliencybased folded data. Proceedings of 2015 IEEE 14th International Conference on Machine Learning and Applications. Miami, FL, USA. 2015. 128-132.
5 Jung JY, Kim SW, Yoo CH, et al. LBP-ferns-based feature extraction for robust facial recognition. IEEE Transactions on Consumer Electronics, 2016, 62(4):446-453.[doi:10.1109/TCE.2016.7838098]
6武瑞霞,张子瑞,陈宇彬,等.利用二维格子复杂性挖掘肝癌CT图像预后信息.温州医科大学学报,2018, 48(6):396-400.[doi:10.3969/j.issn.2095-9400.2018.06.002]
7 Ojala T, Pietikainen M, Harwood I. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 1996, 29(1):51-59.[doi:10.1016/0031-3203(95)00067-4]
8 Ojala T, Pietikainen M, Maenpaa T. Multiresolution grayscale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 24(7):971-987.
9高程程,惠晓威.基于灰度共生矩阵的纹理特征提取.计算机系统应用,2010, 19(6):195-198.[doi:10.3969/j.issn.1003-3254.2010.06.047]
10 Cortes C,Vapnik V. Support-vector networks. Machine Learning, 1995, 20(3):273-297.
11张瑜慧,胡学龙,陈琳.基于支持向量机的图像分类.扬州大学学报(自然科学版),2007, 10(2):42-46.
12 Jung Y. Multiple predicting K-fold cross-validation for model selection. Journal of Nonparametric Statistics,2018,30(1):197-215.[doi:10.1080/10485252.2017.1404598]
13李坤,龚向宁,郎卫华.糖尿病视网膜病变临床前期的视功能变化分析.国际眼科杂志,2015, 15(6):1094-1096.
14冀向宁,王志学,王文英,等.光学相干断层成像在糖尿病视网膜病变临床前期观察中的应用.中国全科医学,2014,17(3):350-352.[doi:10.3969/j.issn. 1007-9572.2014.03.030]
2 Ozdek S, Lonneville YH, Onol M, et al. Assessment of nerve fiber layer in diabetic patients with scanning laser polarimetry. Eye, 2002, 16(6):761-765.[doi:10.1038/sj.eye.6700207]
3王国德,张培林,任国全,等.融合LBP和GLCM的纹理特征提取方法.计算机工程,2012, 38(11):199-201.[doi:10.3969/j.issn. 1000-3428.2012.11.061]
4 Camlica Z,Tizhoosh HR, Khalvati F. Medical image classification via SVM Using LBP features from saliencybased folded data. Proceedings of 2015 IEEE 14th International Conference on Machine Learning and Applications. Miami, FL, USA. 2015. 128-132.
5 Jung JY, Kim SW, Yoo CH, et al. LBP-ferns-based feature extraction for robust facial recognition. IEEE Transactions on Consumer Electronics, 2016, 62(4):446-453.[doi:10.1109/TCE.2016.7838098]
6武瑞霞,张子瑞,陈宇彬,等.利用二维格子复杂性挖掘肝癌CT图像预后信息.温州医科大学学报,2018, 48(6):396-400.[doi:10.3969/j.issn.2095-9400.2018.06.002]
7 Ojala T, Pietikainen M, Harwood I. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 1996, 29(1):51-59.[doi:10.1016/0031-3203(95)00067-4]
8 Ojala T, Pietikainen M, Maenpaa T. Multiresolution grayscale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 24(7):971-987.
9高程程,惠晓威.基于灰度共生矩阵的纹理特征提取.计算机系统应用,2010, 19(6):195-198.[doi:10.3969/j.issn.1003-3254.2010.06.047]
10 Cortes C,Vapnik V. Support-vector networks. Machine Learning, 1995, 20(3):273-297.
11张瑜慧,胡学龙,陈琳.基于支持向量机的图像分类.扬州大学学报(自然科学版),2007, 10(2):42-46.
12 Jung Y. Multiple predicting K-fold cross-validation for model selection. Journal of Nonparametric Statistics,2018,30(1):197-215.[doi:10.1080/10485252.2017.1404598]
13李坤,龚向宁,郎卫华.糖尿病视网膜病变临床前期的视功能变化分析.国际眼科杂志,2015, 15(6):1094-1096.
14冀向宁,王志学,王文英,等.光学相干断层成像在糖尿病视网膜病变临床前期观察中的应用.中国全科医学,2014,17(3):350-352.[doi:10.3969/j.issn. 1007-9572.2014.03.030]