基于G-SA-SVM的快速血管化鉴别方法

生物材料的显微高光谱成像分析技术是生物光谱学研究的前沿.烧伤、深度创伤病人治疗过程中，需要确定移植于患者创面的真皮替代物有没有进入正常的血管化进程，这是评价填充修复材料优劣的关键，也是患者创面恢复的重要指标.提出并实现了一种基于G-SA-SVM的快速血管化鉴别方法.该方法以显微高光谱成像技术为基础，首先对采集的高光谱数据进行光谱维和空间维的空白校正处理，然后对数据进行特征自适应性Gamma校正，最后利用模拟退火优化参数的支持向量机算法(SA-SVM)进行识别处理，有效定位红细胞，进而快速定位血管.实验结果表明，本文提出的G-SA-SVM算法误判率更低，识别精度更高，可以用于微血管新生的评价和鉴定.

Abstract

Microscopic hyperspectral imaging technology of biological material is the forefront of biological spectroscopy study. It is important to make sure whether the dermal substitute transplanted in patient’s wounds gets into normal vascularization process when burned or deeply traumatic patients are treated. This is the key to evaluating the quality of repair material and is also an important index of patient’s wounds recovery. This paper proposes and realizes a method of rapid vascularization identification based on G-SA-SVM. This method is based on the microscopic hyperspectral imaging. First, the blank correction is used in hyperspectral data. Second, an adaptive Gamma correction model is employed to take advantage of the spectral and spatial features. Finally, simulated annealing is used to optimize the parameters of support vector machine (SA-SVM). SA-SVM is applied to locating the red blood cells effectively and then locating the blood vessels quickly. The experimental results confirm that the proposed method called G-SA-SVM has higher classification accuracy. Hence, it can be applied to evaluating the vascularization process.

参考文献

[1] Garlick J A. Engineering skin to study human disease—tissue models for cancer biology and wound repair. Adv Biochem Eng Biotechnol, 2007. 103: 207-39.

[2] Halim A S, Khoo T L, Mohd Yussof SJ., Biologic and synthetic skin substitutes: An overview. Indian J Plast Surg, 2010. 43(Suppl): S23-8.

[3] Austin Pourmoussa, Daniel J Gardner, Maxwell B Johnson. An update and review of cell-based wound dressings and their integration into clinical practice. Ann Transl Med, 2016. 4(23): 457.

[4] Klar AS, Biedermann T, Simmen-Meuli C et al., Comparison of in vivo immune responses following transplantation of vascularized and non-vascularized human dermo-epidermal skin substitutes. Pediatr Surg Int, 2017. 33(3):377-382.

[5] WU Zheng-Jie,HUANG Yao-Xiong, WANG Cheng, et al. Study on quantitative analysis of Raman spectra with strong fluorescence background［J］. Spectroscopy and Spectral Analysis(吴正洁,黄耀熊,王成,等.对强荧光背景拉曼光谱定量分析的研究.光谱学与光谱分析),2010,30(07):1798-1801.

[6] Biedermann T S， Boettcher-Haberzeth, E Reichmann, Tissue engineering of skin for wound coverage. Eur J Pediatr Surg, 2013. 23(5): 375-82.

[7] Luo X, Lin C, Wang X, Lin X, He S,., et al. Acellular Dermal Matrix Combined with Autologous Skin Grafts for Closure of Chronic Wounds after Reconstruction of Skull Defects with Titanium Mesh. J Neurol Surg A Cent Eur Neurosurg, 2016. 77(4): 297-9.

[8] Tasev D, Konijnenberg LS, Amado-Azevedo J, et al. CD34 expression modulates tube-forming capacity and barrier properties of peripheral blood-derived endothelial colony-forming cells (ECFCs). Angiogenesis, 2016. 19(3): 325-38.

[9] Qian Wang,Li Chang,Mei Zhou, et al. A spectral and morphologic method for white blood cell classification. Optics & Laser Technology, 2016. 84:144-148.

[10] Li Q,Peng H. ,Wang J. , et al. Coexpression of CdSe and CdSe/CdS quantum dots in live cells using molecular hyperspectral imaging technology. J Biomed Opt. 2015 Nov; 20(11):110504.

[11] Attas M, Hewko M, Payette J, et al. Visualization of cutaneous hemoglobin oxygenation and skin hydration using near-infrared spectroscopic imaging［J］. Skin Research and Technology, 2001, 7(4): 238.

[12] Kong S G, Du Z, Martin M, et al. Hyperspectral Fluorescence Image Analysis for Use in Medical Diagnostics. Advanced Biomedical and Clinical Diagnostic Systems III［C］. Proc. of SPIE, 2005, 5692:21-28.

[13] Stamatas G N, Southall M, Kollias N. In vivo monitoring of cutaneous edema using spectral imaging in the visible and near infrared［J］. Journal of Investigative Dermatology, 2006, 126(8):1753-1760.

[14] LIU Hong-Ying,LI Qing-Li,GU Bin, et al. Performance analysis and data preprocessing of a new molecular hyperspectral imaging system［J］. Spectroscopy and Spectral Analysis(刘洪英,李庆利,顾彬,等. 新型分子高光谱成像系统性能分析及数据预处理. 光谱学与光谱分析),2012,32(11):3161-3166.

[15] ZENG Tao-Fang, LUO Xu, XIN Guo-Hua, et al..Design,preparation and synchronous transplantation experiments of laser micropore porcine acellular dermal matrix［J］. Journal of Shanghai Jiaotong University(Medical Science) (曾逃方,罗旭，辛国华，等.激光微孔化猪脱细胞真皮基质的设计、制备及同步移植实验. 上海交通大学学报(医学版)),2012. 32(10): 1307-1311.

[16] JIN Shuo,WANG Bin,XIA Wei. Target detection in hyperspectral imagery based on independent component analysis with references［J］. J .Infrared Millim.Waves(金硕,王斌,夏威.基于带参考信号独立分量分析的高光谱图像目标探测.红外与毫米波学报),2015,34(2):177-183.

[17] Mohapatra S, Patra D, Satpathy S. An ensemble classifier system for early diagnosis of acute lymphoblastic leukemia in blood microscopic images［J］. Neural Computing and Applications, 2014, 24(7):1887-1904.

罗旭, 田望晓, 黄怡, 吴秀玲, 李林辉, 陈朋, 朱新国, 李庆利, 褚君浩. 基于G-SA-SVM的快速血管化鉴别方法[J]. 红外与毫米波学报, 2018, 37(1): 98. LUO Xu, TIAN Wang-Xiao, HUANG Yi, WU Xiu-Ling, LI Lin-Hui, CHEN Peng, ZHU Xin-Guo, LI Qing-Li, CHU Jun-Hao. Rapid vascularization identification using adaptive Gamma correction and support vector machine based on simulated annealing[J]. Journal of Infrared and Millimeter Waves, 2018, 37(1): 98.

基于G-SA-SVM的快速血管化鉴别方法

关于本站 Cookie 的使用提示

全站搜索

基于G-SA-SVM的快速血管化鉴别方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索