-
基于电阻抗成像技术和生物阻抗谱技术, 提出一种面向生物组织检测的生物阻抗谱成像方法. 该方法将目标区域可视化并精准识别目标种类, 可用于肺癌早期检测, 协助临床医生对早期肺癌进行精准检测, 提高早期肺癌的治愈率. 本文通过数值仿真的方法验证生物阻抗谱成像方法在肺癌早期检测中的可行性和有效性, 仿真结果表明: 1) 生物阻抗谱成像方法可以实现早期肺癌区域的可视化, 并精确判别出早期肺癌种类; 2) 生物阻抗谱成像方法中阻抗谱的最佳采集模式是4次循环采集, 最佳分类器是Linear-SVM, 5折交叉验证的平均分类准确率可以达到99.9%. 为了验证仿真结果, 本文选取3种具有不同电学特性的生物组织模拟癌变区域进行了检测. 实验结果表明该方法可以对生物组织区域可视化, 并判别出生物组织的种类. 该方法可以兼顾电阻抗成像和生物阻抗谱方法的优点, 有望用于肺癌早期检测.A bioimpedance spectroscopic imaging method for detecting the biological tissue based on electrical impedance tomography (EIT) and bioimpedance spectroscopy (BIS) is proposed. This method visualizes the target area and accurately recognizes the target type, which can be used for detecting the early lung cancer, assist clinicians in accurately detecting the early lung cancer, and improving the cure rate of early lung cancer. In this paper the bioimpedance spectroscopic imaging method is verified to be feasible and effective in detecting the early lung cancer through numerical simulation. The simulation results show that 1) the bioimpedance spectroscopic imaging method can realize the visualization of the early lung cancer area and accurately distinguish the type of early lung cancer, and 2) the optimal number of acquisitions of impedance spectroscopy is 4, and the best classifier is Linear-SVM, and the average classification accuracy of 5-fold cross-validation can reach 99.9%. In order to verify the simulation results, three biological tissues with different electrical characteristics are selected to simulate cancerous regions used for detection. The experimental results show that the method can visualize the biological tissue area and distinguish the type of biological tissue. This method can integrate the advantages of electrical impedance imaging and bioimpedance spectroscopy, and is very promising way of detecting early lung cancer.
-
Keywords:
- bioimpedance spectroscopic tomography /
- bioelectrical impedance spectroscopy /
- electrical impedance tomography /
- early detection of lung cancer
[1] Forman D, Ferlay J, Jemal A, Bray F, Ward E, Center M 2015 CA-Cancer J. Clin. 65 87
Google Scholar
[2] Ferlay J, Colombet M, Soerjomataram I, et al. 2018 Eur. J. Cancer 103 356
Google Scholar
[3] Chen W Q, Zheng R S, Baade P D, Zhang S W, Yu X Q 2016 CA-CANCER J CLIN 66 115
Google Scholar
[4] Blankman P, Hasan D, Mourik M, Gommers D 2013 Intens. Care Med. 39 1057
Google Scholar
[5] Rhee C K, Chau N Q, Yunus F, Matsunaga K, Perng D 2019 Respirology 24 1018
Google Scholar
[6] Hao Z H, Cui Z Q, Yue S H, Wang H X 2018 Rev. Sci. Instrum. 89 064702
Google Scholar
[7] Victorino J, Borges J, Okamoto V, Matos G, Tucci M, Caramez M, Tanaka H 2004 Am. J. Resp. Crit. Care 169 791
Google Scholar
[8] Sun B, Yue S, Hao Z, et al. 2019 IEEE Sens. J. 19 3049
Google Scholar
[9] Gao J, Yue S, Chen J, Wang H 2014 Bio-med. Mater. Eng. 24 2229
Google Scholar
[10] 叶明, 李晓丞, 刘凯, 韩伟, 姚佳烽 2021 仪器仪表学报 42 235
Google Scholar
Ye M, Li X C, Liu K, Han W, Yao J F 2021 Chin. J. Sci. Instrum. 42 235
Google Scholar
[11] Wu Y, Chen B, Liu K, Zhu C J, Pan H P, Jia J B, Wu H T, Yao J F 2021 IEEE Sens. J. 21 9277
Google Scholar
[12] Wang L, Hu S, Liu K, Chen B, Wu H, Jia J, Yao J 2020 Rev. Sci. Instrum. 91 124104
Google Scholar
[13] 姚佳烽, 胡松佩, 杨璐, 吴阳, 韩伟, 刘凯 2021 70 158704
Google Scholar
Yao J, Hu S, Yang L, Wu Y, Han W, Liu K 2021 Acta Phys. Sin. 70 158704
Google Scholar
[14] Lu L, Hamzaoui L, Brown B H, Rigaud B, Smallwood R, Barber D, Morucci J 1996 Med. Biol. Eng. Comput. 34 122
Google Scholar
[15] Mahdavi R, Hosseinpour P, Abbasvandi F, Mehrvarz S, Abdolahad M 2020 Biosens. Bioelectron. 165 112421
Google Scholar
[16] Wang Y R, Yue S H 2018 Ieee 13th World Congress on Intelligent Control and Automation (WCICA) Changsha, PEOPLESR CHINA, July 04–08, 2018 pp341–346
[17] 陈晓艳, 赵秋红 2014 天津科技大学学报 29 50
Google Scholar
Chen X, Zhao Q 2014 J. Tianjin Univ. Sci. Tech. 29 50
Google Scholar
[18] Gabriel C, Gabriel S, Corthout E 1996 Phys. Med. Biol. 41 2231
Google Scholar
[19] Guardo R, Boulay C 1991 IEEE Trans. Bio-med. Eng. 38 617
Google Scholar
[20] 姚佳烽, 万建芬, 杨璐, 刘凯, 陈柏, 吴洪涛 2020 69 163301
Google Scholar
Yao J F, Wan J F, Yang L, Liu K, Chen B, Wu H T 2020 Acta Phys. Sin. 69 163301
Google Scholar
[21] Manavalan B, Shin T H, Lee G 2018 Front. Microbiol. 9 476
Google Scholar
[22] Chan C W, Paelinckx D 2008 Remote Sens. Environ. 112 2999
Google Scholar
[23] Fan M, Zheng B, Li L 2015 J. Bioinf. Comput. Biol. 13 1550022
Google Scholar
-
图 3 BIST仿真结果 (a) 肺癌Nyquist图; (b)模式识别分类准确率
Fig. 3. BIST simulation results: (a) Nyquist diagram of lung cancer; (b) pattern recognition classification accuracy.
表 1 相关生物组织电学参数
Table 1. Electrical parameters of the related biological tissue.
频率f/kHz 1 10 200 400 4000 心脏 电导率 σ/(S·m–1) 0.1036 0.1542 0.2382 0.2685 0.4324 相对介电常数ε/103 352.9 70.05 6.001 3.788 0.594 肺 电导率 σ/(S·m–1) 0.2157 0.2429 0.2835 0.3000 0.3983 相对介电常数 ε/103 252.1 34.04 3.280 2.161 0.3613 其它 电导率 σ/(S·m–1) 0.2216 0.2352 0.2642 0.2935 0.3960 相对介电常数 ε/103 298.0 17.63 4.271 2.906 0.2630 
下载: 导出CSV
-
[1] Forman D, Ferlay J, Jemal A, Bray F, Ward E, Center M 2015 CA-Cancer J. Clin. 65 87
Google Scholar
[2] Ferlay J, Colombet M, Soerjomataram I, et al. 2018 Eur. J. Cancer 103 356
Google Scholar
[3] Chen W Q, Zheng R S, Baade P D, Zhang S W, Yu X Q 2016 CA-CANCER J CLIN 66 115
Google Scholar
[4] Blankman P, Hasan D, Mourik M, Gommers D 2013 Intens. Care Med. 39 1057
Google Scholar
[5] Rhee C K, Chau N Q, Yunus F, Matsunaga K, Perng D 2019 Respirology 24 1018
Google Scholar
[6] Hao Z H, Cui Z Q, Yue S H, Wang H X 2018 Rev. Sci. Instrum. 89 064702
Google Scholar
[7] Victorino J, Borges J, Okamoto V, Matos G, Tucci M, Caramez M, Tanaka H 2004 Am. J. Resp. Crit. Care 169 791
Google Scholar
[8] Sun B, Yue S, Hao Z, et al. 2019 IEEE Sens. J. 19 3049
Google Scholar
[9] Gao J, Yue S, Chen J, Wang H 2014 Bio-med. Mater. Eng. 24 2229
Google Scholar
[10] 叶明, 李晓丞, 刘凯, 韩伟, 姚佳烽 2021 仪器仪表学报 42 235
Google Scholar
Ye M, Li X C, Liu K, Han W, Yao J F 2021 Chin. J. Sci. Instrum. 42 235
Google Scholar
[11] Wu Y, Chen B, Liu K, Zhu C J, Pan H P, Jia J B, Wu H T, Yao J F 2021 IEEE Sens. J. 21 9277
Google Scholar
[12] Wang L, Hu S, Liu K, Chen B, Wu H, Jia J, Yao J 2020 Rev. Sci. Instrum. 91 124104
Google Scholar
[13] 姚佳烽, 胡松佩, 杨璐, 吴阳, 韩伟, 刘凯 2021 70 158704
Google Scholar
Yao J, Hu S, Yang L, Wu Y, Han W, Liu K 2021 Acta Phys. Sin. 70 158704
Google Scholar
[14] Lu L, Hamzaoui L, Brown B H, Rigaud B, Smallwood R, Barber D, Morucci J 1996 Med. Biol. Eng. Comput. 34 122
Google Scholar
[15] Mahdavi R, Hosseinpour P, Abbasvandi F, Mehrvarz S, Abdolahad M 2020 Biosens. Bioelectron. 165 112421
Google Scholar
[16] Wang Y R, Yue S H 2018 Ieee 13th World Congress on Intelligent Control and Automation (WCICA) Changsha, PEOPLESR CHINA, July 04–08, 2018 pp341–346
[17] 陈晓艳, 赵秋红 2014 天津科技大学学报 29 50
Google Scholar
Chen X, Zhao Q 2014 J. Tianjin Univ. Sci. Tech. 29 50
Google Scholar
[18] Gabriel C, Gabriel S, Corthout E 1996 Phys. Med. Biol. 41 2231
Google Scholar
[19] Guardo R, Boulay C 1991 IEEE Trans. Bio-med. Eng. 38 617
Google Scholar
[20] 姚佳烽, 万建芬, 杨璐, 刘凯, 陈柏, 吴洪涛 2020 69 163301
Google Scholar
Yao J F, Wan J F, Yang L, Liu K, Chen B, Wu H T 2020 Acta Phys. Sin. 69 163301
Google Scholar
[21] Manavalan B, Shin T H, Lee G 2018 Front. Microbiol. 9 476
Google Scholar
[22] Chan C W, Paelinckx D 2008 Remote Sens. Environ. 112 2999
Google Scholar
[23] Fan M, Zheng B, Li L 2015 J. Bioinf. Comput. Biol. 13 1550022
Google Scholar
下载:
计量
- 文章访问数: 5520
- PDF下载量: 119
- 被引次数: 0
