生醫電阻抗斷層掃描近年來廣泛應用在臨床呼吸相關研究，其根據胸腔中不同組織電特性，經由影像重建演算法建構出電阻係數在空間中分佈之新式醫學成像技術。其基於組織電特性量測原理，具備非侵入性和無輻射性之醫學成像技術，適合長時間連續監測且即時響應肺臟通氣狀態。
電阻抗成像是屬於高度非線性不適定逆問題，空間解析度不足是長久以來的缺陷，要重建出清晰且高品質的電阻抗斷層影像有它的挑戰性。本研究透過深度學習方法，以U-Net 為基礎並根據生醫電阻抗斷層影像的特性量身設計專為電阻抗成像所用之網路架構，訓練專化的電阻抗模型重建影像；研究中提出的半暹羅U-Net 模型其新穎網路結構分別以多重分離任務和多重損失權重手法，來達到同步學習辨識隱含在生醫電阻抗斷層影像中不同特性的阻抗變化。
透過兩階段1.)基於有限元素的仿生假體與生醫電阻抗模擬實驗，2.)人體電阻抗斷層影像資料測試模型的分割能力。以獨立的測試資料集評估訓練後的模型，平均絕對誤差以及DICE 相似係數評估模型的分割能力，同時實現經典的U-Net模型做為比較的基礎模型。基於有限元素仿生之電阻抗實驗訓練模型的結果，心臟和肺臟相關的阻抗影像分割效能相較於經典的U-Net：DICE 相似係數相對改善達11.37%以及3.2%；平均絕對誤差相對改善3.16%以及5.54%。將第一階段所訓練的模型應用於自動化分割心與肺電阻抗斷層影像之人體實驗，結果證實所提出的深度學習方法，僅透過模擬資料學習的模型，亦具備良好泛化性，實現在真實世界分割心與肺阻抗影像的能力。本研究所提出的半暹羅U-Net 模型實現生醫電阻抗斷層影像重建，提高重建影像的空間解析度，改善電阻抗斷層影像的品質，為電阻抗斷層影像長久以來空間解析度問題提供一種全新的改善方法。
半暹羅 U-Net 模型實現同步分離肺與心相關的功能性阻抗影像，所提供的訊息在呼吸相關研究中開闢新的臨床應用機會，使用電阻抗斷層掃描協助急性呼吸窘迫症候群或是其它通氣/灌流不匹配的心肺疾病患者，於呼吸治療的過程中視覺化即時監測局部肺臟通氣/灌流之阻抗變化。

Electrical impedance tomography (EIT) is widely used for bedside monitoring of lung ventilation status. Its goal is to reflect the internal conductivity changes and estimate the electrical properties of the tissues in the thorax. However, poor spatial resolution affects EIT image reconstruction to the extent that the heart and lung-related impedance images are barely distinguishable. Several studies have attempted to tackle this problem, and approaches based on decomposition of EIT images using linear transformations have been developed. Recently, U-Net has become a prominent architecture for semantic segmentation. In this paper, we propose a novel semi-Siamese U-Net specifically tailored for EIT application. It is based on the state-of-the-art U-Net, whose structure is modified and extended, forming shared encoder with parallel decoders and has multi-task weighted losses added to adapt to the individual separation tasks. The trained semi-Siamese U-Net model was evaluated with a test dataset, and the results were compared with those of the classical U-Net in terms of Dice similarity coefficient and mean absolute error.
Results showed that compared with the classical U-Net, semi-Siamese U-Net exhibited performance improvements of 11.37% and 3.2% in Dice similarity coefficient, and 3.16% and 5.54% in mean absolute error, in terms of heart and lung-impedance image separation, respectively.
EIT is a non-invasive technique that constitutes a promising tool for the real-time imaging and long-term monitoring of the ventilation distribution at bedside. However, clinical monitoring and diagnostic evaluations depend on various methods to assess ventilation-dependent parameters useful for ventilation therapy. This study developed an automatic, robust, and rapidly accessible method for lung segmentation that can be used to define appropriate regions-of-interest (ROIs) within EIT images.
Approach: To date, available methods for patients with lung defects have the disadvantage of not being able to identify lung regions because of their poor ventilation responses. Furthermore, the challenges related to the identification of lung areas in EIT images are attributed to the low spatial resolution of EIT. In this study, a U-Net-based automatic lung segmentation model is used as a postprocessor to transform the original EIT image to a lung ROI image and refine the inherent conductivity distribution of the original EIT image. It is different from conventional approaches in that the trained U-Net network can perform an automatic segmentation of conductivity changes in EIT images without requiring prior information.
Main results: The experimental design of this study was based on a finite element method phantom used to assess the feasibility and effectiveness of the proposed method, and the evaluation of the trained models on the test dataset was performed using the Dice similarity coefficient and the mean absolute error.
Significance: The use of a deep-learning-based approach attained automatic and convenient segmentation of lung ROIs into distinguishable images, which represents a direct benefit for regional lung ventilation-dependent parameter extraction and analysis. However, further investigations and validation are warranted in real human datasets with different physiology conditions with CT cross-section dataset to refine the suggested model.

[1] “Electrical Impedance Tomography - an overview | ScienceDirect Topics.” https://www.sciencedirect.com/topics/medicine-and-dentistry/electrical-impedance-tomography (accessed Feb. 17, 2021).
[2] “Electrical Impedance Tomography: The realisation of regional ventilation monitoring - Dräger - PDF Catalogs | Technical Documentation.” https://pdf.medicalexpo.com/pdf/draeger/electrical-impedance-tomography-realisation-regional-ventilation-monitoring/68268-185033.html (accessed Feb. 17, 2021).
[3] J. Canet and L. Gallart, “The Dark Side of the Lung: Unveiling Regional Lung Ventilation with Electrical Impedance Tomography,” Anesthesiology, vol. 116, no. 6, pp. 1186–1188, 2012, doi: 10.1097/ALN.0b013e318256ef0a.
[4] E. L. V. Costa et al., “Bedside estimation of recruitable alveolar collapse and hyperdistension by electrical impedance tomography,” in Applied Physiology in Intensive Care Medicine 1: Physiological Notes - Technical Notes - Seminal Studies in Intensive Care, M. R. Pinsky, L. Brochard, G. Hedenstierna, and M. Antonelli, Eds. Berlin, Heidelberg: Springer, 2012, pp. 165–170, doi: 10.1007/978-3-642-28270-6_34
[5] O. C. Radke, T. Schneider, A. R. Heller, and T. Koch, “Spontaneous Breathing during General Anesthesia Prevents the Ventral Redistribution of Ventilation as Detected by Electrical Impedance Tomography: A Randomized Trial,” Anesthesiology, vol. 116, no. 6, pp. 1227–1234, Jun. 2012, doi: 10.1097/ALN.0b013e318256ee08.
[6] C.-F. Hsu et al., “Electrical impedance tomography monitoring in acute respiratory distress syndrome patients with mechanical ventilation during prolonged positive end-expiratory pressure adjustments,” J Formos Med Assoc, vol. 115, no. 3, pp. 195–202, Mar. 2016, doi: 10.1016/j.jfma.2015.03.001.
[7] A. S. Slutsky and V. M. Ranieri, “Ventilator-Induced Lung Injury,” New England Journal of Medicine, vol. 369, no. 22, pp. 2126–2136, Nov. 2013, doi: 10.1056/NEJMra1208707.
[8] T. Luecke, J. P. Meinhardt, P. Herrmann, A. Weiss, M. Quintel, and P. Pelosi, “Oleic acid vs saline solution lung lavage-induced acute lung injury: effects on lung morphology, pressure-volume relationships, and response to positive end-expiratory pressure,” Chest, vol. 130, no. 2, pp. 392–401, Aug. 2006, doi: 10.1378/chest.130.2.392.
[9] T. Richter, R. Bergmann, G. Musch, J. Pietzsch, and T. Koch, “Reduced pulmonary blood flow in regions of injury 2 hours after acid aspiration in rats,” BMC Anesthesiol, vol. 15, p. 36, 2015, doi: 10.1186/s12871-015-0013-0.
[10] P. Pelosi and M. G. de Abreu, “Acute respiratory distress syndrome: we can’t miss regional lung perfusion!,” BMC Anesthesiol, vol. 15, Mar. 2015, doi: 10.1186/s12871-015-0014-z.
[11] The ARDS Definition Task Force, “Acute respiratory distress syndrome: The Berlin Definition.,” JAMA, vol. 307, no. 23, pp. 2526–2533, Jun. 2012, doi: 10.1001/jama.2012.5669.
[12] N. D. Ferguson et al., “The Berlin definition of ARDS: an expanded rationale, justification, and supplementary material,” Intensive Care Med, vol. 38, no. 10, pp. 1573–1582, Oct. 2012, doi: 10.1007/s00134-012-2682-1.
[13] T. J. Nuckton et al., “Pulmonary Dead-Space Fraction as a Risk Factor for Death in the Acute Respiratory Distress Syndrome,” New England Journal of Medicine, vol. 346, no. 17, pp. 1281–1286, Apr. 2002, doi: 10.1056/NEJMoa012835.
[14] J. Piiper and P. Scheid, “Model for capillary-alveolar equilibration with special reference to O2 uptake in hypoxia,” Respir Physiol, vol. 46, no. 3, pp. 193–208, Dec. 1981, doi: 10.1016/0034-5687(81)90121-3.
[15] N. C. Staub, “Alveolar-arterial oxygen tension gradient due to diffusion,” Journal of Applied Physiology, vol. 18, no. 4, pp. 673–680, Jul. 1963, doi: 10.1152/jappl.1963.18.4.673.
[16] E. Calzia and P. Radermacher, “Alveolar ventilation and pulmonary blood flow: the V(A)/Q concept,” Intensive Care Med, vol. 29, no. 8, pp. 1229–1232, Aug. 2003, doi: 10.1007/s00134-003-1835-7.
[17] D. G. Ashbaugh, D. B. Bigelow, T. L. Petty, and B. E. Levine, “Acute respiratory distress in adults,” Lancet, vol. 2, no. 7511, pp. 319–323, Aug. 1967, doi: 10.1016/s0140-6736(67)90168-7.
[18] “Ventilation with Lower Tidal Volumes as Compared with Traditional Tidal Volumes for Acute Lung Injury and the Acute Respiratory Distress Syndrome,” New England Journal of Medicine, vol. 342, no. 18, pp. 1301–1308, May 2000, doi: 10.1056/NEJM200005043421801.
[19] M. Briel et al., “Higher vs lower positive end-expiratory pressure in patients with acute lung injury and acute respiratory distress syndrome: systematic review and meta-analysis,” JAMA, vol. 303, no. 9, pp. 865–873, Mar. 2010, doi: 10.1001/jama.2010.218.
[20] S. K. Sahetya, E. C. Goligher, and R. G. Brower, “Fifty Years of Research in ARDS. Setting Positive End-Expiratory Pressure in Acute Respiratory Distress Syndrome,” Am J Respir Crit Care Med, vol. 195, no. 11, pp. 1429–1438, Jun. 2017, doi: 10.1164/rccm.201610-2035CI.
[21] L. Brochard et al., “Clinical review: Respiratory monitoring in the ICU - a consensus of 16,” Crit Care, vol. 16, no. 2, p. 219, Dec. 2012, doi: 10.1186/cc11146.
[22] D. R. Dantzker, C. J. Brook, P. Dehart, J. P. Lynch, and J. G. Weg, “Ventilation-perfusion distributions in the adult respiratory distress syndrome,” Am. Rev. Respir. Dis., vol. 120, no. 5, pp. 1039–1052, Nov. 1979, doi: 10.1164/arrd.1979.120.5.1039.
[23] M. Sarkar, N. Niranjan, and P. Banyal, “Mechanisms of hypoxemia,” Lung India, vol. 34, no. 1, pp. 47–60, 2017, doi: 10.4103/0970-2113.197116.
[24] M. Ragaller and T. Richter, “Acute lung injury and acute respiratory distress syndrome,” J Emerg Trauma Shock, vol. 3, no. 1, pp. 43–51, 2010, doi: 10.4103/0974-2700.58663.
[25] J. Petersson and R. W. Glenny, “Gas exchange and ventilation–perfusion relationships in the lung,” European Respiratory Journal, vol. 44, no. 4, pp. 1023–1041, Oct. 2014, doi: 10.1183/09031936.00037014.
[26] J. B. Borges et al., “Regional lung perfusion estimated by electrical impedance tomography in a piglet model of lung collapse,” J Appl Physiol (1985), vol. 112, no. 1, pp. 225–236, Jan. 2012, doi: 10.1152/japplphysiol.01090.2010.
[27] X. He et al., “Electrical Impedance Tomography-guided PEEP Titration in Patients Undergoing Laparoscopic Abdominal Surgery,” Medicine (Baltimore), vol. 95, no. 14, Apr. 2016, doi: 10.1097/MD.0000000000003306.
[28] M.-Y. Chang, “A Comparison of Optimal Positive End-expiratory Pressure Determination Guided by Electrical Impedance Tomography and Protective Ventilation Tool by G5(MV) in Moderate and Severe Acute Respiratory Distress Syndrome Patients,” clinicaltrials.gov, Clinical trial registration NCT03112512, Sep. 2020. Accessed: Feb. 15, 2021. [Online]. Available: https://clinicaltrials.gov/ct2/show/NCT03112512.
[29] D. T. Nguyen, C. Jin, A. Thiagalingam, and A. L. McEwan, “A review on electrical impedance tomography for pulmonary perfusion imaging,” Physiol Meas, vol. 33, no. 5, pp. 695–706, May 2012, doi: 10.1088/0967-3334/33/5/695.
[30] R. Pikkemaat and S. Leonhardt, “Separation of ventilation and perfusion related signals within EIT-data streams,” J. Phys.: Conf. Ser., vol. 224, p. 012028, Apr. 2010, doi: 10.1088/1742-6596/224/1/012028.
[31] M. Graf and T. Riedel, “Electrical impedance tomography: Amplitudes of cardiac related impedance changes in the lung are highly position dependent,” PLoS ONE, vol. 12, no. 11, p. e0188313, 2017, doi: 10.1371/journal.pone.0188313.
[32] T. Rahman, M. M. Hasan, A. Farooq, and M. Z. Uddin, “Extraction of cardiac and respiration signals in electrical impedance tomography based on independent component analysis,” Journal of Electrical Bioimpedance, vol. 4, no. 1, pp. 38–44, Oct. 2013, doi: 10.5617/jeb.553.
[33] I. Frerichs et al., “Detection of local lung air content by electrical impedance tomography compared with electron beam CT,” J Appl Physiol (1985), vol. 93, no. 2, pp. 660–666, Aug. 2002, doi: 10.1152/japplphysiol.00081.2002.
[34] I. Frerichs et al., “Regional lung perfusion as determined by electrical impedance tomography in comparison with electron beam CT imaging,” IEEE Trans Med Imaging, vol. 21, no. 6, pp. 646–652, Jun. 2002, doi: 10.1109/TMI.2002.800585.
[35] F. J. McArdle, A. J. Suggett, B. H. Brown, and D. C. Barber, “An assessment of dynamic images by applied potential tomography for monitoring pulmonary perfusion,” Clin Phys Physiol Meas, vol. 9 Suppl A, pp. 87–91, 1988, doi: 10.1088/0143-0815/9/4a/015.
[36] R. Pikkemaat and S. Leonhardt, “Separation of ventilation and perfusion related signals within EIT-data streams,” J. Phys.: Conf. Ser., vol. 224, p. 012028, Apr. 2010, doi: 10.1088/1742-6596/224/1/012028.
[37] B. M. Eyüboglu and B. H. Brown, “Methods of cardiac gating applied potential tomography,” Clin Phys Physiol Meas, vol. 9 Suppl A, pp. 43–48, 1988, doi: 10.1088/0143-0815/9/4a/008.
[38] H. J. Smit, A. Vonk-Noordegraaf, A. Boonstra, P. M. de Vries, and P. E. Postmus, “Assessment of the pulmonary volume pulse in idiopathic pulmonary arterial hypertension by means of electrical impedance tomography,” Respiration, vol. 73, no. 5, pp. 597–602, 2006, doi: 10.1159/000088694.
[39] J. M. Deibele, H. Luepschen, and S. Leonhardt, “Dynamic separation of pulmonary and cardiac changes in electrical impedance tomography,” Physiol Meas, vol. 29, no. 6, pp. S1-14, Jun. 2008, doi: 10.1088/0967-3334/29/6/S01.
[40] T. Rahman, M. M. Hasan, A. Farooq, and M. Z. Uddin, “Extraction of cardiac and respiration signals in electrical impedance tomography based on independent component analysis,” Journal of Electrical Bioimpedance, vol. 4, no. 1, pp. 38–44, Oct. 2013, doi: 10.5617/jeb.553.
[41] C. A. Grant, T. Pham, J. Hough, T. Riedel, C. Stocker, and A. Schibler, “Measurement of ventilation and cardiac related impedance changes with electrical impedance tomography,” Critical Care, vol. 15, no. 1, p. R37, Jan. 2011, doi: 10.1186/cc9985.
[42] M. Zadehkoochak, B. H. Blott, T. K. Hames, and R. F. George, “Pulmonary perfusion and ventricular ejection imaging by frequency domain filtering of EIT (electrical impedance tomography) images,” Clin Phys Physiol Meas, vol. 13 Suppl A, pp. 191–196, 1992, doi: 10.1088/0143-0815/13/a/037.
[43] A. D. Leathard, B. H. Brown, J. Campbell, F. Zhang, A. H. Morice, and D. Tayler, “A comparison of ventilatory and cardiac related changes in EIT images of normal human lungs and of lungs with pulmonary emboli,” Physiol Meas, vol. 15 Suppl 2a, pp. A137-146, May 1994, doi: 10.1088/0967-3334/15/2a/018.
[44] I. Frerichs et al., “Assessment of changes in distribution of lung perfusion by electrical impedance tomography,” Respiration, vol. 77, no. 3, pp. 282–291, 2009, doi: 10.1159/000193994.
[45] M. Graf and T. Riedel, “Electrical impedance tomography: Amplitudes of cardiac related impedance changes in the lung are highly position dependent,” PLoS ONE, vol. 12, no. 11, p. e0188313, 2017, doi: 10.1371/journal.pone.0188313.
[46] C. A. Grant, T. Pham, J. Hough, T. Riedel, C. Stocker, and A. Schibler, “Measurement of ventilation and cardiac related impedance changes with electrical impedance tomography,” Critical Care, vol. 15, no. 1, p. R37, Jan. 2011, doi: 10.1186/cc9985.
[47] J. M. Deibele, H. Luepschen, and S. Leonhardt, “Dynamic separation of pulmonary and cardiac changes in electrical impedance tomography,” Physiol Meas, vol. 29, no. 6, pp. S1-14, Jun. 2008, doi: 10.1088/0967-3334/29/6/S01.
[48] N. Kerrouche, C. N. McLeod, and W. R. Lionheart, “Time series of EIT chest images using singular value decomposition and Fourier transform,” Physiol Meas, vol. 22, no. 1, pp. 147–157, Feb. 2001, doi: 10.1088/0967-3334/22/1/318.
[49] W. Huang, Z. Shen, N. E. Huang, and Y. C. Fung, “Engineering analysis of biological variables: An example of blood pressure over 1 day,” PNAS, vol. 95, no. 9, pp. 4816–4821, Apr. 1998, doi: 10.1073/pnas.95.9.4816.
[50] W. Huang, Z. Shen, N. E. Huang, and Y. C. Fung, “Nonlinear indicial response of complex nonstationary oscillations as pulmonary hypertension responding to step hypoxia,” Proc Natl Acad Sci U S A, vol. 96, no. 5, pp. 1834–1839, Mar. 1999, doi: 10.1073/pnas.96.5.1834.
[51] D. A. T. Cummings et al., “Travelling waves in the occurrence of dengue haemorrhagic fever in Thailand,” Nature, vol. 427, no. 6972, pp. 344–347, Jan. 2004, doi: 10.1038/nature02225.
[52] N. E. Huang et al., “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,” Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, vol. 454, no. 1971, pp. 903–995, Mar. 1998, doi: 10.1098/rspa.1998.0193.
[53] M.-C. Wu and C.-K. Hu, “Empirical mode decomposition and synchrogram approach to cardiorespiratory synchronization,” Phys Rev E Stat Nonlin Soft Matter Phys, vol. 73, no. 5 Pt 1, p. 051917, May 2006, doi: 10.1103/PhysRevE.73.051917.
[54] M. Wu, Phase Statistics Approach to Time Series Analysis. 2006.
[55] A. Nait-Ali, Advanced Biosignal Processing. Springer Science & Business Media, 2009.
[56] N. E. Huang and S. S. P. Shen, Hilbert-Huang Transform and Its Applications, vol. 5. WORLD SCIENTIFIC, 2005, doi: 10.1142/5862.
[57] H. Ammari and H. Kang, Reconstruction of Small Inhomogeneities from Boundary Measurements. Berlin Heidelberg: Springer-Verlag, 2004.
[58] D. Peng, Y. Zhang, and H. Guan, “End-to-End Change Detection for High Resolution Satellite Images Using Improved UNet++,” Remote Sensing, vol. 11, no. 11, p. 1382, Jan. 2019, doi: 10.3390/rs11111382.
[59] J. Lampinen, A. Vehtari, and K. Leinonen, “Application of Bayesian neural network in electrical impedance tomography,” in IJCNN’99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339), Jul. 1999, vol. 6, pp. 3942–3947 vol.6, doi: 10.1109/IJCNN.1999.830787.
[60] S. Martin and C. T. M. Choi, “A novel post-processing scheme for two-dimensional electrical impedance tomography based on artificial neural networks,” PLOS ONE, vol. 12, no. 12, p. e0188993, Dec. 2017, doi: 10.1371/journal.pone.0188993.
[61] S. J. Hamilton and A. Hauptmann, “Deep D-Bar: Real-Time Electrical Impedance Tomography Imaging With Deep Neural Networks,” IEEE Transactions on Medical Imaging, vol. 37, no. 10, pp. 2367–2377, Oct. 2018, doi: 10.1109/TMI.2018.2828303.
[62] W. Yao, Z. Zeng, C. Lian, and H. Tang, “Pixel-wise regression using U-Net and its application on pansharpening,” Neurocomputing, vol. 312, pp. 364–371, Oct. 2018, doi: 10.1016/j.neucom.2018.05.103.
[63] V. Iglovikov and A. Shvets, “TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation,” arXiv:1801.05746 [cs], Jan. 2018, Accessed: Dec. 17, 2019. [Online]. Available: http://arxiv.org/abs/1801.05746.
[64] B. H. Menze et al., “The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS),” IEEE Trans. Med. Imaging, vol. 34, no. 10, pp. 1993–2024, 2015, doi: 10.1109/TMI.2014.2377694.
[65] Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang, “UNet++: A Nested U-Net Architecture for Medical Image Segmentation,” arXiv:1807.10165 [cs, eess, stat], Jul. 2018, Accessed: Oct. 28, 2020. [Online]. Available: http://arxiv.org/abs/1807.10165.
[66] A. A. Albishri, S. J. H. Shah, and Y. Lee, “CU-Net: Cascaded U-Net Model for Automated Liver and Lesion Segmentation and Summarization,” in 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Nov. 2019, pp. 1416–1423, doi: 10.1109/BIBM47256.2019.8983266.
[67] G. Gaál, B. Maga, and A. Lukács, “Attention U-Net Based Adversarial Architectures for Chest X-ray Lung Segmentation,” arXiv:2003.10304 [cs, eess], Mar. 2020, Accessed: Feb. 01, 2021. [Online]. Available: http://arxiv.org/abs/2003.10304.
[68] J. Andersson, H. Ahlström, and J. Kullberg, “Separation of water and fat signal in whole-body gradient echo scans using convolutional neural networks,” Magnetic Resonance in Medicine, vol. 82, no. 3, pp. 1177–1186, 2019, doi: 10.1002/mrm.27786.
[69] B. S. Lin, K. Michael, S. Kalra, and H. R. Tizhoosh, “Skin lesion segmentation: U-Nets versus clustering,” in 2017 IEEE Symposium Series on Computational Intelligence (SSCI), Nov. 2017, pp. 1–7, doi: 10.1109/SSCI.2017.8280804.
[70] J. Wang, G. Zhang, Z. He, S. Wang, and Y. Sun, “Research on Dermoscopic Segmentation based on Multi-scale Convolutional Neural Network,” Procedia Computer Science, vol. 174, pp. 443–447, Jan. 2020, doi: 10.1016/j.procs.2020.06.112.
[71] Q. Jin, Z. Meng, T. D. Pham, Q. Chen, L. Wei, and R. Su, “DUNet: A deformable network for retinal vessel segmentation,” Knowledge-Based Systems, vol. 178, pp. 149–162, 2019, doi: 10.1016/j.knosys.2019.04.025.
[72] C. Wang, Z. Zhao, Q. Ren, Y. Xu, and Y. Yu, “Dense U-net Based on Patch-Based Learning for Retinal Vessel Segmentation,” Entropy, vol. 21, no. 2, p. 168, Feb. 2019, doi: 10.3390/e21020168.
[73] Yuliang Ma, Xue Li, Xiaopeng Duan, Yun Peng, Yingchun Zhang, "Retinal Vessel Segmentation by Deep Residual Learning with Wide Activation", Computational Intelligence and Neuroscience, vol. 2020, Article ID 8822407, 11 pages, 2020. doi: 10.1155/2020/8822407
[74] Yifei Xu, Zhuming Zhou, Xiao Li, Nuo Zhang, Meizi Zhang, Pingping Wei, "FFU-Net: Feature Fusion U-Net for Lesion Segmentation of Diabetic Retinopathy", BioMed Research International, vol. 2021, Article ID 6644071, 12 pages, 2021. doi: 10.1155/2021/6644071
[75] A.-A.-Z. Imran, A. Hatamizadeh, S. P. Ananth, X. Ding, D. Terzopoulos, and N. Tajbakhsh, “Automatic Segmentation of Pulmonary Lobes Using a Progressive Dense V-Network,” arXiv:1902.06362 [cs], vol. 11045, pp. 282–290, 2018, doi: 10.1007/978-3-030-00889-5_32.
[76] U. Kamal, A. M. Rafi, R. Hoque, and M. K. Hasan, “Lung Cancer Tumor Region Segmentation Using Recurrent 3D-DenseUNet,” arXiv:1812.01951 [eess], Dec. 2018, Accessed: Aug. 01, 2020. [Online]. Available: http://arxiv.org/abs/1812.01951.
[77] C. Zheng et al., “Deep Learning-based Detection for COVID-19 from Chest CT using Weak Label,” medRxiv, p. 2020.03.12.20027185, Mar. 2020, doi: 10.1101/2020.03.12.20027185.
[78] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” arXiv:1505.04597 [cs], May 2015, Accessed: Nov. 09, 2020. [Online]. Available: http://arxiv.org/abs/1505.04597.
[79] N. Ibtehaz and M. S. Rahman, “MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation,” Neural Networks, vol. 121, pp. 74–87, 2020, doi: 10.1016/j.neunet.2019.08.025.
[80] H. Dong, G. Yang, F. Liu, Y. Mo, and Y. Guo, “Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks,” arXiv:1705.03820 [cs], Jun. 2017, Accessed: Nov. 09, 2020. [Online]. Available: http://arxiv.org/abs/1705.03820.
[81] S. Cheon, E. Yang, W. J. Lee, and J.-H. Kim, “CAI-UNet for segmentation of liver lesion in CT image,” in Medical Imaging 2020: Image Processing, Houston, United States, Mar. 2020, p. 76, doi: 10.1117/12.2549152.
[82] S. J. Hamilton, J. L. Mueller, and M. Alsaker, “Incorporating a Spatial Prior into Nonlinear D-Bar EIT Imaging for Complex Admittivities,” IEEE Transactions on Medical Imaging, vol. 36, no. 2, pp. 457–466, Feb. 2017, doi: 10.1109/TMI.2016.2613511.
[83] J. K. Seo, K. C. Kim, A. Jargal, K. Lee, and B. Harrach, “A Learning-Based Method for Solving Ill-Posed Nonlinear Inverse Problems: A Simulation Study of Lung EIT,” SIAM J. Imaging Sci., vol. 12, no. 3, pp. 1275–1295, Jan. 2019, doi: 10.1137/18M1222600.
[84] F. Milletari, N. Navab, and S.-A. Ahmadi, “V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation,” arXiv:1606.04797 [cs], Jun. 2016, Accessed: Oct. 28, 2020. [Online]. Available: http://arxiv.org/abs/1606.04797.
[85] M. Z. Alom, M. Hasan, C. Yakopcic, T. M. Taha, and V. K. Asari, “Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation,” arXiv:1802.06955 [cs], May 2018, Accessed: Oct. 26, 2020. [Online]. Available: http://arxiv.org/abs/1802.06955.
[86] Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang, “UNet++: A Nested U-Net Architecture for Medical Image Segmentation,” arXiv:1807.10165 [cs, eess, stat], Jul. 2018, Accessed: Oct. 28, 2020. [Online]. Available: http://arxiv.org/abs/1807.10165.
[87] M. Drozdzal, E. Vorontsov, G. Chartrand, S. Kadoury, and C. Pal, “The Importance of Skip Connections in Biomedical Image Segmentation,” arXiv:1608.04117 [cs], Sep. 2016, Accessed: Nov. 08, 2020. [Online]. Available: http://arxiv.org/abs/1608.04117.
[88] F. I. Diakogiannis, F. Waldner, P. Caccetta, and C. Wu, “ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 162, pp. 94–114, Apr. 2020, doi: 10.1016/j.isprsjprs.2020.01.013.
[89] D. Jha et al., “ResUNet++: An Advanced Architecture for Medical Image Segmentation,” arXiv:1911.07067 [cs, eess], Nov. 2019, Accessed: Nov. 10, 2020. [Online]. Available: http://arxiv.org/abs/1911.07067.
[90] A. Adler et al., “GREIT: a unified approach to 2D linear EIT reconstruction of lung images,” Physiol. Meas., vol. 30, no. 6, pp. S35–S55, Jun. 2009, doi: 10.1088/0967-3334/30/6/S03.
[91] A. Adler and W. R. B. Lionheart, “Uses and abuses of EIDORS: an extensible software base for EIT,” Physiol Meas, vol. 27, no. 5, pp. S25-42, May 2006, doi: 10.1088/0967-3334/27/5/S03.
[92] H. R. Carlisle, R. K. Armstrong, P. G. Davis, A. Schibler, I. Frerichs, and D. G. Tingay, “Regional distribution of blood volume within the preterm infant thorax during synchronised mechanical ventilation,” Intensive Care Med, vol. 36, no. 12, pp. 2101–2108, Dec. 2010, doi: 10.1007/s00134-010-2049-4.
[93] S. Pulletz et al., “Comparison of different methods to define regions of interest for evaluation of regional lung ventilation by EIT,” Physiol Meas, vol. 27, no. 5, pp. S115-127, May 2006, doi: 10.1088/0967-3334/27/5/S10.
[94] G. Hahn, I. Frerichs, M. Kleyer, and G. Hellige, “Local mechanics of the lung tissue determined by functional EIT,” Physiol. Meas., vol. 17, no. 4A, pp. A159–A166, Nov. 1996, doi: 10.1088/0967-3334/17/4A/020.
[95] Z. Zhao, K. Moller, D. Steinmann, and J. Guttmann, “Determination of Lung Area in EIT Images,” in 2009 3rd International Conference on Bioinformatics and Biomedical Engineering, Jun. 2009, pp. 1–4, doi: 10.1109/ICBBE.2009.5162621.
[96] P. W. Kunst et al., “Regional pressure volume curves by electrical impedance tomography in a model of acute lung injury,” Crit Care Med, vol. 28, no. 1, pp. 178–183, Jan. 2000, doi: 10.1097/00003246-200001000-00029.
[97] Z. Zhao, K. Möller, D. Steinmann, I. Frerichs, and J. Guttmann, “Evaluation of an electrical impedance tomography-based global inhomogeneity index for pulmonary ventilation distribution,” Intensive Care Med, vol. 35, no. 11, p. 1900, Aug. 2009, doi: 10.1007/s00134-009-1589-y.
[98] Z. Zhao, S. Pulletz, I. Frerichs, U. Müller-Lisse, and K. Möller, “The EIT-based global inhomogeneity index is highly correlated with regional lung opening in patients with acute respiratory distress syndrome,” BMC Res Notes, vol. 7, p. 82, Feb. 2014, doi: 10.1186/1756-0500-7-82.
[99] V. D. Gaertner et al., “Transmission of Oscillatory Volumes into the Preterm Lung during Noninvasive High-Frequency Ventilation,” Am J Respir Crit Care Med, Oct. 2020, doi: 10.1164/rccm.202007-2701OC.
[100] F. Thürk et al., “Effects of individualized electrical impedance tomography and image reconstruction settings upon the assessment of regional ventilation distribution: Comparison to 4-dimensional computed tomography in a porcine model,” PLoS One, vol. 12, no. 8, p. e0182215, 2017, doi: 10.1371/journal.pone.0182215.