Deep learning correction for image reconstruction in electrical impedance tomography using UNet model

• Autorzy: Maciura Łukasz , Rymarczyk Tomasz , Wójcik Dariusz , Gauda Konrad , Kowalski Marcin

Identyfikatory

DOI

10.15199/48.2023.06.27

Warianty tytułu

PL

Poprawa rekonstrukcji tomografii impedancyjnej oparta o głębokie uczenie przy użyciu modelu UNet

• Języki publikacji: EN

Abstrakty

EN

This article was inspired by a similar Deep DBar algorithm, where a modified UNet convolutional model was used to correct the output of the DBar algorithm using the UNet model. However, instead of the DBar algorithm, another deterministic electrical impedance tomography reconstruction algorithm was used in this solution. The modified UNet model was used to successfully correct the initial reconstructions, which were computed using Kotre regularities using pseudo-inversion of the sensitivity matrix.

PL

Ten artykuł został inspirowany podobnym algorytmem Deep DBar, w którym zmodyfikowany model splotowy UNet został użyty do skorygowania danych wyjściowych algorytmu DBar przy użyciu modelu UNet. Jednak zamiast algorytmu DBar w tym rozwiązaniu zastosowano inny deterministyczny algorytm rekonstrukcji elektrycznej tomografii impedancyjnej. Zmodyfikowany model UNet został wykorzystany do skutecznej korekcji wstępnych rekonstrukcji, które zostały obliczone przy użyciu regularności Kotrego z wykorzystaniem pseudo-inwersji macierzy czułości.

Słowa kluczowe

EN

electrical impedance tomography; convolutional neural network; UNet

PL

elektryczna tomografia impedancyjna; sieć konwolucyjna; UNet

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2023
• Tom: R. 99, nr 6
• Strony: 134--137
• Opis fizyczny: Bibliogr. 27 poz., rys., tab.

Twórcy

autor

Maciura Łukasz

• Netrix S.A., Research & Development Centre, Lublin, Poland

• https://orcid.org/0000-0001-8657-3472

autor

Rymarczyk Tomasz

• Netrix S.A., Research & Development Centre, Lublin, Poland
• WSEI University, Lublin, Poland

• https://orcid.org/0000-0002-4200-3432

autor

Wójcik Dariusz

• Netrix S.A., Research & Development Centre, Lublin, Poland
• WSEI University, Lublin, Poland

• https://orcid.org/0000-0002-3524-9151

autor

Gauda Konrad

• WSEI University, Lublin, Poland

• https://orcid.org/0000-0002-7300-6978

autor

Kowalski Marcin

• WSEI University, Lublin, Poland

• https://orcid.org/0000-0002-1644-0612

Bibliografia

• [1] Rymarczyk T., Niderla K. Kozłowski E. Król K., Wyrwisz J. Skrzypek-Ahmed S., Gołąbek P., Logistic Regression with Wave Preprocessing to Solve Inverse Problem in Industrial Tomography for Technological Process Control, Energies, 14 (2021), No. 23, 8116.
• [2] Rymarczyk T., Kłosowski G., Application of neural reconstruction of tomographic images in the problem of reliability of flood protection facilities, Eksploatacja i Niezawodnosc – Maintenance and Reliability, 20 (2018); No. 3, 425–434
• [3] Kłosowski G., Rymarczyk T., Cieplak T., Niderla K., Skowron Ł., Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid Tomography, Sensors, 20 (2020), No. 11, 3324
• [4] Koulountzios P., Rymarczyk T., Soleimani M., A triple-modality ultrasound computed tomography based on fullwaveform data for industrial processes, IEEE Sensors Journal, 21 (2021), No. 18, 20896-20909
• [5] Rymarczyk T., Kłosowski G., Hoła A., Sikora J., Wołowiec T., Tchórzewski P., Skowron S., Comparison of Machine Learning Methods in Electrical Tomography for Detecting Moisture in Building Walls, Energies, 14 (2021), No. 10, 2777
• [6] Kłosowski G., Hoła A., Rymarczyk T., Skowron Ł., Wołowiec T., Kowalski M., The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography, Energies, 14 (2021), No. 22, 7617
• [7] Kłosowski G., Rymarczyk T., Kania K., Świć A., Cieplak T., Maintenance of industrial reactors supported by deep learning driven ultrasound tomography, Eksploatacja i Niezawodnosc – Maintenance and Reliability; 22 (2020), No 1, 138–147
• [8] Styła, M., Adamkiewicz, P., Optimisation of commercial building management processes using user behaviour analysis systems supported by computational intelligence and RTI, Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 12 (2022), No 1, 28-35
• [9] Łukiański, M., & Wajman, R., The diagnostic of two phase separation process using digital image segmentation algorithms, Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska, (2020),. 10(3), 5-8
• [10] Korzeniewska, E., Sekulska-Nalewajko, J., Gocawski, J., Drożdż, T., Kiebasa, P., Analysis of changes in fruit tissue after the pulsed electric field treatment using optical coherence tomography, EPJ Applied Physics, 91 (2020), No. 3, 30902
• [11] Korzeniewska, E., Krawczyk, A., Mróz, J., Wyszyńska, E., Zawiślak, R., Applications of smart textiles in post-stroke rehabilitation, Sensors, 20 (2020), No. 8, 2370.
• [12] Rybak G., Strzecha K., Short-Time Fourier Transform Based on Metaprogramming and the Stockham Optimization Method, Sensors, 21 (2021), No. 12, 4123
• [13] Mosorov V.; Rybak G., Sankowski D., Plug Regime Flow Velocity Measurement Problem Based on Correlability Notion and Twin Plane Electrical Capacitance Tomography: Use Case, Sensors, 21 (2021), No. 6, 2189
• [14] Dušek J., Hladký D., Mikulka J., Electrical Impedance Tomography Methods and Algorithms Processed with a GPU, In PIERS Proceedings, (2017), 1710-1714
• [15] Shi, XW; Tan, C; Dong, F; dos Santos, EN; da Silva, MJ, Conductance Sensors for Multiphase Flow Measurement: A Review, IEEE Sensors Journal, 21 (2021), No. 11, 12913-12925
• [16] Hamilton S. J., Hauptmann A., Deep D-bar: Real time Electrical Impedance Tomography Imaging with Deep Neural Networks, IEEE Transactions on Medical Imaging, 37 (2018), No. 10, 2367-2377
• [17] Klosowski G., Rymarczyk T., Using neural networks and deep learning algorithms in electrical impedance tomography, Informatyka Automatyka Pomiary w Gospodarce I Ochronie Środowiska, 7 (2017), No. 3, 99-102
• [18] Malone E., Gustavo Sato dos Santos, David Holder and Simon Arridge, A Reconstructio Classification Method for Multifrequency Electrical Impedance Tomography, IEEE Transactions on Medical Imaging, 34 (2015), No 7, 1486-1497
• [19] Khan T. A., Ling S.H., Review on Electrical Impedance Tomography: Artificial Intelligence Methods and its Applications, Algorithms, 12 (2019), No. 5, 88
• [20] Seo J. K., Kim K.C., Jargal A., Lee K., Harrach B., Learning-Based Method for Solving Ill-Posed Nonlinear Inverse Problems: A Simulation Study of Lung EIT, SIAM J. Imaging Sci., 12 (2019), No. 3, 1275-1295
• [21] Fernandez-Fuentes X., Mera D., Gomez A., Vidal-Franco I., Towards a Fast and Accurate EIT Inverse Problem Solver: A Machine Learning Approach, Electronics, 7 (2018), No. 12, 422
• [22] Li X., Lu Y., Wang J., Dang X., Wang Q., Duan X., An image reconstruction framework based on deep neural network for electrical impedance tomography, IEEE International Conference on Image Processing (ICIP), 2017, 3585–3589
• [23] Li. X., Zhou Y., Wang Y., Wang Q., Lu Y., Duan X., Sun Y., Zhang J., Liu Z., A novel deep neural network method for electrical impedance tomography, Transactions of the Institute of Measurement and Control, 41 (2019), No. 14, https://doi.org/10.1177/0142331219845037
• [24] Hamilton S. J., Mueller J. L., Santos T. R., Robust computation in 2D absolute EIT (a-EIT) using D-bar methods with the' exp' approximation, Physiological Measurement, 39 (2018), No. 6, 064005
• [25] Kotre C. J., A sensitivity coefficient method for the reconstruction of electrical impedance tomograms, Clin Phys Physion Meas., 10 (1989), No. 3, 275-81
• [26] Ronneberger O., Fischer P., Brox T., U-Net: Convolutional Networks for Biomedical Image Segmentation, Medical Image Computing and Computer – Assisted Intervention, 9351 (2015), 234-241
• [27] Aziz Taha A., Hanbury A., Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool, BMC Medical Imaging, 15 (2015), No. 29, 1-2