Enhanced Electroacoustic Tomographywith Supervised Learning for Real-time Electroporation Monitoring

Abstract

Background: Nanosecond pulsed electric fields (nsPEF)-based electroporation is a new therapy modality potentially synergized with radiation therapy to improve treatment outcomes. To verify its treatment accuracy intraoperatively, electroacoustic tomography (EAT) has been developed to monitor in-vivo electric energy deposition by detecting ultrasound signals generated by nsPEFs in real-time. However, utility of EAT is limited by image distortions due to the limited-angle view of ultrasound transducers.

Methods: This study proposed a supervised learning-based workflow to address the ill-conditioning in EAT reconstruction. Electroacoustic signals were detected by a linear array and initially reconstructed into EAT images, which were then fed into a deep learning model for distortion correction. In this study, 56 distinct electroacoustic data sets from nsPEFs of different intensities and geometries were collected experimentally, avoiding simulation-to-real-world variations. Forty-six data were used for model training and 10 for testing. The model was trained using supervised learning, enabled by a custom rotating platform to acquire paired full-view and single-view signals for the same electric field.

Results: The proposed method considerably improved the image quality of linear array-based EAT, generating pressure maps with accurate and clear structures. Quantitatively, the enhanced single-view images achieved a low-intensity error (RMSE: 0.018), high signal-to-noise ratio (PSNR: 35.15), and high structural similarity (SSIM: 0.942) compared to the reference full-view images.

Conclusions: This study represented a pioneering stride in achieving high-quality EAT using a single linear array in an experimental environment, which improves EAT’s utility in real-time monitoring for nsPEF-based electroporation therapy.

Keywords

electroacoustic tomography / electroporation / interventional therapy / limited-angle reconstruction / supervised learning

References

[1] Barker A, Freeston I. Medical applications of electric and magnetic fields. Electron Pow. 1985;31(10):757-760.

[2] Hart FX, Palisano JR. The application of electric fields in biology and medicine. Electric Field. 2018;23:161-186.

[3] Tai G, Tai M, Zhao M. Electrically stimulated cell migration and its contribution to wound healing. Burns Trauma. 2018;6:20. Published 2018 Jul 9.

[4] Wenger C, Miranda PC, Salvador R, et al. A Review on Tumor-Treating Fields (TTFields): Clinical Implications Inferred From Computational Modeling. IEEE Rev Biomed Eng. 2018;11:195-207.

[5] Markx GH. The use of electric fields in tissue engineering: A review. Organogenesis. 2008;4(1):11-17.

[6] Weaver J, Chizmadzhev Y. Theory of electroporation: a review. Bioelectrochemistry Bioenerg. 1996;41(2):135-160.

[7] Gehl J. Electroporation: theory and methods, perspectives for drug delivery, gene therapy and research. Acta Physiol Scand. 2003;177(4):437-447.

[8] Potter H, Heller R. Transfection by Electroporation. Curr Protoc Mol Biol. 2018;121:9.3.1-9.3.13.

[9] Xin YL. Advances in the treatment of malignant tumours by electrochemical therapy (ECT). Eur J Surg Suppl. 1994;(574):31-35.

[10] Davalos RV, Mir IL, Rubinsky B. Tissue ablation with irreversible electroporation. Ann Biomed Eng. 2005;33(2):223-231.

[11] Beebe SJ, Sain NM, Ren W. Induction of Cell Death Mechanisms and Apoptosis by Nanosecond Pulsed Electric Fields (nsPEFs). Cells. 2013;2(1):136-162.

[12] Sersa G, Kranjc S, Cemazar M. Improvement of combined modality therapy with cisplatin and radiation using electroporation of tumors. Int J Radiat Oncol Biol Phys. 2000;46(4):1037-1041.

[13] Yadollahpour A, Rezaee Z, Bayati V, Tahmasebi Birgani MJ, Negad Dehbashi F. Radiotherapy Enhancement with Electroporation in Human Intestinal Colon Cancer HT-29 Cells. Asian Pac J Cancer Prev. 2018;19(5):1259-1262.

[14] Zupanic A, Kos B, Miklavcic D. Treatment planning of electroporationbasedmedical interventions: electrochemotherapy, gene electrotransfer and irreversible electroporation. Phys Med Biol. 2012;57(17):5425-5440.

[15] Granata V, de Lutio di Castelguidone E, Fusco R, et al. Irreversible electroporation of hepatocellular carcinoma: preliminary report on the diagnostic accuracy of magnetic resonance, computer tomography, and contrast-enhanced ultrasound in evaluation of the ablated area. Radiol Med. 2016;121(2):122-131.

[16] Xu Y, Sun L, Wang S, et al. Electroacoustic tomography for realtime visualization of electrical field dynamics in deep tissue during electroporation. Commun Eng. 2023;2:75.

[17] Wang S, Zarafshani A, Xiang L. Electroacoustic tomography (EAT):2D electric field reconstruction for electroporation treatment monitoring. Proc. SPIE 11598, Medical Imaging 2021: Image-Guided Procedures, Robotic Interventions, and Modeling, 1159820 (15 February 2021).

[18] Wang M, Zarafshani A, Samant P, Merrill J, Li D, Xiang L. Feasibility of Electroacoustic Tomography: A Simulation Study. IEEE Trans Ultrason Ferroelectr Freq Control. 2020;67(5):889-897.

[19] Sidky EY, Pan X. Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization. Phys Med Biol. 2008;53(17):4777-4807.

[20] Jiang Z, Yin FF, Ge Y, Ren L. Enhancing digital tomosynthesis (DTS) for lung radiotherapy guidance using patient-specific deep learning model. Phys Med Biol. 2021;66(3):035009.

[21] Graff CG, Sidky EY. Compressive sensing in medical imaging. Appl Opt. 2015;54(8):C23-C44.

[22] Chan HP, Samala RK, Hadjiiski LM, Zhou C. Deep Learning in Medical Image Analysis. Adv Exp Med Biol. 2020;1213:3-21.

[23] Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60-88.

[24] Jiang Z, Chen Y, Zhang Y, Ge Y, Yin FF, Ren L. Augmentation of CBCT Reconstructed From Under-Sampled Projections Using Deep Learning. IEEE Trans Med Imaging. 2019;38(11):2705-2715.

[25] Jiang Z, Yin FF, Ge Y, Ren L. A multi-scale framework with unsupervised joint training of convolutional neural networks for pulmonary deformable image registration. Phys Med Biol. 2020;65(1):015011.

[26] Wang R, Lei T, Cui R, Zhang B, Meng H, Nandi A. Medical image segmentation using deep learning: A survey. IET Image Processing. 2022;16(5):1243-1267.

[27] Sagheer SVM, George SN. A review on medical image denoising algorithms. Biomed Signal Proces. 2020;61:102036.

[28] Ahishakiye E, Gijzen M, Tumwiine J, Wario R, Obungoloch J. A survey on deep learning in medical image reconstruction. Intel Med. 2021;1(3):118-127.

[29] Huang Y, Preuhs A, Lauritsch G, Manhart M, Huang X, Maier A. Data consistent artifact reduction for limited angle tomography with deep learning prior. Machine Learning for Medical Image Reconstruction (MLMIR). Lect Notes Comput Sci. 2019;11905:101-112.

[30] Shen L, Zhao W, Xing L. Patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning. Nat Biomed Eng. 2019;3(11):880-888.

[31] Jiang Z, Sun L, Yao W, Wu QJ, Xiang L, Ren L. 3Din vivodose verification in prostate proton therapy with deep learning-based protonacoustic imaging. Phys Med Biol. 2022;67(21):ac9881.

[32] Jiang Z, Polf JC, Barajas CA, Gobbert MK, Ren L. A feasibility study of enhanced prompt gamma imaging for range verification in proton therapy using deep learning. Phys Med Biol. 2023;68(7):acbf9a.

[33] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI. Lect Notes Comput Sci. 2015;9351:234-241.

[34] Kingma DP. Adam: Amethod for stochastic optimization. International Conference on Learning Representations (ICLR). 2014. doi:10.48550/arXiv.1412.6980

[35] Waibel D, Gröhl J, Isensee F, Kirchner T, Maier-Hein K, Maier-Hein L. Reconstruction of initial pressure from limited view photoacoustic images using deep learning. Proc. SPIE 10494, Photons Plus Ultrasound: Imaging and Sensing 2018, 104942S (19 February 2018);

[36] Gröhl J, Schellenberg M, Dreher K, Maier-Hein L. Deep learning for biomedical photoacoustic imaging: A review. Photoacoustics. 2021;22:100241. Published 2021 Feb 2.

[37] Guan S, Khan AA, Sikdar S, Chitnis PV. Limited-View and Sparse Photoacoustic Tomography for Neuroimaging with Deep Learning. Sci Rep. 2020;10(1):8510.

RIGHTS & PERMISSIONS

2024 The Author(s). Precision Radiation Oncology published by John Wiley & Sons Australia, Ltd on behalf of Shandong Cancer Hospital & Institute.