{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:48:42Z","timestamp":1780512522583,"version":"3.54.1"},"reference-count":52,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T00:00:00Z","timestamp":1698364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"INOVAIT (funding from the SIF program from the government of Canada)"},{"name":"Arrayus technologies"},{"name":"Temerty Chair in Focused Ultrasound Research at Sunnybrook Health Sciences Centre"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Convolutional neural networks (CNNs), initially developed for image processing applications, have recently received significant attention within the field of medical ultrasound imaging. In this study, passive cavitation imaging\/mapping (PCI\/PAM), which is used to map cavitation sources based on the correlation of signals across an array of receivers, is evaluated. Traditional reconstruction techniques in PCI, such as delay-and-sum, yield high spatial resolution at the cost of a substantial computational time. This results from the resource-intensive process of determining sensor weights for individual pixels in these methodologies. Consequently, the use of conventional algorithms for image reconstruction does not meet the speed requirements that are essential for real-time monitoring. Here, we show that a three-dimensional (3D) convolutional network can learn the image reconstruction algorithm for a 16\u00d716 element matrix probe with a receive frequency ranging from 256 kHz up to 1.0 MHz. The network was trained and evaluated using simulated data representing point sources, resulting in the successful reconstruction of volumetric images with high sensitivity, especially for single isolated sources (100% in the test set). As the number of simultaneous sources increased, the network\u2019s ability to detect weaker intensity sources diminished, although it always correctly identified the main lobe. Notably, however, network inference was remarkably fast, completing the task in approximately 178 s for a dataset comprising 650 frames of 413 volume images with signal duration of 20\u03bcs. This processing speed is roughly thirty times faster than a parallelized implementation of the traditional time exposure acoustics algorithm on the same GPU device. This would open a new door for PCI application in the real-time monitoring of ultrasound ablation.<\/jats:p>","DOI":"10.3390\/s23218760","type":"journal-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T11:50:18Z","timestamp":1698407418000},"page":"8760","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Convolutional Neural Network for Beamforming and Image Reconstruction in Passive Cavitation Imaging"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2309-7135","authenticated-orcid":false,"given":"Hossein J.","family":"Sharahi","sequence":"first","affiliation":[{"name":"Physical Sciences Platform, Sunnybrook Research Institute, Toronto, ON M4N 3M5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher N.","family":"Acconcia","sequence":"additional","affiliation":[{"name":"Physical Sciences Platform, Sunnybrook Research Institute, Toronto, ON M4N 3M5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Li","sequence":"additional","affiliation":[{"name":"Physical Sciences Platform, Sunnybrook Research Institute, Toronto, ON M4N 3M5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne","family":"Martel","sequence":"additional","affiliation":[{"name":"Physical Sciences Platform, Sunnybrook Research Institute, Toronto, ON M4N 3M5, Canada"},{"name":"Department of Medical Biophysics, University of Toronto, Toronto, ON M5G 1L7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6219-2982","authenticated-orcid":false,"given":"Kullervo","family":"Hynynen","sequence":"additional","affiliation":[{"name":"Physical Sciences Platform, Sunnybrook Research Institute, Toronto, ON M4N 3M5, Canada"},{"name":"Department of Medical Biophysics, University of Toronto, Toronto, ON M5G 1L7, Canada"},{"name":"Institute of Biomedical Engineering, University of Toronto, Toronto, ON M5S 3G9, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1109\/TMI.2019.2941271","article-title":"Deep unfolded robust PCA with application to clutter suppression in ultrasound","volume":"39","author":"Solomon","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_2","first-page":"829","article-title":"Super-resolution ultrasound localization microscopy through deep learning","volume":"40","author":"Solomon","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1820","DOI":"10.1109\/TUFFC.2020.2988164","article-title":"Deep learning of spatiotemporal filtering for fast super-resolution ultrasound imaging","volume":"67","author":"Brown","year":"2020","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yun, C., Eom, B., Park, S., Kim, C., Kim, D., Jabeen, F., Kim, W.H., Kim, H.J., and Kim, J. (2023). A Study on the Effectiveness of Deep Learning-Based Anomaly Detection Methods for Breast Ultrasonography. Sensors, 23.","DOI":"10.3390\/s23052864"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Simson, W., Paschali, M., Navab, N., and Zahnd, G. (2018, January 22\u201325). Deep learning beamforming for sub-sampled ultrasound data. Proceedings of the 2018 IEEE International Ultrasonics Symposium (IUS), Kobe, Japan.","DOI":"10.1109\/ULTSYM.2018.8579818"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"30","DOI":"10.34133\/bmef.0030","article-title":"Transcranial Acoustic Metamaterial Parameters Inverse Designed by Neural Networks","volume":"4","author":"Yang","year":"2023","journal-title":"BMEF (BME Front.)"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Du, B., Wang, J., Zheng, H., Xiao, C., Fang, S., Lu, M., and Mao, R. (2020). A novel transcranial ultrasound imaging method with diverging wave transmission and deep learning approach. Comput. Methods Programs Biomed., 186.","DOI":"10.1016\/j.cmpb.2019.105308"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Luijten, B., Cohen, R., de Bruijn, F.J., Schmeitz, H.A., Mischi, M., Eldar, Y.C., and van Sloun, R.J. (2019, January 12\u201317). Deep learning for fast adaptive beamforming. Proceedings of the ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8683478"},{"key":"ref_9","unstructured":"Khan, S., Huh, J., and Ye, J.C. (2019). Universal deep beamformer for variable rate ultrasound imaging. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"106069","DOI":"10.1016\/j.ultras.2020.106069","article-title":"A unified deep network for beamforming and speckle reduction in plane wave imaging: A simulation study","volume":"103","author":"Mor","year":"2020","journal-title":"Ultrasonics"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Nair, A.A., Tran, T.D., Reiter, A., and Bell, M.A.L. (2019, January 20\u201322). A generative adversarial neural network for beamforming ultrasound images: Invited presentation. Proceedings of the 2019 53rd Annual Conference on Information Sciences and Systems (CISS), Baltimore, MD, USA.","DOI":"10.1109\/CISS.2019.8692835"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.1007\/s11548-020-02197-w","article-title":"Deep learning-based reconstruction of ultrasound images from raw channel data","volume":"15","author":"Strohm","year":"2020","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref_13","unstructured":"Anas, E.M.A., Zhang, H.K., Audigier, C., and Boctor, E.M. (2018). Simulation, Image Processing, and Ultrasound Systems for Assisted Diagnosis and Navigation, Springer."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"106778","DOI":"10.1016\/j.ultras.2022.106778","article-title":"Deep reconstruction of high-quality ultrasound images from raw plane-wave data: A simulation and in vivo study","volume":"125","author":"Goudarzi","year":"2022","journal-title":"Ultrasonics"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3466","DOI":"10.1109\/TUFFC.2021.3094849","article-title":"Deep learning for ultrasound image formation: CUBDL evaluation framework and open datasets","volume":"68","author":"Hyun","year":"2021","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"102891","DOI":"10.1016\/j.ndteint.2023.102891","article-title":"Ultrasonic adaptive plane wave high-resolution imaging based on convolutional neural network","volume":"138","author":"Zhang","year":"2023","journal-title":"NDT E Int."},{"key":"ref_17","unstructured":"Sharifzadeh, M., Goudarzi, S., Tang, A., Benali, H., and Rivaz, H. (2023). Phase Aberration Correction: A Deep Learning-Based Aberration to Aberration Approach. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3079","DOI":"10.1109\/TMI.2020.2986762","article-title":"Nondestructive detection of targeted microbubbles using dual-mode data and deep learning for real-time ultrasound molecular imaging","volume":"39","author":"Hyun","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"898","DOI":"10.1109\/TUFFC.2019.2903795","article-title":"Beamforming and speckle reduction using neural networks","volume":"66","author":"Hyun","year":"2019","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1312","DOI":"10.1109\/TUFFC.2022.3152225","article-title":"Deep learning-based microbubble localization for ultrasound localization microscopy","volume":"69","author":"Chen","year":"2022","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2374","DOI":"10.1109\/TMI.2023.3251197","article-title":"Localization free super-resolution microbubble velocimetry using a long short-term memory neural network","volume":"42","author":"Chen","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wang, R., and Lee, W.N. (2022, January 10\u201313). A general deep learning model for ultrasound localization microscopy. Proceedings of the 2022 IEEE International Ultrasonics Symposium (IUS), Venice, Italy.","DOI":"10.1109\/IUS54386.2022.9958291"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2649","DOI":"10.1109\/TUFFC.2020.2964698","article-title":"A deep learning approach to photoacoustic wavefront localization in deep-tissue medium","volume":"67","author":"Johnstonbaugh","year":"2020","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1130","DOI":"10.1038\/s42256-023-00724-3","article-title":"A deep neural network for real-time optoacoustic image reconstruction with adjustable speed of sound","volume":"5","author":"Dehner","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Zhu, H., and Cai, X. (2022, January 10\u201313). A switchable deep beamformer for passive acoustic mapping. Proceedings of the 2022 IEEE International Ultrasonics Symposium (IUS), Venice, Italy.","DOI":"10.1109\/IUS54386.2022.9958130"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Tracey, B., Aeron, S., Miller, E., Sun, T., McDannold, N., and Murphy, J. (2019, January 19\u201321). Artifact suppression for passive cavitation imaging using U-Net CNNs with uncertainty quantification. Proceedings of the 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP), Wuxi, China.","DOI":"10.1109\/SIPROCESS.2019.8868593"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1109\/36.843027","article-title":"Time exposure acoustics","volume":"38","author":"Norton","year":"2000","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Goudarzi, S., Asif, A., and Rivaz, H. (2021). Plane-wave ultrasound beamforming through independent component analysis. Comput. Methods Programs Biomed., 203.","DOI":"10.1016\/j.cmpb.2021.106036"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2909","DOI":"10.7150\/thno.24911","article-title":"Three-dimensional transcranial microbubble imaging for guiding volumetric ultrasound-mediated blood\u2013brain barrier opening","volume":"8","author":"Jones","year":"2018","journal-title":"Theranostics"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1148\/radiol.2202001804","article-title":"Noninvasive MR imaging\u2013guided focal opening of the blood\u2013brain barrier in rabbits","volume":"220","author":"Hynynen","year":"2001","journal-title":"Radiology"},{"key":"ref_31","unstructured":"Jones, R.M. (2018). Transcranial Acoustic Imaging for Guiding Cavitation-Mediated Ultrasonic Brain Therapy. [Ph.D. Thesis, University of Toronto (Canada)]."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Lin, Y., O\u2019Reilly, M.A., and Hynynen, K. (2023). A PVDF Receiver for Acoustic Monitoring of Microbubble-Mediated Ultrasound Brain Therapy. Sensors, 23.","DOI":"10.3390\/s23031369"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1121\/1.401891","article-title":"Acoustic microcavitation: Its active and passive acoustic detection","volume":"90","author":"Madanshetty","year":"1991","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Pajek, D., and Hynynen, K. (2012). The design of a focused ultrasound transducer array for the treatment of stroke: A simulation study. Phys. Med. Biol., 57.","DOI":"10.1088\/0031-9155\/57\/15\/4951"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.1121\/1.424383","article-title":"Focusing of therapeutic ultrasound through a human skull: A numerical study","volume":"104","author":"Sun","year":"1998","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Clement, G.T., and Hynynen, K. (2002). A non-invasive method for focusing ultrasound through the human skull. Phys. Med. Biol., 47.","DOI":"10.1088\/0031-9155\/47\/8\/301"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1693","DOI":"10.1109\/TBME.2004.831516","article-title":"Patterns of thermal deposition in the skull during transcranial focused ultrasound surgery","volume":"51","author":"Connor","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1109\/TBME.2019.2912146","article-title":"A spine-specific phased array for transvertebral ultrasound therapy: Design and simulation","volume":"67","author":"Xu","year":"2019","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Pichardo, S., and Hynynen, K. (2007). Treatment of near-skull brain tissue with a focused device using shear-mode conversion: A numerical study. Phys. Med. Biol., 52.","DOI":"10.1088\/0031-9155\/52\/24\/008"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1121\/1.1906542","article-title":"Theory of focusing radiators","volume":"21","year":"1949","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2840","DOI":"10.1121\/1.2188667","article-title":"Passive imaging of underground acoustic sources","volume":"119","author":"Norton","year":"2006","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/53.665","article-title":"Beamforming: A versatile approach to spatial filtering","volume":"5","author":"Buckley","year":"1988","journal-title":"IEEE ASSP Mag."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/79.526899","article-title":"Two decades of array signal processing research: The parametric approach","volume":"13","author":"Krim","year":"1996","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/TBME.2009.2026907","article-title":"Passive spatial mapping of inertial cavitation during HIFU exposure","volume":"57","author":"Gyongy","year":"2009","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Duck, F.A. (1990). Physical Properties of Tissue: A Comprehensive Reference Book, Academic Press.","DOI":"10.1016\/B978-0-12-222800-1.50006-1"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Acconcia, C.N., Jones, R.M., Goertz, D.E., O\u2019Reilly, M.A., and Hynynen, K. (2017). Megahertz rate, volumetric imaging of bubble clouds in sonothrombolysis using a sparse hemispherical receiver array. Phys. Med. Biol., 62.","DOI":"10.1088\/1361-6560\/aa84d7"},{"key":"ref_47","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"4385","DOI":"10.1118\/1.4922677","article-title":"Experimental demonstration of passive acoustic imaging in the human skull cavity using CT-based aberration corrections","volume":"42","author":"Jones","year":"2015","journal-title":"Med. Phys."},{"key":"ref_49","unstructured":"Dai, E., Zhao, T., Zhu, H., Xu, J., Guo, Z., Liu, H., Tang, J., and Wang, S. (2022). A comprehensive survey on trustworthy graph neural networks: Privacy, robustness, fairness, and explainability. arXiv."},{"key":"ref_50","unstructured":"Wu, L., Cui, P., Pei, J., Zhao, L., and Guo, X. (2022). KDD \u201922, Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, 14\u201318 August 2022, Association for Computing Machinery."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"8925","DOI":"10.1016\/j.jfranklin.2020.04.033","article-title":"Non-iterative and fast deep learning: Multilayer extreme learning machines","volume":"357","author":"Zhang","year":"2020","journal-title":"J. Frankl. Inst."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1109\/TNSRE.2022.3226860","article-title":"Physics-informed deep learning for musculoskeletal modeling: Predicting muscle forces and joint kinematics from surface EMG","volume":"31","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/21\/8760\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:12:47Z","timestamp":1760130767000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/21\/8760"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,27]]},"references-count":52,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["s23218760"],"URL":"https:\/\/doi.org\/10.3390\/s23218760","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,27]]}}}