{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T23:59:16Z","timestamp":1778543956583,"version":"3.51.4"},"reference-count":47,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2020,8,11]],"date-time":"2020-08-11T00:00:00Z","timestamp":1597104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["-"],"award-info":[{"award-number":["-"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000147","name":"Canadian Cancer Society","doi-asserted-by":"publisher","award":["300028"],"award-info":[{"award-number":["300028"]}],"id":[{"id":"10.13039\/501100000147","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>A deep learning technique to enhance 3D images of the complex-valued permittivity of the breast obtained via microwave imaging is investigated. The developed technique is an extension of one created to enhance 2D images. We employ a 3D Convolutional Neural Network, based on the U-Net architecture, that takes in 3D images obtained using the Contrast-Source Inversion (CSI) method and attempts to produce the true 3D image of the permittivity. The training set consists of 3D CSI images, along with the true numerical phantom images from which the microwave scattered field utilized to create the CSI reconstructions was synthetically generated. Each numerical phantom varies with respect to the size, number, and location of tumors within the fibroglandular region. The reconstructed permittivity images produced by the proposed 3D U-Net show that the network is not only able to remove the artifacts that are typical of CSI reconstructions, but it also enhances the detectability of the tumors. We test the trained U-Net with 3D images obtained from experimentally collected microwave data as well as with images obtained synthetically. Significantly, the results illustrate that although the network was trained using only images obtained from synthetic data, it performed well with images obtained from both synthetic and experimental data. Quantitative evaluations are reported using Receiver Operating Characteristics (ROC) curves for the tumor detectability and RMS error for the enhancement of the reconstructions.<\/jats:p>","DOI":"10.3390\/jimaging6080080","type":"journal-article","created":{"date-parts":[[2020,8,11]],"date-time":"2020-08-11T09:28:57Z","timestamp":1597138137000},"page":"80","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Full 3D Microwave Breast Imaging Using a Deep-Learning Technique"],"prefix":"10.3390","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6241-8467","authenticated-orcid":false,"given":"Vahab","family":"Khoshdel","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad","family":"Asefi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Ashraf","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joe","family":"LoVetri","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,8,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2580","DOI":"10.1109\/TBME.2018.2809541","article-title":"Microwave Breast Imaging: Clinical Advances and Remaining Challenges","volume":"65","author":"Moloney","year":"2018","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_2","unstructured":"Lakhtakia, A., and Furse, C.M. (2018). Crossed Viewpoints on Microwave-Based Imaging for Medical Diagnosis: From Genesis to Earliest Clinical Outcomes. The World of Applied Electromagnetics: In Appreciation of Magdy Fahmy Iskander, Springer International Publishing."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"6093","DOI":"10.1088\/0031-9155\/52\/20\/002","article-title":"A large-scale study of the ultrawideband microwave dielectric properties of normal, benign and malignant breast tissues obtained from cancer surgeries","volume":"52","author":"Lazebnik","year":"2007","journal-title":"Phys. Med. Biol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"S121","DOI":"10.1088\/0967-3334\/30\/6\/S08","article-title":"The correlation of in vivo and ex vivo tissue dielectric properties to validate electromagnetic breast imaging: Initial clinical experience","volume":"30","author":"Halter","year":"2009","journal-title":"Physiol. Meas."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pastorino, M. (2010). Microwave Imaging, John Wiley & Sons.","DOI":"10.1002\/9780470602492"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1088\/0266-5611\/13\/6\/013","article-title":"A contrast source inversion method","volume":"13","author":"Kleinman","year":"1997","journal-title":"Inverse Probl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1761","DOI":"10.1109\/TMTT.2002.800427","article-title":"Imaging of biomedical data using a multiplicative regularized contrast source inversion method","volume":"50","author":"Abubakar","year":"2002","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"115010","DOI":"10.1088\/0266-5611\/26\/11\/115010","article-title":"Finite-element contrast source inversion method for microwave imaging","volume":"26","author":"Zakaria","year":"2010","journal-title":"Inverse Probl."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6461","DOI":"10.1002\/mp.12585","article-title":"Integrating prior information into microwave tomography Part 1: Impact of detail on image quality","volume":"44","author":"Kurrant","year":"2017","journal-title":"Med. Phys."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6482","DOI":"10.1002\/mp.12584","article-title":"Integrating prior information into microwave tomography part 2: Impact of errors in prior information on microwave tomography image quality","volume":"44","author":"Baran","year":"2017","journal-title":"Med. Phys."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, X. (2018). Computational Methods for Electromagnetic Inverse Scattering, Wiley Online Library.","DOI":"10.1002\/9781119311997"},{"key":"ref_12","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: http:\/\/www.deeplearningbook.org."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1109\/TMI.2018.2791721","article-title":"Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning","volume":"37","author":"Wang","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","article-title":"Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning","volume":"35","author":"Shin","year":"2016","journal-title":"IEEE Trans. Med Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1109\/MSP.2017.2739299","article-title":"Convolutional Neural Networks for Inverse Problems in Imaging: A Review","volume":"34","author":"McCann","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1109\/TMI.2018.2876510","article-title":"Knowledge-based Collaborative Deep Learning for Benign-Malignant Lung Nodule Classification on Chest CT","volume":"38","author":"Xie","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e360","DOI":"10.1002\/mp.12344","article-title":"A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction","volume":"44","author":"Kang","year":"2017","journal-title":"Med. Phys."},{"key":"ref_19","unstructured":"Han, Y., Yoo, J.J., and Ye, J.C. (2016). Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","article-title":"Deep Convolutional Neural Network for Inverse Problems in Imaging","volume":"26","author":"Jin","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1002\/mrm.27106","article-title":"Deep learning with domain adaptation for accelerated projection-reconstruction MR","volume":"80","author":"Han","year":"2018","journal-title":"Magn. Reson. Med."},{"key":"ref_22","first-page":"5119","article-title":"Novel Microwave Tomography System Using a Phased-Array Antenna","volume":"66","author":"Rahama","year":"2018","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1109\/20.996272","article-title":"Neural-network-based inverse-scattering technique for online microwave medical imaging","volume":"38","author":"Rekanos","year":"2002","journal-title":"IEEE Trans. Magn."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1819","DOI":"10.1109\/TAP.2018.2885437","article-title":"DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering","volume":"67","author":"Li","year":"2019","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Khoshdel, V., and Ashraf, A.L.J. (2019). Enhancement of Multimodal Microwave-Ultrasound Breast Imaging Using a Deep-Learning Technique. Sensors, 19.","DOI":"10.3390\/s19184050"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-46974-3","article-title":"Machine learning approaches for automated lesion detection in microwave breast imaging clinical data","volume":"9","author":"Rana","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3946","DOI":"10.1109\/TMTT.2019.2906619","article-title":"An Experimental Phantom Study for Air-Based Quasi-Resonant Microwave Breast Imaging","volume":"67","author":"Asefi","year":"2019","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1109\/TBME.2002.1010855","article-title":"Quantification of 3-D field effects during 2-D microwave imaging","volume":"49","author":"Meaney","year":"2002","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Golnabi, A.H., Meaney, P.M., Epstein, N.R., and Paulsen, K.D. (September, January 30). Microwave imaging for breast cancer detection: Advances in three\u2013dimensional image reconstruction. Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Boston, MA, USA.","DOI":"10.1109\/IEMBS.2011.6091418"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2566","DOI":"10.1109\/TBME.2019.2892303","article-title":"3-D Microwave Tomography Using the Soft Prior Regularization Technique: Evaluation in Anatomically Realistic MRI-Derived Numerical Breast Phantoms","volume":"66","author":"Golnabi","year":"2019","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/JMMCT.2019.2905344","article-title":"Incorporation of Ultrasonic Prior Information for Improving Quantitative Microwave Imaging of Breast","volume":"4","author":"Abdollahi","year":"2019","journal-title":"IEEE J. Multiscale Multiphys. Comput. Tech."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Gil Cano, J.D., Fasoula, A.D.L., and Bernard, J.G. (2020). Wavelia Breast Imaging: The Optical Breast Contour Detection Subsystem. Appl. Sci., 10.","DOI":"10.3390\/app10041234"},{"key":"ref_33","first-page":"428","article-title":"Breast imaging artifacts","volume":"89","author":"Odle","year":"2015","journal-title":"Radiol. Technol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1109\/42.56334","article-title":"Reconstruction of two-dimensional permittivity distribution using the distorted Born iterative method","volume":"9","author":"Chew","year":"1990","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1742","DOI":"10.1109\/8.121595","article-title":"Inverse scattering: An iterative numerical method for electromagnetic imaging","volume":"39","author":"Joachimowicz","year":"1991","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1109\/8.560338","article-title":"Microwave imaging-complex permittivity reconstruction with a Levenberg-Marquardt method","volume":"45","author":"Franchois","year":"1997","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1109\/10.942596","article-title":"Computational modeling of three-dimensional microwave tomography of breast cancer","volume":"48","author":"Bulyshev","year":"2001","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"4239","DOI":"10.1002\/mp.12384","article-title":"Two-step inversion with a logarithmic transformation for microwave breast imaging","volume":"44","author":"Meaney","year":"2017","journal-title":"Med. Phys."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2658","DOI":"10.1109\/TAP.2009.2027161","article-title":"Overview and classification of some regularization techniques for the Gauss-Newton inversion method applied to inverse scattering problems","volume":"57","author":"Mojabi","year":"2009","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Van den Berg, P., Abubakar, A., and Fokkema, J. (2003). Multiplicative regularization for contrast profile inversion. Radio Sci., 38.","DOI":"10.1029\/2001RS002555"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"463","DOI":"10.2528\/PIER13080706","article-title":"Full-Vectorial Parallel Finite-Element Contrast Source Inversion Method","volume":"142","author":"Zakaria","year":"2013","journal-title":"Prog. Electromagn. Res."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"4347","DOI":"10.1109\/TMTT.2017.2694823","article-title":"Modeling Error and Calibration Techniques for a Faceted Metallic Chamber for Magnetic Field Microwave Imaging","volume":"65","author":"Nemez","year":"2017","journal-title":"IEEE Trans. Microw. Theory Techn."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_44","unstructured":"Trabelsi, C., Bilaniuk, O., Zhang, Y., Serdyuk, D., Subramanian, S., Santos, J.F., Mehri, S., Rostamzadeh, N., Bengio, Y., and Pal, C. (2018). Deep Complex Networks. arXiv."},{"key":"ref_45","unstructured":"Pereira, F., Burges, C.J.C., Bottou, L., and Weinberger, K.Q. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25, Curran Associates, Inc."},{"key":"ref_46","unstructured":"Glorot, X., and Bengio, Y. (2010, January 21\u201323). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS\u201910), Society for Artificial Intelligence and Statistics, T\u00fcbingen, Germany."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"43","author":"Hanley","year":"1982","journal-title":"Radiology"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/6\/8\/80\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:59:04Z","timestamp":1760176744000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/6\/8\/80"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,11]]},"references-count":47,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2020,8]]}},"alternative-id":["jimaging6080080"],"URL":"https:\/\/doi.org\/10.3390\/jimaging6080080","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,11]]}}}