Full 3D Microwave Breast Imaging Using a Deep-Learning Technique

Overview

Journal J Imaging

Publisher MDPI

Specialty Radiology

Date 2021 Aug 30

PMID 34460695

Citations 11

Authors

Vahab Khoshdel

Mohammad Asefi

Ahmed Ashraf

Joe LoVetri

Affiliations

Soon will be listed here.

Abstract

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.

Citing Articles

Review and Analysis of Tumour Detection and Image Quality Analysis in Experimental Breast Microwave Sensing.

Reimer T, Pistorius S Sensors (Basel). 2023; 23(11).

PMID: 37299852 PMC: 10255334. DOI: 10.3390/s23115123.

A Deep Learning Approach for Diagnosis Support in Breast Cancer Microwave Tomography.

Franceschini S, Autorino M, Ambrosanio M, Pascazio V, Baselice F Diagnostics (Basel). 2023; 13(10).

PMID: 37238177 PMC: 10217126. DOI: 10.3390/diagnostics13101693.

Brain Tumor Segmentation and Classification from Sensor-Based Portable Microwave Brain Imaging System Using Lightweight Deep Learning Models.

Hossain A, Islam M, Rahman T, Chowdhury M, Tahir A, Kiranyaz S Biosensors (Basel). 2023; 13(3).

PMID: 36979514 PMC: 10046629. DOI: 10.3390/bios13030302.

Radar-Based Microwave Breast Imaging Using Neurocomputational Models.

Bicer M Diagnostics (Basel). 2023; 13(5).

PMID: 36900075 PMC: 10000704. DOI: 10.3390/diagnostics13050930.

A Lightweight Deep Learning Based Microwave Brain Image Network Model for Brain Tumor Classification Using Reconstructed Microwave Brain (RMB) Images.

Hossain A, Islam M, Rahim S, Rahman M, Rahman T, Arshad H Biosensors (Basel). 2023; 13(2).

PMID: 36832004 PMC: 9954219. DOI: 10.3390/bios13020238.

References

OLoughlin D, OHalloran M, Moloney B, Glavin M, Jones E, Elahi M . Microwave Breast Imaging: Clinical Advances and Remaining Challenges. IEEE Trans Biomed Eng. 2018; 65(11):2580-2590. DOI: 10.1109/TBME.2018.2809541. View

Wang G, Li W, Zuluaga M, Pratt R, Patel P, Aertsen M . Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning. IEEE Trans Med Imaging. 2018; 37(7):1562-1573. PMC: 6051485. DOI: 10.1109/TMI.2018.2791721. View

Meaney P, Paulsen K, Geimer S, Haider S, Fanning M . Quantification of 3-D field effects during 2-D microwave imaging. IEEE Trans Biomed Eng. 2002; 49(7):708-20. DOI: 10.1109/TBME.2002.1010855. View

Kurrant D, Fear E, Baran A, LoVetri J . Integrating prior information into microwave tomography part 2: Impact of errors in prior information on microwave tomography image quality. Med Phys. 2017; 44(12):6482-6503. DOI: 10.1002/mp.12584. View

Xie Y, Xia Y, Zhang J, Song Y, Feng D, Fulham M . Knowledge-based Collaborative Deep Learning for Benign-Malignant Lung Nodule Classification on Chest CT. IEEE Trans Med Imaging. 2018; 38(4):991-1004. DOI: 10.1109/TMI.2018.2876510. View

Rana S, Dey M, Tiberi G, Sani L, Vispa A, Raspa G . Machine Learning Approaches for Automated Lesion Detection in Microwave Breast Imaging Clinical Data. Sci Rep. 2019; 9(1):10510. PMC: 6642213. DOI: 10.1038/s41598-019-46974-3. View

Kurrant D, Baran A, LoVetri J, Fear E . Integrating prior information into microwave tomography Part 1: Impact of detail on image quality. Med Phys. 2017; 44(12):6461-6481. DOI: 10.1002/mp.12585. View

Odle T . Breast Imaging Artifacts. Radiol Technol. 2015; 87(1):65M-87M. View

Meaney P, Geimer S, Paulsen K . Two-step inversion with a logarithmic transformation for microwave breast imaging. Med Phys. 2017; 44(8):4239-4251. PMC: 5553696. DOI: 10.1002/mp.12384. View

10.

Jin K, McCann M, Froustey E, Unser M . Deep Convolutional Neural Network for Inverse Problems in Imaging. IEEE Trans Image Process. 2017; 26(9):4509-4522. DOI: 10.1109/TIP.2017.2713099. View

11.

Lazebnik M, Popovic D, McCartney L, Watkins C, Lindstrom M, Harter J . A large-scale study of the ultrawideband microwave dielectric properties of normal, benign and malignant breast tissues obtained from cancer surgeries. Phys Med Biol. 2007; 52(20):6093-115. DOI: 10.1088/0031-9155/52/20/002. View

12.

Kang E, Min J, Ye J . A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction. Med Phys. 2017; 44(10):e360-e375. DOI: 10.1002/mp.12344. View

13.

Shin H, Roth H, Gao M, Lu L, Xu Z, Nogues I . Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE Trans Med Imaging. 2016; 35(5):1285-98. PMC: 4890616. DOI: 10.1109/TMI.2016.2528162. View

14.

Halter R, Zhou T, Meaney P, Hartov A, Barth Jr R, Rosenkranz K . The correlation of in vivo and ex vivo tissue dielectric properties to validate electromagnetic breast imaging: initial clinical experience. Physiol Meas. 2009; 30(6):S121-36. PMC: 2792899. DOI: 10.1088/0967-3334/30/6/S08. View

15.

Han Y, Yoo J, Kim H, Shin H, Sung K, Ye J . Deep learning with domain adaptation for accelerated projection-reconstruction MR. Magn Reson Med. 2018; 80(3):1189-1205. DOI: 10.1002/mrm.27106. View

16.

Khoshdel V, Ashraf A, LoVetri J . Enhancement of Multimodal Microwave-Ultrasound Breast Imaging Using a Deep-Learning Technique. Sensors (Basel). 2019; 19(18). PMC: 6767656. DOI: 10.3390/s19184050. View

17.

Hanley J, McNeil B . The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology. 1982; 143(1):29-36. DOI: 10.1148/radiology.143.1.7063747. View

18.

Golnabi A, Meaney P, Epstein N, Paulsen K . Microwave imaging for breast cancer detection: advances in three--dimensional image reconstruction. Annu Int Conf IEEE Eng Med Biol Soc. 2012; 2011:5730-3. PMC: 3774049. DOI: 10.1109/IEMBS.2011.6091418. View

19.

Chew W, Wang Y . Reconstruction of two-dimensional permittivity distribution using the distorted Born iterative method. IEEE Trans Med Imaging. 1990; 9(2):218-25. DOI: 10.1109/42.56334. View

20.

Golnabi A, Meaney P, Geimer S, Paulsen K . 3-D Microwave Tomography Using the Soft Prior Regularization Technique: Evaluation in Anatomically Realistic MRI-Derived Numerical Breast Phantoms. IEEE Trans Biomed Eng. 2019; 66(9):2566-2575. PMC: 6620171. DOI: 10.1109/TBME.2019.2892303. View