ROI Limited Unknowns Reduction-Based Contrast Source Inversion for Microwave Breast Imaging

We present a deep learning method used in conjunction with dual-modal microwave-ultrasound imaging to produce tomographic reconstructions of the complex-valued permittivity of numerical breast phantoms. We also assess tumor segmentation performance using the reconstructed permittivity as a feature. The contrast source inversion (CSI) technique is used to create the complex-permittivity images of the breast with ultrasound-derived tissue regions utilized as prior information. However, imaging artifacts make the detection of tumors difficult. To overcome this issue we train a convolutional neural network (CNN) that takes in, as input, the dual-modal CSI reconstruction and attempts to produce the true image of the complex tissue permittivity. The neural network consists of successive convolutional and downsampling layers, followed by successive deconvolutional and upsampling layers based on the U-Net architecture. To train the neural network, the input-output pairs consist of CSI’s dual-modal reconstructions, along with the true numerical phantom images from which the microwave scattered field was synthetically generated. The reconstructed permittivity images produced by the CNN show that the network is not only able to remove the artifacts that are typical of CSI reconstructions, but can also improve the detectability of tumors. The performance of the CNN is assessed using a four-fold cross-validation on our dataset that shows improvement over CSI both in terms of reconstruction error and tumor segmentation performance.

Download Full-text

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

Journal of Imaging ◽

10.3390/jimaging6080080 ◽

2020 ◽

Vol 6 (8) ◽

pp. 80 ◽

Cited By ~ 1

Author(s):

Vahab Khoshdel ◽

Mohammad Asefi ◽

Ahmed Ashraf ◽

Joe LoVetri

Keyword(s):

Deep Learning ◽

Breast Imaging ◽

Synthetic Data ◽

Roc Curves ◽

Source Inversion ◽

Operating Characteristics ◽

3D Images ◽

Size Number ◽

Contrast Source Inversion ◽

Learning Technique

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.

Download Full-text

Novel Stopping Criteria for Optimization-Based Microwave Breast Imaging Algorithms

Journal of Imaging ◽

10.3390/jimaging5050055 ◽

2019 ◽

Vol 5 (5) ◽

pp. 55 ◽

Cited By ~ 1

Author(s):

Cameron Kaye ◽

Ian Jeffrey ◽

Joe LoVetri

Keyword(s):

Breast Imaging ◽

Goodness Of Fit ◽

Reconstruction Technique ◽

Source Inversion ◽

Inversion Algorithm ◽

Goodness Of Fit Test ◽

Stopping Criteria ◽

Data Error ◽

Microwave Breast Imaging ◽

Number Of Iterations

A discontinuous Galerkin formulation of the Contrast Source Inversion algorithm (DGM-CSI) for microwave breast imaging employing a frequency-cycling reconstruction technique has been modified here to include a set of automated stopping criteria that determine a suitable time to shift imaging frequencies and to globally terminate the reconstruction. Recent studies have explored the use of tissue-dependent geometrical mapping of the well-reconstructed real part to its imaginary part as initial guesses during consecutive frequency hops. This practice was shown to improve resulting 2D images of the dielectric properties of synthetic breast models, but a fixed number of iterations was used to halt DGM-CSI inversions arbitrarily. Herein, a new set of stopping conditions is introduced based on an intelligent statistical analysis of a window of past iterations of data error using the two-sample Kolmogorov-Smirnov (K-S) test. This non-parametric goodness-of-fit test establishes a pattern in the data error distribution, indicating an appropriate time to shift frequencies, or terminate the algorithm. The proposed stopping criteria are shown to improve the efficiency of DGM-CSI while yielding images of equivalent quality to assigning an often liberally overestimated number of iterations per reconstruction.

Download Full-text