Usinga prioriInformation for Regularization in Breast Microwave Image Reconstruction

Abstract

Regularization methods are used in microwave image reconstruction problems, which are ill-posed. Traditional regularization methods are usually problem-independent and do not take advantage of a priori information specific to any particular imaging application. In this paper, a novel problem-dependent regularization approach is introduced for the application of breast imaging. A real genetic algorithm (RGA) minimizes a cost function that is the error between the recorded and the simulated data. At each iteration of the RGA, a priori information about the shape of the breast profiles is used by a neural network classifier to reject the solutions that cannot be a map of the dielectric properties of a breast profile. The algorithm was tested against four realistic numerical breast phantoms including a mostly fatty, a scattered fibroglandular, a heterogeneously dense, and a very dense sample. The tests were also repeated where a 4 mm x 4 mm tumor was inserted in the fibroglandular tissue in each of the four breast types. The results show the effectiveness of the proposed approach, which to the best of our knowledge has the highest resolution amongst the evolutionary algorithms used for the inversion of realistic numerical breast phantoms.

Two‐step inversion with a logarithmic transformation for microwave breast imaging

“…[19][20][21] A priori information has been considered in various forms. 12,14,17,[22][23][24] For example, Fhager and Persson 14 investigated abnormality detection within a normal, homogeneous organ, and provided accurate property values of a large object (presumably an organ) as the initial estimate to reconstruct internal aberrations. Catapano et al 17 used a linear sampling method to recover target morphology, and then imposed a uniform property distribution across the target as the starting point for their reconstruction process.…”

Microwave Imaging Within the Interval Analysis Framework

“…This is indicative of the attention on this subject from academic, industrial, and governmental researchers and experts. As a matter of fact, the range of potential applications is wide and it spans from the more traditional (e.g., geophysical investigations and remote sensing [3][4][5], nondestructive testing and evaluation [6][7][8][9][10], and medical imaging [11][12][13][14][15][16][17][18]) to the latest ones mainly related to security and surveillance (e.g., throughthe-wall imaging [19][20][21][22][23][24]) up to more recent applications [25].…”

“…In order to avoid nonuniqueness and instability as well as to prevent the retrieval of false solutions [28], several inversion strategies have been proposed based on (a) a suitable definition of the integral equations either in exact [29,30] or approximated [31][32][33][34][35] forms to model the scattering phenomena, (b) the exploitation of the available a-priori information on some features of the scenario/scatterers under test [15,[36][37][38][39] or/and the knowledge of input-output samples of data and reference solutions [40][41][42] and/or the information acquired during the inversion process [43][44][45][46][47], and (c) the use of suitable global optimization strategies [48][49][50][51][52][53][54][55]. Whatever the approach, inversion methods generally consider an optimization step aimed at minimizing/maximizing a suitably defined data-mismatch cost function through gradient or evolutionarybased algorithms with still not fully resolved drawbacks.…”

Microwave tomography for breast cancer detection on Cell broadband engine processors

“…To our knowledge, the microwave tomography technique incorporating FDTD together with GA is the original work proposed by authors in [24,3,28]. Please refer to Section 3 for more detailed description on microwave tomography using GA and FDTD.…”