Resolution improvement using enriched Krylov subspace for microwave tomography breast imaging system

Abstract

In this work, a resolution improvement strategy has been presented for microwave tomography imaging in the dense and heterogeneous breasts. While improving the spatial resolution by reducing the size of pixels, the resultant image will be affected by spatial oscillation, and it will also lack to differentiate the dielectric values of low contrast tissue regions which are the unavoidable problems in the microwave tomography dense breast imaging. These difficulties are addressed as discrete ill‐posed and ill‐condition problems. In this paper, Enriched Conjugate Gradient Least Square (ECGLS) regularization method has been proposed and it is associated with the Distorted Born Iterative Method (DBIM) to improve the quality of high‐resolution images of heterogeneous and dense type breasts. The Proposed‐ECGLS (PECGLS) method introduces the span of enriched subspace with external penalization value to resolve the discrete ill‐posed problem. The Gram‐Schmidt factorization (or QR factorization) based step length and the external penalization value control the spatial oscillations and resolve the ill‐condition problem with quick convergence. The performance of the Proposed‐ECGLS method has been tested on heterogeneous and dense breast phantoms for synthetically embedded malignant along with differences in permittivity value of +8% to +10% in the fibrogland tissues. The results from the simulation studies depict that the Proposed‐ECGLS has achieved up to 0.8276 of structural similarity in different level discretization error and it is better than the existing methods such as ECGLS and standard CGLS. This high‐resolution microwave tomography imaging method will be helpful in malignant detection and fibroadenoma diagnosis in dense type breasts.