Compressive sensing unmixing algorithm for breast cancer detection

Abstract

Traditional breast cancer imaging methods using microwave imaging (MWI) seek to recover the complex permittivity of the tissues at each voxel in the imaging region. This approach is suboptimal in that it does not directly consider the permittivity values that healthy and cancerous breast tissues typically have. The authors describe a novel unmixing algorithm for detecting breast cancer. In this approach, the breast tissue is separated into three components, low water content, high water content, and cancerous tissues, and the goal of the optimisation procedure is to recover the mixture proportions of each component. By utilising this approach in a hybrid digital breast tomosynthesis/MWI system, the unmixing reconstruction process can be posed as a sparse recovery problem such that compressive sensing techniques can be employed. A numerical analysis is performed, which demonstrates that cancerous lesions can be detected from their mixture proportion under the appropriate conditions.

Enhanced Detection of Magnetic Nanoparticles Using a Novel Microwave Ferromagnetic Resonance Imaging System

“…For instance, a promising form of simultaneous multi-frequency inversion employing compressive sensing unmixing algorithms has been developed which does not directly recover the complex permittivity of individual pixels or voxels but instead parameterizes breast targets into mixtures of high water content, low water content, and cancerous tissues (i.e. frequency-independent quantities) [51]. This method was demonstrated for hybrid DBT/MWI systems which require ionizing radiation exposure, however, as baseline tissue proportions for the MWI reconstruction process were first segmented directly from DBT images.…”

A Novel Texture Extraction-Based Compressive Sensing for Lung Cancer Classification

“…Recently, a CS simulation in image classification or detection is reported in Jokić and Vuković, Islam et al ., and Obermeier and Martinez-Lorenzo. [ 9 19 20 ] Their study proved that CS is a potential approach for both compression and feature extraction.…”

A Machine Learning Workflow for Tumour Detection in Breasts Using 3D Microwave Imaging

“…For example, parallel finite-element method (FEM) or discontinuous Galerkin method (DGM) based algorithms have been applied to realistic biomedical imaging scenarios for breast cancer monitoring [12][13][14] and stroke detection [15]. Microwave imaging, both in 2-D and 3-D, has also benefited from advancements in understanding and using prior information [16,17], including hard and/or soft prior from another modality [7,18,19], another algorithm applied to the same data [20], or knowledge of the expected materials [21,22].…”