Detecting Breast Cancer using a Compressive Sensing Unmixing Algorithm

TL;DR

This paper introduces a novel compressive sensing unmixing algorithm for breast cancer detection that separates tissue components and identifies cancerous regions more effectively than traditional methods.

Contribution

It presents a new unmixing approach that directly estimates tissue component proportions using CS techniques in a hybrid imaging system.

Findings

Cancerous lesions can be detected from mixture proportions.

The method improves detection accuracy over traditional permittivity recovery.

Numerical analysis confirms the effectiveness of the approach.

Abstract

Traditional breast cancer imaging methods using microwave Nearfield Radar Imaging (NRI) 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. In this paper, we describe a novel unmixing algorithm for detecting breast cancer. In this approach, the breast tissue is separated into three components, low water content (LWC), high water content (HWC), and cancerous tissues, and the goal of the optimization procedure is to recover the mixture proportions for each component. By utilizing this approach in a hybrid DBT / NRI system, the unmixing reconstruction process can be posed as a sparse recovery problem, such that compressive sensing (CS) 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.