Evaluating Performance of Microwave Image Reconstruction Algorithms: Extracting Tissue Types with Segmentation Using Machine Learning

Abstract

Evaluating the quality of reconstructed images requires consistent approaches to extracting information and applying metrics. Partitioning medical images into tissue types permits the quantitative assessment of regions that contain a specific tissue. The assessment facilitates the evaluation of an imaging algorithm in terms of its ability to reconstruct the properties of various tissue types and identify anomalies. Microwave tomography is an imaging modality that is model-based and reconstructs an approximation of the actual internal spatial distribution of the dielectric properties of a breast over a reconstruction model consisting of discrete elements. The breast tissue types are characterized by their dielectric properties, so the complex permittivity profile that is reconstructed may be used to distinguish different tissue types. This manuscript presents a robust and flexible medical image segmentation technique to partition microwave breast images into tissue types in order to facilitate the evaluation of image quality. The approach combines an unsupervised machine learning method with statistical techniques. The key advantage for using the algorithm over other approaches, such as a threshold-based segmentation method, is that it supports this quantitative analysis without prior assumptions such as knowledge of the expected dielectric property values that characterize each tissue type. Moreover, it can be used for scenarios where there is a scarcity of data available for supervised learning. Microwave images are formed by solving an inverse scattering problem that is severely ill-posed, which has a significant impact on image quality. A number of strategies have been developed to alleviate the ill-posedness of the inverse scattering problem. The degree of success of each strategy varies, leading to reconstructions that have a wide range of image quality. A requirement for the segmentation technique is the ability to partition tissue types over a range of image qualities, which is demonstrated in the first part of the paper. The segmentation of images into regions of interest corresponding to various tissue types leads to the decomposition of the breast interior into disjoint tissue masks. An array of region and distance-based metrics are applied to compare masks extracted from reconstructed images and ground truth models. The quantitative results reveal the accuracy with which the geometric and dielectric properties are reconstructed. The incorporation of the segmentation that results in a framework that effectively furnishes the quantitative assessment of regions that contain a specific tissue is also demonstrated. The algorithm is applied to reconstructed microwave images derived from breasts with various densities and tissue distributions to demonstrate the flexibility of the algorithm and that it is not data-specific. The potential for using the algorithm to assist in diagnosis is exhibited with a tumor tracking example. This example also establishes the usefulness of the approach in evaluating the performance of the reconstruction algorithm in terms of its sensitivity and specificity to malignant tissue and its ability to accurately reconstruct malignant tissue.

EISPY2D: An Open-Source Python Library for the Development and Comparison of Algorithms in Two-Dimensional Electromagnetic Inverse Scattering Problems

“…This set of indicators can measure the performance of the algorithms, thus indicating their quality in locating, recovering the shape, estimating the electrical properties of the scatterers, estimating the total field, and quantifying the error in the equations. Although indicators for the reconstruction of tumor geometry have been recently proposed in the literature [23], which are a kind of scatterer, our geometry and positioning error measurement methodology have been proposed to be used in general applications. Furthermore, in [23], the geometry indicators depend on an image segmentation procedure using Machine Learning whereas, in our work, the calculation of ζ P and ζ S depends on simpler procedures.…”

“…Although indicators for the reconstruction of tumor geometry have been recently proposed in the literature [23], which are a kind of scatterer, our geometry and positioning error measurement methodology have been proposed to be used in general applications. Furthermore, in [23], the geometry indicators depend on an image segmentation procedure using Machine Learning whereas, in our work, the calculation of ζ P and ζ S depends on simpler procedures. Therefore, ζ P and ζ S are original indicators in their formulation and contribute to the literature as a way to measure the quality of location and shape recovery of scatterers in a general EISP approach and using simpler operations.…”

A Modified Exact Reconstruction Algorithm to Determine the Complex Permittivity Perturbations of a Cancer Affected Biological Target using Microwave Tomography Technique

“…Microwave tomography is currently showing some remarkable results in different areas of biomedicine [1,2], specifically the detection of cancerous tumors inside the human body. The MTT can detect the presence of tumors based on certain cell properties and is considered to be one of the best among the existing techniques such as X-ray computed tomography, MR imaging (MRI), positron emission, ultrasound, C-ray imaging, etc.…”

Advanced Computational Methods for Oncological Image Analysis

“…Along with the well-known imaging modalities, such as MR, CT, PET, US, which are now consolidated and used in clinical routine, recently new modalities have emerged that exploit techniques initially born in non-clinical contexts, such as microwaves [17,18]. When the aim is to reconstruct the dielectric/conductivity profile of the tissue under examination, "quantitative" algorithms must be adopted.…”

“…Microwave-based tomography is a model-based imaging modality that approximately reconstructs the actual internal spatial distribution of a breast's dielectric properties over a reconstruction model consisting of discrete elements. Breast tissue types are characterized by their dielectric properties, so the complex permittivity profile could help distinguish different tissue types [18].…”