Semiautomated multimodal breast image registration.

Charlotte Curtis,Elise Fear,Richard Frayne

doi:10.1155/2012/890830

Charlotte Curtis, Elise Fear + Show 1 more

Open Access

https://doi.org/10.1155/2012/890830

Copy DOI

Abstract

Consideration of information from multiple modalities has been shown to have increased diagnostic power in breast imaging. As a result, new techniques such as microwave imaging continue to be developed. Interpreting these novel image modalities is a challenge, requiring comparison to established techniques such as the gold standard X-ray mammography. However, due to the highly deformable nature of breast tissues, comparison of 3D and 2D modalities is a challenge. To enable this comparison, a registration technique was developed to map features from 2D mammograms to locations in the 3D image space. This technique was developed and tested using magnetic resonance (MR) images as a reference 3D modality, as MR breast imaging is an established technique in clinical practice. The algorithm was validated using a numerical phantom then successfully tested on twenty-four image pairs. Dice's coefficient was used to measure the external goodness of fit, resulting in an excellent overall average of 0.94. Internal agreement was evaluated by examining internal features in consultation with a radiologist, and subjective assessment concludes that reasonable alignment was achieved.

Highlights

To overcome these limitations of mammography, other modalities such as magnetic resonance (MR) and ultrasound imaging are used to assist in the diagnosis of symptomatic and high-risk patients
As the first stage of this procedure, this paper focuses on registration of mammograms to 3D image projections in order to obtain an estimate of mammographic features in an undistorted
The algorithm presented in this paper is aimed at obtaining an approximate 2D registration in order to map features seen on mammograms to regions of interest on a projection image formed from corresponding MR data

Summary

Introduction

To overcome these limitations of mammography, other modalities such as magnetic resonance (MR) and ultrasound imaging are used to assist in the diagnosis of symptomatic and high-risk patients. In the early stages of clinical trials, TSAR shows potential as a safe and inexpensive means of obtaining 3D images of the breast. As a new type of image, interpretation requires direct comparison with an established modality that provides reference data about the location of internal structures. Information about the breast exists in the form of X-ray mammograms, as current clinical protocols specify acquisition of mammograms in almost all cases [1]. These images are a valuable source of information about the internal and external structure of the breast and could potentially be used in place of MR images to assist with TSAR image interpretation.

Objectives

Methods

Results

Discussion

Conclusion