A Model-based Approach to Comparing Breast Images
Lead Research Organisation:
Institute of Cancer Research
Department Name: Division of Radiotherapy and Imaging
Abstract
X-ray mammography is the method of choice in screening for breast cancer. Mammograms are x-ray images of the breast, taken with the breast tightly compressed between approximately parallel plates. Two different views, are commonly used: cranio-caudal (CC / looking vertically down on the breast) and medio-lateral oblique (MLO / looking at the breast from the opposite shoulder). In a few cases, potential signs of cancer can be detected in a single mammogram, but more usually, radiologists detect abnormalities by comparing mammograms. In bilateral comparison, the radiologist compares the mammograms of the left and right breasts and looks for asymmetries and architectural distortions between the images, though these terms are ill-defined (and thus not easily built into an algorithm). In temporal comparison, the radiologist compares the current mammogram with the previous one and looks for signs of significant change. In multi-view comparison, the radiologist compares the CC and MLO views of the same breast and looks for consistent evidence of an abnormality. Through experience, radiologists learn to make these comparisons, but the task is intrinsically difficult, because the effects of biological variation, soft tissue deformation, and projection imaging are confounded, so that establishing point-by-point correspondence between mammograms is impossible. Our aim is to develop computational methods for assisting the radiologist in this comparison. We plan to take a comprehensive model-based approach to making meaningful comparisons. This will draw on our previous experience of image registration together with modelling the statistics of anatomical variability, the biomechanics of tissue deformation, and the physics of image formation. To understand the effects of these different sources of variability in 2D mammograms, and develop appropriate models, we will make use of a large existing collection of 3D MR breast images, with corresponding mammograms. The application to breast imaging is of value in its own right, with the potential to make a significant contribution to more effective systems for computer-aided detection, but the methods we propose to develop are generic and capable of broad application to other applications in medical image analysis, where organs are imaged whilst undergoing mechanical deformation / for example, the heart, liver, lung, stomach and colon.
People |
ORCID iD |
Martin Leach (Principal Investigator) |
Publications
Denholm R
(2018)
Growth Trajectories, Breast Size, and Breast-Tissue Composition in a British Prebirth Cohort of Young Women.
in American journal of epidemiology
Denholm R
(2016)
Pre-natal exposures and breast tissue composition: findings from a British pre-birth cohort of young women and a systematic review.
in Breast cancer research : BCR
Doran SJ
(2017)
Breast MRI segmentation for density estimation: Do different methods give the same results and how much do differences matter?
in Medical physics
Ertas G
(2011)
Computerized detection of breast lesions in multi-centre and multi-instrument DCE-MR data using 3D principal component maps and template matching.
in Physics in medicine and biology
Ertas G
(2017)
A computerized volumetric segmentation method applicable to multi-centre MRI data to support computer-aided breast tissue analysis, density assessment and lesion localization.
in Medical & biological engineering & computing
Kousi E
(2016)
Quality assurance in MRI breast screening: comparing signal-to-noise ratio in dynamic contrast-enhanced imaging protocols.
in Physics in medicine and biology
Ledger AE
(2014)
Investigating the influence of flip angle and k-space sampling on dynamic contrast-enhanced MRI breast examinations.
in Academic radiology
Ledger AE
(2016)
Comparison of Dixon Sequences for Estimation of Percent Breast Fibroglandular Tissue.
in PloS one
Description | Methods to better segment the breast and different breast tissues to aid breast cancer evaluation, and risk prediction to stratify for screening. Application of these techniques to the ALSPAC cohort of children in Bristol has led to the ability to include MRI measuremetns of breast density and to relate these to maternal breast density and to a number of characteristics of these children at birth, with important implications for factors underpinning elevated breast cancer risk. |
Exploitation Route | We are using these techniques with the London School of Hygiene, UCL, and the UNiversity of Bristol, to investigate breast density in a cohort of women. We have also won an NIHR Fellowship to develop improved density and parenchymal enhancement methods. The techniques have also been applied to a data base of images from the MARIBS breast screening study. Aspects of the developments have contributed to software developments under a separate EPSRC grant. |
Sectors | Healthcare |
Description | To develop methods to segment breast tissues for density analysis To advance the development of more accurate methods of assessing breast density, using MRI, providing a basis for improved evaluation of risk and stratification for screening Development and evaluation of methods for assessing breast parenchymal enhancement as a potential indicator of risk To support breast analysis and visualisation techniques and software. Results submitted for publication identify links of breast cancer risk factors with maternal breast density, and characteristics of children measured at birth. |
First Year Of Impact | 2008 |
Sector | Healthcare |
Impact Types | Societal |
Description | Advanced computer diagnostics for whole body magnetic resonance imaging to improve management of patients with metastatic bone cancer. |
Amount | £1,201,674 (GBP) |
Funding ID | II-LA-0216-20007 |
Organisation | National Institute for Health Research |
Department | NIHR i4i Invention for Innovation (i4i) Programme |
Sector | Public |
Country | United Kingdom |
Start | 02/2017 |
End | 01/2020 |
Description | Commercialisation of novel image processing and display software for breast screening |
Amount | £101,607 (GBP) |
Funding ID | EP/J50077X/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start |
Description | NIHR TRF |
Amount | £198,520 (GBP) |
Funding ID | TRF-2013-06-003 |
Organisation | National Institute for Health Research |
Sector | Public |
Country | United Kingdom |
Start | 11/2013 |
End | 10/2015 |
Description | breast density assessment and risk |
Organisation | London School of Hygiene and Tropical Medicine (LSHTM) |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Development of analysis techniques for assessing MRI breast images. Application to a range of data from a large study hosted at LSHTM |
Collaborator Contribution | Making available a large image data base (partly built on earlier collaborations with me) Developing additional image processing approaches |
Impact | Several papers published or in course of publication Epidemiology, physics, informatics, public health |
Start Year | 2012 |
Description | breast density assessment and risk |
Organisation | University College London |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Development of analysis techniques for assessing MRI breast images. Application to a range of data from a large study hosted at LSHTM |
Collaborator Contribution | Making available a large image data base (partly built on earlier collaborations with me) Developing additional image processing approaches |
Impact | Several papers published or in course of publication Epidemiology, physics, informatics, public health |
Start Year | 2012 |