Scattered radiation reduction tool to improve computer-aided diagnosis performance in digital breast tomosynthesis

Project Information

SCARtool

Grant agreement ID: 657875

DOI

10.3030/657875

Project closed

EC signature date 14 April 2015

Start date 1 September 2015

End date 31 August 2017

Funded under

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Total cost

€ 158 121,60

EU contribution

€ 158 121,60

Coordinated by

UNIVERSITAT DE GIRONA
Spain

Periodic Reporting for period 1 - SCARtool (Scattered radiation reduction tool to improve computer-aided diagnosis performance in digital breast tomosynthesis)

Reporting period: 2015-09-01 to 2017-08-31

Summary of the context and overall objectives of the project

Breast cancer is the most common form of cancer in the female population and represents the principal cause of cancer mortality in women worldwide. Around the world, every 19 seconds a woman is diagnosed with breast cancer and also, a woman dies from breast cancer every 74 seconds. Thus, further research, based on early detection, is necessary to reduce its high impact on the population.

Breast cancer screening programs (BSPs) is the current approach used to find early cancer signs in an asymptomatic target population. Screening population is invited to have regular mammograms (MG). However, digital breast tomosynthesis (DBT) has shown potential to be the future imaging technique for BSPs. DBT setup is similar to MG, however, DBT images are generated from several low-dose image projections at different angles, producing pseudo-3D images of the breast.

The SCARtool project investigates algorithms to improve image quality in DBT. The algorithms developed within the project have the aim to reduce scattered radiation in the DBT images, a type of radiation which might affect lesion detectability. Therefore, SCARtool's main goal is to improve early detection of breast cancer signs via DBT imaging.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

X-ray mammography (MG) has an anti-scatter grid to reduce scattered radiation, and therefore improve image quality. However, the presence of the grid increases the dose to the patient. For this reason, SCARtool started investigating the reduction of scattered radiation by means of image processing. Results from test objects shown that same contract could be obtained as grid images with a lower dose.

At the same time, scattered radiation for DBT imaging has been explored. Initially, a camera system was designed to investigate the breast deformation during the breast compression step. It was discovered that several compresson modes were available (rigid and flexible paddle), producing different scatter field distributions in the images. In fact, it was obseved that flexible paddles reduce the scatter radiation since the breast tissue is more spread. Currently, the sucessful scatter reduction algorithm for MG is being extended for DBT and its performance will be tested with an automatic microcalcification detection algorithm, as well as radiologist perception of breast lesion appearence.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

A reduction in the patient dose while maintaining image quality is expected for mammography imaging. This algorthm applied to a screening population will be of great benefit for each individual women since the dose absorbed will be reduced.

In case of DBT, a potential benefit of the algorithms developed within SCARtool is the increase of sensitivity in the DBT lesion detection. This will be tested using an automated microcalcification detection algorithm and radiologist perception. Additionally, it was found that breast compression mode can play an important role in the scatter distribution. Flexible compression paddles seem to spread the breast tissue much better and reduce the amount of scattered radiation in the image.

SCARtool logo

Simulation of DBT system