A comparison of methods to evaluate gray scale response of tomosynthesis systems using a software breast phantom

Sousa, Maria Angélica Zucareli; Bakić, Predrag R.; Schiabel, Homero; Maidment, Andrew D. A.

doi:10.1117/12.2255554

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an alternative, the use of both physical and computationally synthesized breast phantoms [CALDWELL & YAFFE, 1990], [CHEN et al, 2017], [ACCIAVATTI et al, 2017], [SOUZA et al, 2017], [BAKIC et al, 2018] may be useful for replacing datasets of images from actual breasts overcoming their restrictions and availability. In addition, this rules out the need for medical and/or biopsy reports to obtain the data requested in performance evaluation of computational schemes.…”

Section: Introductionmentioning

confidence: 99%

Features of a Free Mammography Database to Manage a Random Breast Phantom Images Dataset Intended for Testing Cad Schemes

Schiabel¹,

Matheus²,

Cardoso³

2022

JHS

View full text Add to dashboard Cite

A previous structured images database intended to be used as a tool to researchers testing developed image processing techniques in mammography is being upgraded with new tools and images sets. Its original management system allows to choose and download high quality mammographic images, as from old digitized films as well as from direct digital files acquired more recently. Its search engine is of freely access online, it has incorporated new features, and new types of images intended to aid performance tests of processing schemes. In this sense, we discuss here new tools implemented in the management system to be able to handle images of a new breast phantom with random distributions, exposed to different DR mammography equipment. We described some of the new database management system features to archive, search and download phantom images, together with an evaluation which compares these kind of images with those from actual breasts in order to validate this new set in terms of visual analysis. Previous results not only have indicated a reasonable level of similarity between phantom (ie., simulated) images and actual ones, but the utility of implement this dataset as a section of our mammography database in aiding performance tests of CADx schemes techniques addressed to detect and/or classify signals of interest in digital mammography.

show abstract