https://doi.org/10.1140/epjs/s11734-025-01945-w
Regular Article
Automated rotation and cropping of the wax insert area of mammography phantom images
1
Centro de Desenvolvimento da Tecnologia Nuclear, CDTN, 31270-901, Belo Horizonte, MG, Brazil
2
Graduate Program in Electrical Engineering, Universidade Federal de Minas Gerais, Av. Antônio Carlos 6627, 31270-901, Belo Horizonte, MG, Brazil
3
Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil
a
This email address is being protected from spambots. You need JavaScript enabled to view it.
Received:
29
June
2024
Accepted:
8
September
2025
Published online:
17
September
2025
The assessment of a breast phantom image is required by mammography quality assurance guidelines. The visual assessment of the radiographic image of the breast phantoms specified by the American College of Radiology (ACR) and the Brazilian College of Radiology and Imaging Diagnosis (CBR) is subjective and can benefit from automation by computer tools. Aiming to preprocess the images for later full automation of the assessment process and to decrease the image file size, this work develops a computer program, applying a computer vision open-source library, to automatically detect, align and crop the wax insert area (useful area) of radiographic images of ACR and CBR breast phantoms. An extensive and heterogeneous image base from several mammography units was used, including images from clinical practice and obtained in laboratory. The approach used was effective in detecting, aligning and cropping the wax insert area, being unable to crop only a few images. The influence of interpolation methods on the rotation degradation was also investigated and the results showed the superior performance of the Lanchos method.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
