MammogramAnnotationTool: Markup tool for breast tissue abnormality annotation
Isosalo, Antti; Inkinen, Satu I.; Heino, Helinä; Turunen, Topi; Nieminen, Miika T. (2023-11-24)
Elsevier
24.11.2023
Antti Isosalo, Satu I. Inkinen, Helinä Heino, Topi Turunen, Miika T. Nieminen, MammogramAnnotationTool: Markup tool for breast tissue abnormality annotation, Software Impacts, Volume 19, 2024, 100599, ISSN 2665-9638, https://doi.org/10.1016/j.simpa.2023.100599
https://creativecommons.org/licenses/by-nc-nd/4.0/
© 2023 Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0).
https://creativecommons.org/licenses/by-nc-nd/4.0/
© 2023 Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0).
https://creativecommons.org/licenses/by-nc-nd/4.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202401151241
https://urn.fi/URN:NBN:fi:oulu-202401151241
Tiivistelmä
Abstract
In this work, we present an open-source MATLAB software tool for mammography image annotation. The tool has an easy-to-use graphical user interface enabling simultaneous visualization of both breasts. Annotations can be assigned to six categories for abnormal breast tissue: malignant mass, benign mass, malignant calcification, benign calcification, malignant architectural distortion, benign architectural distortion. Furthermore, characterization details, such as, morphology of the abnormality, can be assigned to each annotation. Optional examination-level breast density assessment can also be specified. This tool has been successfully applied as part of the data collection pipeline in already published deep learning-based segmentation and classification studies.
In this work, we present an open-source MATLAB software tool for mammography image annotation. The tool has an easy-to-use graphical user interface enabling simultaneous visualization of both breasts. Annotations can be assigned to six categories for abnormal breast tissue: malignant mass, benign mass, malignant calcification, benign calcification, malignant architectural distortion, benign architectural distortion. Furthermore, characterization details, such as, morphology of the abnormality, can be assigned to each annotation. Optional examination-level breast density assessment can also be specified. This tool has been successfully applied as part of the data collection pipeline in already published deep learning-based segmentation and classification studies.
Kokoelmat
- Avoin saatavuus [38840]
Ellei muuten mainita, aineiston lisenssi on https://creativecommons.org/licenses/by-nc-nd/4.0/