Cargando…

Multiclass Segmentation of Breast Tissue and Suspicious Findings: A Simulation-Based Study for the Development of Self-Steering Tomosynthesis

In breast tomosynthesis, multiple low-dose projections are acquired in a single scanning direction over a limited angular range to produce cross-sectional planes through the breast for three-dimensional imaging interpretation. We built a next-generation tomosynthesis system capable of multidirection...

Descripción completa

Detalles Bibliográficos
Autores principales: Barufaldi, Bruno, da Nobrega, Yann N. G., Carvalhal, Giulia, Teixeira, Joao P. V., Silva Filho, Telmo M., do Rego, Thais G., Malheiros, Yuri, Acciavatti, Raymond J., Maidment, Andrew D. A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10303463/
https://www.ncbi.nlm.nih.gov/pubmed/37368544
http://dx.doi.org/10.3390/tomography9030092
_version_ 1785065282972155904
author Barufaldi, Bruno
da Nobrega, Yann N. G.
Carvalhal, Giulia
Teixeira, Joao P. V.
Silva Filho, Telmo M.
do Rego, Thais G.
Malheiros, Yuri
Acciavatti, Raymond J.
Maidment, Andrew D. A.
author_facet Barufaldi, Bruno
da Nobrega, Yann N. G.
Carvalhal, Giulia
Teixeira, Joao P. V.
Silva Filho, Telmo M.
do Rego, Thais G.
Malheiros, Yuri
Acciavatti, Raymond J.
Maidment, Andrew D. A.
author_sort Barufaldi, Bruno
collection PubMed
description In breast tomosynthesis, multiple low-dose projections are acquired in a single scanning direction over a limited angular range to produce cross-sectional planes through the breast for three-dimensional imaging interpretation. We built a next-generation tomosynthesis system capable of multidirectional source motion with the intent to customize scanning motions around “suspicious findings”. Customized acquisitions can improve the image quality in areas that require increased scrutiny, such as breast cancers, architectural distortions, and dense clusters. In this paper, virtual clinical trial techniques were used to analyze whether a finding or area at high risk of masking cancers can be detected in a single low-dose projection and thus be used for motion planning. This represents a step towards customizing the subsequent low-dose projection acquisitions autonomously, guided by the first low-dose projection; we call this technique “self-steering tomosynthesis.” A U-Net was used to classify the low-dose projections into “risk classes” in simulated breasts with soft-tissue lesions; class probabilities were modified using post hoc Dirichlet calibration (DC). DC improved the multiclass segmentation (Dice = 0.43 vs. 0.28 before DC) and significantly reduced false positives (FPs) from the class of the highest risk of masking (sensitivity = 81.3% at 2 FPs per image vs. 76.0%). This simulation-based study demonstrated the feasibility of identifying suspicious areas using a single low-dose projection for self-steering tomosynthesis.
format Online
Article
Text
id pubmed-10303463
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-103034632023-06-29 Multiclass Segmentation of Breast Tissue and Suspicious Findings: A Simulation-Based Study for the Development of Self-Steering Tomosynthesis Barufaldi, Bruno da Nobrega, Yann N. G. Carvalhal, Giulia Teixeira, Joao P. V. Silva Filho, Telmo M. do Rego, Thais G. Malheiros, Yuri Acciavatti, Raymond J. Maidment, Andrew D. A. Tomography Article In breast tomosynthesis, multiple low-dose projections are acquired in a single scanning direction over a limited angular range to produce cross-sectional planes through the breast for three-dimensional imaging interpretation. We built a next-generation tomosynthesis system capable of multidirectional source motion with the intent to customize scanning motions around “suspicious findings”. Customized acquisitions can improve the image quality in areas that require increased scrutiny, such as breast cancers, architectural distortions, and dense clusters. In this paper, virtual clinical trial techniques were used to analyze whether a finding or area at high risk of masking cancers can be detected in a single low-dose projection and thus be used for motion planning. This represents a step towards customizing the subsequent low-dose projection acquisitions autonomously, guided by the first low-dose projection; we call this technique “self-steering tomosynthesis.” A U-Net was used to classify the low-dose projections into “risk classes” in simulated breasts with soft-tissue lesions; class probabilities were modified using post hoc Dirichlet calibration (DC). DC improved the multiclass segmentation (Dice = 0.43 vs. 0.28 before DC) and significantly reduced false positives (FPs) from the class of the highest risk of masking (sensitivity = 81.3% at 2 FPs per image vs. 76.0%). This simulation-based study demonstrated the feasibility of identifying suspicious areas using a single low-dose projection for self-steering tomosynthesis. MDPI 2023-06-10 /pmc/articles/PMC10303463/ /pubmed/37368544 http://dx.doi.org/10.3390/tomography9030092 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Barufaldi, Bruno
da Nobrega, Yann N. G.
Carvalhal, Giulia
Teixeira, Joao P. V.
Silva Filho, Telmo M.
do Rego, Thais G.
Malheiros, Yuri
Acciavatti, Raymond J.
Maidment, Andrew D. A.
Multiclass Segmentation of Breast Tissue and Suspicious Findings: A Simulation-Based Study for the Development of Self-Steering Tomosynthesis
title Multiclass Segmentation of Breast Tissue and Suspicious Findings: A Simulation-Based Study for the Development of Self-Steering Tomosynthesis
title_full Multiclass Segmentation of Breast Tissue and Suspicious Findings: A Simulation-Based Study for the Development of Self-Steering Tomosynthesis
title_fullStr Multiclass Segmentation of Breast Tissue and Suspicious Findings: A Simulation-Based Study for the Development of Self-Steering Tomosynthesis
title_full_unstemmed Multiclass Segmentation of Breast Tissue and Suspicious Findings: A Simulation-Based Study for the Development of Self-Steering Tomosynthesis
title_short Multiclass Segmentation of Breast Tissue and Suspicious Findings: A Simulation-Based Study for the Development of Self-Steering Tomosynthesis
title_sort multiclass segmentation of breast tissue and suspicious findings: a simulation-based study for the development of self-steering tomosynthesis
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10303463/
https://www.ncbi.nlm.nih.gov/pubmed/37368544
http://dx.doi.org/10.3390/tomography9030092
work_keys_str_mv AT barufaldibruno multiclasssegmentationofbreasttissueandsuspiciousfindingsasimulationbasedstudyforthedevelopmentofselfsteeringtomosynthesis
AT danobregayannng multiclasssegmentationofbreasttissueandsuspiciousfindingsasimulationbasedstudyforthedevelopmentofselfsteeringtomosynthesis
AT carvalhalgiulia multiclasssegmentationofbreasttissueandsuspiciousfindingsasimulationbasedstudyforthedevelopmentofselfsteeringtomosynthesis
AT teixeirajoaopv multiclasssegmentationofbreasttissueandsuspiciousfindingsasimulationbasedstudyforthedevelopmentofselfsteeringtomosynthesis
AT silvafilhotelmom multiclasssegmentationofbreasttissueandsuspiciousfindingsasimulationbasedstudyforthedevelopmentofselfsteeringtomosynthesis
AT doregothaisg multiclasssegmentationofbreasttissueandsuspiciousfindingsasimulationbasedstudyforthedevelopmentofselfsteeringtomosynthesis
AT malheirosyuri multiclasssegmentationofbreasttissueandsuspiciousfindingsasimulationbasedstudyforthedevelopmentofselfsteeringtomosynthesis
AT acciavattiraymondj multiclasssegmentationofbreasttissueandsuspiciousfindingsasimulationbasedstudyforthedevelopmentofselfsteeringtomosynthesis
AT maidmentandrewda multiclasssegmentationofbreasttissueandsuspiciousfindingsasimulationbasedstudyforthedevelopmentofselfsteeringtomosynthesis