AI in breast screening mammography: breast screening readers' perspectives

Clarisse Florence de Vries; Samantha J Colosimo; Moragh Boyle; Gerald Lip; Lesley A Anderson; Roger T Staff; iCAIRD Radiology Collaboration

doi:10.1186/s13244-022-01322-4

AI in breast screening mammography: breast screening readers' perspectives

Clarisse Florence de Vries, Samantha J Colosimo, Moragh Boyle, Gerald Lip, Lesley A Anderson, Roger T Staff, iCAIRD Radiology Collaboration

Aberdeen Royal Infirmary

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

9 Downloads (Pure)

Abstract

OBJECTIVES: This study surveyed the views of breast screening readers in the UK on how to incorporate Artificial Intelligence (AI) technology into breast screening mammography.

METHODS: An online questionnaire was circulated to the UK breast screening readers. Questions included their degree of approval of four AI implementation scenarios: AI as triage, AI as a companion reader/reader aid, AI replacing one of the initial two readers, and AI replacing all readers. They were also asked to rank five AI representation options (discrete opinion; mammographic scoring; percentage score with 100% indicating malignancy; region of suspicion; heat map) and indicate which evidence they considered necessary to support the implementation of AI into their practice among six options offered.

RESULTS: The survey had 87 nationally accredited respondents across the UK; 73 completed the survey in full. Respondents approved of AI replacing one of the initial two human readers and objected to AI replacing all human readers. Participants were divided on AI as triage and AI as a reader companion. A region of suspicion superimposed on the image was the preferred AI representation option. Most screen readers considered national guidelines (77%), studies using a nationally representative dataset (65%) and independent prospective studies (60%) as essential evidence. Participants' free-text comments highlighted concerns and the need for additional validation.

CONCLUSIONS: Overall, screen readers supported the introduction of AI as a partial replacement of human readers and preferred a graphical indication of the suspected tumour area, with further evidence and national guidelines considered crucial prior to implementation.

Original language	English
Article number	186
Number of pages	7
Journal	Insights into Imaging
Volume	13
Issue number	1
Early online date	9 Dec 2022
DOIs	https://doi.org/10.1186/s13244-022-01322-4
Publication status	Published - 9 Dec 2022

Bibliographical note

Acknowledgements
We would like to thank all the survey respondents for their time and input. We would also like to thank the Scottish Breast Radiology Forum (SBRF) and British Society of Breast Radiology (BSBR) for their aid in dissemination of the survey. Furthermore, we would like to thank Dr Rumana Newlands for her advice on how to perform content analysis and report its results.

iCAIRD Radiology Collaboration team members:
Harrison D (iCAIRD Director), University of St Andrews. Black C, Murray A and Wilde K, University of Aberdeen. Blackwood JD, NHS Greater Glasgow and Clyde. Butterly C and Zurowski J, University of Glasgow. Eilbeck J and McSkimming C, NHS Grampian. Canon Medical Research Europe Ltd. – SHAIP platform.

Funding
This work is supported by the Industrial Centre for Artificial Intelligence Research in Digital Diagnostics (iCAIRD) which is funded by Innovate UK on behalf of UK Research and Innovation (UKRI) [project number: 104690]. The funding source was not involved in study design; collection, analysis and interpretation of data; writing of the report; or in the decision to submit the article for publication.

Author info

Keywords

Mammography
Screening
Radiologist
Breast screening reader

Access to Document

10.1186/s13244-022-01322-4Licence: CC BY

Florence_etal_III_AI_In_Breast_VoR
© The Author(s) 2022. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Final published version, 1.16 MBLicence: CC BY

Aberdeen Biomedical Imaging Centre
Waiter, G. (Manager) & Morris, T. (Facilities Co-ordinator)
Aberdeen Biomedical Imaging Centre
Research Facilities: Facility

Cite this

@article{24a6cef446804b6ead86d15806056560,

title = "AI in breast screening mammography: breast screening readers' perspectives",

abstract = "OBJECTIVES: This study surveyed the views of breast screening readers in the UK on how to incorporate Artificial Intelligence (AI) technology into breast screening mammography.METHODS: An online questionnaire was circulated to the UK breast screening readers. Questions included their degree of approval of four AI implementation scenarios: AI as triage, AI as a companion reader/reader aid, AI replacing one of the initial two readers, and AI replacing all readers. They were also asked to rank five AI representation options (discrete opinion; mammographic scoring; percentage score with 100% indicating malignancy; region of suspicion; heat map) and indicate which evidence they considered necessary to support the implementation of AI into their practice among six options offered.RESULTS: The survey had 87 nationally accredited respondents across the UK; 73 completed the survey in full. Respondents approved of AI replacing one of the initial two human readers and objected to AI replacing all human readers. Participants were divided on AI as triage and AI as a reader companion. A region of suspicion superimposed on the image was the preferred AI representation option. Most screen readers considered national guidelines (77%), studies using a nationally representative dataset (65%) and independent prospective studies (60%) as essential evidence. Participants' free-text comments highlighted concerns and the need for additional validation.CONCLUSIONS: Overall, screen readers supported the introduction of AI as a partial replacement of human readers and preferred a graphical indication of the suspected tumour area, with further evidence and national guidelines considered crucial prior to implementation.",

keywords = "Mammography, Screening, Radiologist, Breast screening reader",

author = "{de Vries}, {Clarisse Florence} and Colosimo, {Samantha J} and Moragh Boyle and Gerald Lip and Anderson, {Lesley A} and Staff, {Roger T} and {iCAIRD Radiology Collaboration}",

note = "Acknowledgements We would like to thank all the survey respondents for their time and input. We would also like to thank the Scottish Breast Radiology Forum (SBRF) and British Society of Breast Radiology (BSBR) for their aid in dissemination of the survey. Furthermore, we would like to thank Dr Rumana Newlands for her advice on how to perform content analysis and report its results. iCAIRD Radiology Collaboration team members: Harrison D (iCAIRD Director), University of St Andrews. Black C, Murray A and Wilde K, University of Aberdeen. Blackwood JD, NHS Greater Glasgow and Clyde. Butterly C and Zurowski J, University of Glasgow. Eilbeck J and McSkimming C, NHS Grampian. Canon Medical Research Europe Ltd. – SHAIP platform. Funding This work is supported by the Industrial Centre for Artificial Intelligence Research in Digital Diagnostics (iCAIRD) which is funded by Innovate UK on behalf of UK Research and Innovation (UKRI) [project number: 104690]. The funding source was not involved in study design; collection, analysis and interpretation of data; writing of the report; or in the decision to submit the article for publication. Author info",

year = "2022",

month = dec,

day = "9",

doi = "10.1186/s13244-022-01322-4",

language = "English",

volume = "13",

journal = "Insights into Imaging",

issn = "1869-4101",

publisher = "Springer ",

number = "1",

}

TY - JOUR

T1 - AI in breast screening mammography

T2 - breast screening readers' perspectives

AU - de Vries, Clarisse Florence

AU - Colosimo, Samantha J

AU - Boyle, Moragh

AU - Lip, Gerald

AU - Anderson, Lesley A

AU - Staff, Roger T

AU - iCAIRD Radiology Collaboration

N1 - Acknowledgements We would like to thank all the survey respondents for their time and input. We would also like to thank the Scottish Breast Radiology Forum (SBRF) and British Society of Breast Radiology (BSBR) for their aid in dissemination of the survey. Furthermore, we would like to thank Dr Rumana Newlands for her advice on how to perform content analysis and report its results. iCAIRD Radiology Collaboration team members: Harrison D (iCAIRD Director), University of St Andrews. Black C, Murray A and Wilde K, University of Aberdeen. Blackwood JD, NHS Greater Glasgow and Clyde. Butterly C and Zurowski J, University of Glasgow. Eilbeck J and McSkimming C, NHS Grampian. Canon Medical Research Europe Ltd. – SHAIP platform. Funding This work is supported by the Industrial Centre for Artificial Intelligence Research in Digital Diagnostics (iCAIRD) which is funded by Innovate UK on behalf of UK Research and Innovation (UKRI) [project number: 104690]. The funding source was not involved in study design; collection, analysis and interpretation of data; writing of the report; or in the decision to submit the article for publication. Author info

PY - 2022/12/9

Y1 - 2022/12/9

N2 - OBJECTIVES: This study surveyed the views of breast screening readers in the UK on how to incorporate Artificial Intelligence (AI) technology into breast screening mammography.METHODS: An online questionnaire was circulated to the UK breast screening readers. Questions included their degree of approval of four AI implementation scenarios: AI as triage, AI as a companion reader/reader aid, AI replacing one of the initial two readers, and AI replacing all readers. They were also asked to rank five AI representation options (discrete opinion; mammographic scoring; percentage score with 100% indicating malignancy; region of suspicion; heat map) and indicate which evidence they considered necessary to support the implementation of AI into their practice among six options offered.RESULTS: The survey had 87 nationally accredited respondents across the UK; 73 completed the survey in full. Respondents approved of AI replacing one of the initial two human readers and objected to AI replacing all human readers. Participants were divided on AI as triage and AI as a reader companion. A region of suspicion superimposed on the image was the preferred AI representation option. Most screen readers considered national guidelines (77%), studies using a nationally representative dataset (65%) and independent prospective studies (60%) as essential evidence. Participants' free-text comments highlighted concerns and the need for additional validation.CONCLUSIONS: Overall, screen readers supported the introduction of AI as a partial replacement of human readers and preferred a graphical indication of the suspected tumour area, with further evidence and national guidelines considered crucial prior to implementation.

AB - OBJECTIVES: This study surveyed the views of breast screening readers in the UK on how to incorporate Artificial Intelligence (AI) technology into breast screening mammography.METHODS: An online questionnaire was circulated to the UK breast screening readers. Questions included their degree of approval of four AI implementation scenarios: AI as triage, AI as a companion reader/reader aid, AI replacing one of the initial two readers, and AI replacing all readers. They were also asked to rank five AI representation options (discrete opinion; mammographic scoring; percentage score with 100% indicating malignancy; region of suspicion; heat map) and indicate which evidence they considered necessary to support the implementation of AI into their practice among six options offered.RESULTS: The survey had 87 nationally accredited respondents across the UK; 73 completed the survey in full. Respondents approved of AI replacing one of the initial two human readers and objected to AI replacing all human readers. Participants were divided on AI as triage and AI as a reader companion. A region of suspicion superimposed on the image was the preferred AI representation option. Most screen readers considered national guidelines (77%), studies using a nationally representative dataset (65%) and independent prospective studies (60%) as essential evidence. Participants' free-text comments highlighted concerns and the need for additional validation.CONCLUSIONS: Overall, screen readers supported the introduction of AI as a partial replacement of human readers and preferred a graphical indication of the suspected tumour area, with further evidence and national guidelines considered crucial prior to implementation.

KW - Mammography

KW - Screening

KW - Radiologist

KW - Breast screening reader

U2 - 10.1186/s13244-022-01322-4

DO - 10.1186/s13244-022-01322-4

M3 - Article

C2 - 36484919

SN - 1869-4101

VL - 13

JO - Insights into Imaging

JF - Insights into Imaging

IS - 1

M1 - 186

ER -

AI in breast screening mammography: breast screening readers' perspectives

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Equipment

Aberdeen Biomedical Imaging Centre

Cite this