Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Correspondence between areas causing recall in breast cancer screening and artificial intelligence findings

Dahlblom, Victor LU orcid ; Tingberg, Anders LU ; Zackrisson, Sophia LU and Dustler, Magnus LU (2022) 16th International Workshop on Breast Imaging, IWBI 2022 In Proceedings of SPIE - The International Society for Optical Engineering 12286.
Abstract

False positive recall is a major issue in breast cancer screening and the introduction of artificial intelligence (AI) might affect which women who are unnecessarily recalled. We have investigated how an AI system works on false positive recalls at screening and compared with radiologist findings. Two-view digital mammography (DM) examinations from 656 recalled women (136 with screening detected cancer), were analysed with a commercial AI system. The AI findings were matched with the areas on the images causing the recalls. The agreement was studied both at the examination level and for individual findings. Scores were compared between true positive and false positive recalls. ROC analysis was used to study the AI-system's ability to... (More)

False positive recall is a major issue in breast cancer screening and the introduction of artificial intelligence (AI) might affect which women who are unnecessarily recalled. We have investigated how an AI system works on false positive recalls at screening and compared with radiologist findings. Two-view digital mammography (DM) examinations from 656 recalled women (136 with screening detected cancer), were analysed with a commercial AI system. The AI findings were matched with the areas on the images causing the recalls. The agreement was studied both at the examination level and for individual findings. Scores were compared between true positive and false positive recalls. ROC analysis was used to study the AI-system's ability to distinguish between true and false positive recalls. It was also studied how the AI system performed on cases where there were discordant readings. AI identified the same areas as radiologists in 80% of the cases recalled on DM. For true positives both the proportion of matching areas and AI scores were higher than for false positive recalls. The AI system also had a relatively large AUC (0.83) for differentiating between false positive recalls and cancers. Further, the AI system identified most of the findings leading to recall in cases where only one of the readers had marked the case for discussion. There is a relatively large agreement between the AI system and radiologists. The AI system scores the false positives lower than true positives. AI complements a single reader in a way similar to a second reader.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
artificial intelligence, breast cancer screening, False positive recalls
host publication
16th International Workshop on Breast Imaging, IWBI 2022
series title
Proceedings of SPIE - The International Society for Optical Engineering
editor
Bosmans, Hilde ; Marshall, Nicholas and Van Ongeval, Chantal
volume
12286
article number
122860K
publisher
SPIE
conference name
16th International Workshop on Breast Imaging, IWBI 2022
conference location
Leuven, Belgium
conference dates
2022-05-22 - 2022-05-25
external identifiers
  • scopus:85136157827
ISSN
0277-786X
1996-756X
ISBN
9781510655843
DOI
10.1117/12.2625731
language
English
LU publication?
yes
id
e2190562-1885-4483-942c-8a64ab2869c1
date added to LUP
2022-09-19 14:30:40
date last changed
2024-03-21 12:45:23
@inproceedings{e2190562-1885-4483-942c-8a64ab2869c1,
  abstract     = {{<p>False positive recall is a major issue in breast cancer screening and the introduction of artificial intelligence (AI) might affect which women who are unnecessarily recalled. We have investigated how an AI system works on false positive recalls at screening and compared with radiologist findings. Two-view digital mammography (DM) examinations from 656 recalled women (136 with screening detected cancer), were analysed with a commercial AI system. The AI findings were matched with the areas on the images causing the recalls. The agreement was studied both at the examination level and for individual findings. Scores were compared between true positive and false positive recalls. ROC analysis was used to study the AI-system's ability to distinguish between true and false positive recalls. It was also studied how the AI system performed on cases where there were discordant readings. AI identified the same areas as radiologists in 80% of the cases recalled on DM. For true positives both the proportion of matching areas and AI scores were higher than for false positive recalls. The AI system also had a relatively large AUC (0.83) for differentiating between false positive recalls and cancers. Further, the AI system identified most of the findings leading to recall in cases where only one of the readers had marked the case for discussion. There is a relatively large agreement between the AI system and radiologists. The AI system scores the false positives lower than true positives. AI complements a single reader in a way similar to a second reader. </p>}},
  author       = {{Dahlblom, Victor and Tingberg, Anders and Zackrisson, Sophia and Dustler, Magnus}},
  booktitle    = {{16th International Workshop on Breast Imaging, IWBI 2022}},
  editor       = {{Bosmans, Hilde and Marshall, Nicholas and Van Ongeval, Chantal}},
  isbn         = {{9781510655843}},
  issn         = {{0277-786X}},
  keywords     = {{artificial intelligence; breast cancer screening; False positive recalls}},
  language     = {{eng}},
  publisher    = {{SPIE}},
  series       = {{Proceedings of SPIE - The International Society for Optical Engineering}},
  title        = {{Correspondence between areas causing recall in breast cancer screening and artificial intelligence findings}},
  url          = {{http://dx.doi.org/10.1117/12.2625731}},
  doi          = {{10.1117/12.2625731}},
  volume       = {{12286}},
  year         = {{2022}},
}