EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Missed and true interval cancers on digital breast tomosynthesis screening mammograms: radiologists’ assessment and artificial intelligence markings

Nataliia Moshina iD, Marthe Larsen, Hildegunn S Aase, Kerstin Obst-Gleditsch, Ingrid Margrethe Ohm Ulvik, Hauke Bartsch, Leif Oltedal, Solveig Hofvind iD

Acta Radiologica Open · 2026-08 · 15 (8)

DOI: 10.1177/20584601261467016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acta Radiologica Open, online erschienen am 07.08.2026. Verfasst von Nataliia Moshina und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Breast Cancer Screening, Cancer Registry, Norwegian Institute of Public Health, Oslo, Norway. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Kreftforeningen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Interval cancer, breast cancer detected after a negative screening examination but before the next scheduled appointment, represents a challenge in mammography screening programs due to less favorable histopathological characteristics compared to screen-detected cancer.

Purpose

To determine which interval cancers from digital breast tomosynthesis (DBT) were classified as missed and true by radiologists in a review, and to stratify the findings by risk scores and markings provided by an artificial intelligence (AI) model. Material and methods In this retrospective informed consensus-based review, radiologists assessed mammograms from 46 interval cancers and classified those as false negative, minimal-sign significant or non-specific, or true negative. An AI risk score (1–7, low; 8–9, intermediate; or 10, high risk of malignancy) was available for each examination. For cases with AI risk scores of 8–10, the location of AI-detected markings was compared with the true cancer site.

Results

A total of 17% (8/46) of interval cancers were classified as false negative, 22% (10/46) as minimal-sign significant, 20% (9/46) as minimal-sign non-specific, and 41% (19/46) as true negative. The AI model correctly identified 35% (16/46) and incorrectly located 24% (11/46). Considering false negative and minimal-sign significant as cases with the highest probability of being diagnosed at screening due to mammographic visibility, the proportion of cases correctly identified by the AI model was reduced from 35% to 22% (10/46).

Conclusion

About 20% of interval cancers have potential to be diagnosed earlier using AI in DBT screen-reading.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencedigital breast tomosynthesisinterval cancerradiological reviewscreening

Autor:innen und Institutionen

  • Department of Breast Cancer Screening, Cancer Registry, Norwegian Institute of Public Health, Oslo, Norway.
  • Department of Radiology, Haukeland University Hospital, Bergen, Norway.
  • Mohn Medical Imaging and Visualization Centre (MMIV), Department of Radiology, Haukeland University Hospital, Bergen, Norway.
  • Department of Clinical Medicine, University of Bergen, Bergen, Norway.
  • Department of Health and Care Sciences, Faculty of Health Sciences, UiT, The Arctic University of Norway, Tromsø, Norway.

ORCID-Profile: Nataliia Moshina, Solveig Hofvind

Förderung

  • Kreftforeningen

Zitieren

APA

Moshina, N., Larsen, M., Aase, H. S., Obst-Gleditsch, K., Margrethe Ohm Ulvik, I., Bartsch, H., Oltedal, L., & Hofvind, S. (2026). Missed and true interval cancers on digital breast tomosynthesis screening mammograms: radiologists’ assessment and artificial intelligence markings. Acta Radiologica Open, 15(8). https://doi.org/10.1177/20584601261467016

Vancouver

Moshina N, Larsen M, Aase HS, Obst-Gleditsch K, Margrethe Ohm Ulvik I, Bartsch H, et al. Missed and true interval cancers on digital breast tomosynthesis screening mammograms: radiologists’ assessment and artificial intelligence markings. Acta Radiologica Open. 2026;15(8). doi:10.1177/20584601261467016

BibTeX
@article{Moshina2026,
  author = {Moshina, Nataliia and Larsen, Marthe and Aase, Hildegunn S and Obst-Gleditsch, Kerstin and Margrethe Ohm Ulvik, Ingrid and Bartsch, Hauke and Oltedal, Leif and Hofvind, Solveig},
  title = {Missed and true interval cancers on digital breast tomosynthesis screening mammograms: radiologists’ assessment and artificial intelligence markings},
  journal = {Acta Radiologica Open},
  year = {2026},
  volume = {15},
  number = {8},
  doi = {10.1177/20584601261467016}
}
Kostenlos starten →