EUVIMEDEUVIMED entdecken
Multizentrische Studie

Artificial Intelligence Impact on Radiologist Performance in Breast Cancer Screening With Digital Breast Tomosynthesis

Kathy Schilling, Jeff Hoffmeister, Sharika Sarquis-Kolber, Nicole Coates, Julie Shisler

Journal of the American College of Radiology · 2026

DOI: 10.1016/j.jacr.2026.02.014 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of the American College of Radiology, 2026. Verfasst von Kathy Schilling und 4 weiteren Autor:innen. Beteiligte Einrichtung: Boca Raton Regional Hospital at Baptist Health South Florida, Boca Raton, Florida. Electronic address: kschilling@bocaradiology.com. Hauptthemen laut MEDLINE: Breast Neoplasms, Artificial Intelligence, Mammography, Clinical Competence. Die Arbeit nennt 16 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: The aim of this study was to assess the impact of artificial intelligence (AI) on radiologists' detection of cancer on digital breast tomosynthesis examinations on the basis of density, size, stage, and histopathology. METHODS: A retrospective analysis of mammographic audit data and screening cancers was conducted at four sites during two time periods with nine dedicated breast radiologists. Data were collected from March 1, 2018, to February 29, 2020 (pre-AI) and March 1, 2020, to February 28, 2022, with concurrent use of AI detection (post-AI). Age, density, tumor size, staging, and histopathology were collected for all screen-detected cancers. End points were cancer detection rate (CDR), recall rate, tumor size, stage, and histopathology. RESULTS: The pre-AI period had 54,440 examinations (339 true positives) and the post-AI had 48,742 examinations (369 true positives). CDR improved from 6.23 to 7.57, an increase of 1.34 (95% confidence interval [CI], 0.33 to 2.36; P < .01). The recall rate was 6.97% pre-AI and 6.96% post-AI, a decrease of 0.01% (95% CI, -0.32% to 0.30%; P = .47). Radiologists detected more cancers in dense breasts post-AI (45.0% vs 37.2% pre-AI, an increase of 7.8% [95% CI, 0.6% to 15.0%; P = .04]). The mean size of invasive cancers pre-AI was 12.16 mm, decreasing to 10.74 mm post-AI (1.42 mm smaller; 95% CI, -2.83 to -0.01 mm; P < .05). More cancers were T1 post-AI (70.7%) than pre-AI (63.1%), an increase of 7.6% (95% CI, 0.68% to 14.53%; P = .03), without a change in detection of ductal carcinoma in situ post-AI (23.0%) versus pre-AI (25.7%) (P = .42). The invasive CDR/ increased from 4.63 pre-AI to 5.83 post-AI, a difference 1.20 (95% CI, 0.31 to 2.08; P < .01). The rate of lobular cancers increased post-AI from 0.44 to 0.98, a difference of 0.54 (95% CI, 0.21 to 0.87; P < .001). CONCLUSIONS: Interpretation of screening digital breast tomosynthesis examinations by dedicated breast radiologists with the concurrent use of AI increased the CDR by 22% and the invasive detection rate by 26%, and the lobular detection rate doubled, with an increase in cancers detected in dense breasts and a decrease in mean invasive size and stage. The use of AI enabled the detection of more invasive cancers without an increase in noninvasive cancers or recall rate.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsArtificial IntelligenceMammographyClinical CompetenceEarly Detection of CancerRadiologistsFemaleHumansRetrospective StudiesMiddle AgedAged

Stichwörter der Autor:innen

Breast imagingartificial intelligencebreast cancer screeningdigital breast tomosynthesis

Autor:innen und Institutionen

  • Boca Raton Regional Hospital at Baptist Health South Florida, Boca Raton, Florida. Electronic address: kschilling@bocaradiology.com.
  • Manhattan Beach, California.
  • Boca Raton Regional Hospital at Baptist Health South Florida, Boca Raton, Florida.
  • JLS Consulting, Jupiter, Florida.

Zitieren

APA

Schilling, K., Hoffmeister, J., Sarquis-Kolber, S., Coates, N., & Shisler, J. (2026). Artificial Intelligence Impact on Radiologist Performance in Breast Cancer Screening With Digital Breast Tomosynthesis. Journal of the American College of Radiology. https://doi.org/10.1016/j.jacr.2026.02.014

Vancouver

Schilling K, Hoffmeister J, Sarquis-Kolber S, Coates N, Shisler J. Artificial Intelligence Impact on Radiologist Performance in Breast Cancer Screening With Digital Breast Tomosynthesis. Journal of the American College of Radiology. 2026. doi:10.1016/j.jacr.2026.02.014

BibTeX
@article{Schilling2026,
  author = {Schilling, Kathy and Hoffmeister, Jeff and Sarquis-Kolber, Sharika and Coates, Nicole and Shisler, Julie},
  title = {Artificial Intelligence Impact on Radiologist Performance in Breast Cancer Screening With Digital Breast Tomosynthesis},
  journal = {Journal of the American College of Radiology},
  year = {2026},
  doi = {10.1016/j.jacr.2026.02.014}
}
Kostenlos starten →