EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Determining HER2 Status by Artificial Intelligence: An Investigation of Primary, Metastatic, and HER2 Low Breast Tumors

Christiane Palm iD, Catherine E Connolly, Regina Masser, Barbara Padberg Sgier, Eva Karamitopoulou, Quentin Simon, Beata Bode, Marianne Tinguely iD

Diagnostics · 03.01.2023 · 13 (1) · 168

DOI: 10.3390/diagnostics13010168 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 03.01.2023. Verfasst von Christiane Palm und 7 weiteren Autor:innen. Beteiligte Einrichtung: Pathologie Institute Enge, 8005 Zurich, Switzerland. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The expression of human epidermal growth factor receptor 2 (HER2) protein or gene transcripts is critical for therapeutic decision making in breast cancer. We examined the performance of a digitalized and artificial intelligence (AI)-assisted workflow for HER2 status determination in accordance with the American Society of Clinical Oncology (ASCO)/College of Pathologists (CAP) guidelines. Our preliminary cohort consisted of 495 primary breast carcinomas, and our study cohort included 67 primary breast carcinomas and 30 metastatic deposits, which were evaluated for HER2 status by immunohistochemistry (IHC) and in situ hybridization (ISH). Three practicing breast pathologists independently assessed and scored slides, building the ground truth. Following a washout period, pathologists were provided with the results of the AI digital image analysis (DIA) and asked to reassess the slides. Both rounds of assessment from the pathologists were compared to the AI results and ground truth for each slide. We observed an overall HER2 positivity rate of 15% in our study cohort. Moderate agreement (Cohen’s κ 0.59) was observed between the ground truth and AI on IHC, with most discrepancies occurring between 0 and 1+ scores. Inter-observer agreement amongst pathologists was substantial (Fleiss´ κ 0.77) and pathologists’ agreement with AI scores was 80.6%. Substantial agreement of the AI with the ground truth (Cohen´s κ 0.80) was detected on ISH-stained slides, and the accuracy of AI was similar for the primary and metastatic tumors. We demonstrated the feasibility of a combined HER2 IHC and ISH AI workflow, with a Cohen’s κ of 0.94 when assessed in accordance with the ASCO/CAP recommendations.

Schlagwörter

Stichwörter der Autor:innen

HER2 immunohistochemistryHER2 in situ hybridizationartificial intelligencebreast carcinomadigital pathology

Autor:innen und Institutionen

  • Pathologie Institute Enge, 8005 Zurich, Switzerland.
  • Faculty of Medicine, University of Zurich, 8006 Zurich, Switzerland.

ORCID-Profile: Christiane Palm, Marianne Tinguely

Zitieren

APA

Palm, C., Connolly, C. E., Masser, R., Padberg Sgier, B., Karamitopoulou, E., Simon, Q., Bode, B., & Tinguely, M. (2023). Determining HER2 Status by Artificial Intelligence: An Investigation of Primary, Metastatic, and HER2 Low Breast Tumors. Diagnostics, 13(1), 168. https://doi.org/10.3390/diagnostics13010168

Vancouver

Palm C, Connolly CE, Masser R, Padberg Sgier B, Karamitopoulou E, Simon Q, et al. Determining HER2 Status by Artificial Intelligence: An Investigation of Primary, Metastatic, and HER2 Low Breast Tumors. Diagnostics. 2023;13(1):168. doi:10.3390/diagnostics13010168

BibTeX
@article{Palm2023,
  author = {Palm, Christiane and Connolly, Catherine E and Masser, Regina and Padberg Sgier, Barbara and Karamitopoulou, Eva and Simon, Quentin and Bode, Beata and Tinguely, Marianne},
  title = {Determining HER2 Status by Artificial Intelligence: An Investigation of Primary, Metastatic, and HER2 Low Breast Tumors},
  journal = {Diagnostics},
  year = {2023},
  volume = {13},
  number = {1},
  pages = {168},
  doi = {10.3390/diagnostics13010168}
}
Kostenlos starten →