Predicting estrogen receptor status from HE-stained breast cancer slides using artificial intelligence
On the internal test set, the proposed model achieved a micro accuracy, a macro accuracy, and an area under the curve of 0.91, 0.86, and 0.95, respectively. The corresponding results on the external test set were 0.93, 0.76, and 0.91, respectively. Using larger patch sizes resulted in significantly better classification performance, while no significant differences were observed when changing CLAM configurations.
Authors
- Borgny Ytterhus (ORCID: https://orcid.org/0009-0005-2802-667X)
- Elisabeth Wik (ORCID: https://orcid.org/0000-0002-5069-5715)
- Erik Smistad (ORCID: https://orcid.org/0000-0002-7258-4709)
- Ingerid Reinertsen (ORCID: https://orcid.org/0000-0003-0999-3849)
- Marit Valla (ORCID: https://orcid.org/0000-0001-7336-8779)
- Lars A. Akslen (ORCID: https://orcid.org/0000-0003-2710-9543)
- Maren Høibø
- André Pedersen (ORCID: https://orcid.org/0000-0002-3637-953X)
- Cecilie Askeland
- Ute Spiske
Institutions
- SINTEF (NO)
- Norwegian University of Science and Technology (NO)
- Haukeland University Hospital (NO)
- St Olav's University Hospital (NO)
- Sopra (France) (FR)
- University of Bergen (NO)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-06-09
- DOI
- https://doi.org/10.3389/fmed.2025.1593143
- Citations
- 1
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- Norges Teknisk-Naturvitenskapelige Universitet
- Helse Midt-Norge
- Norges Forskningsråd
- St. Olavs Hospital Universitetssykehuset i Trondheim
- Fakultet for medisin og helsevitenskap, Norges Teknisk-Naturvitenskapelige Universitet
- Faculty of Medicine and Health, University of Sydney