Sustainable deep learning-based breast lesion segmentation: impact of breast region segmentation on performance
The findings indicate that applying BRS significantly enhances model performance. The most notable improvement was observed in the fourth approach, BRS with OV, which achieved approximately a 50% increase in segmentation accuracy compared to the non-BRS baseline. Furthermore, the BRS with OV approach resulted in a substantial reduction in computational energy consumption-up to 450%, highlighting its potential as an environmentally sustainable solution for large-scale applications.
Authors
- Endre Grøvik (ORCID: https://orcid.org/0000-0002-9925-1162)
- Jürgen Geisler (ORCID: https://orcid.org/0000-0001-6239-3856)
- Solveig Roth Hoff (ORCID: https://orcid.org/0000-0001-7928-3821)
- Kathinka D. Kurz (ORCID: https://orcid.org/0000-0003-1308-041X)
- Kjell‐Inge Gjesdal (ORCID: https://orcid.org/0000-0003-4568-762X)
- Sam Narimani
Institutions
- University of Oslo (NO)
- Norwegian University of Science and Technology (NO)
- Stavanger University Hospital (NO)
- Akershus University Hospital (NO)
- Helse Møre og Romsdal HF (NO)
- University of Stavanger (NO)
Publication Details
- Journal
- BMC Medical Imaging
- Published
- 2025-10-10
- DOI
- https://doi.org/10.1186/s12880-025-01947-z
- Citations
- 1
- Primary Topic
- MRI in cancer diagnosis
- Type
- article
- Field-Weighted Citation Impact
- 1.36
Funders
- Norges Teknisk-Naturvitenskapelige Universitet
- Helse Midt-Norge
- St. Olavs Hospital Universitetssykehuset i Trondheim