Automated subcutaneous fat segmentation with a convolutional neural network in magnetic resonance guided high-intensity focused ultrasound treatment for uterine fibroids
We established an automatic segmentation algorithm based on an attention-gated U-Net architecture to delineate the abdominal fat layer in MR images of uterine fibroids patients. The model achieved high accuracy, robustly handling both thin and thick fat layers, and performed reliable on data prepared by a second reader.
Authors
- Roberto T. Blanco Sequeiros (ORCID: https://orcid.org/0000-0002-0167-9639)
- Teija Sainio (ORCID: https://orcid.org/0000-0001-5846-2601)
- Gaber Komar (ORCID: https://orcid.org/0000-0001-5072-3782)
- A.G. Partanen
- Kirsi Joronen (ORCID: https://orcid.org/0000-0002-5527-8371)
- Anna Laaksonen
- Simon Köttgen
Institutions
- University of Turku (FI)
- Turku University Hospital (FI)
- Profound Medical (Canada) (CA)
Publication Details
- Journal
- International Journal of Hyperthermia
- Published
- 2026-02-26
- DOI
- https://doi.org/10.1080/02656736.2026.2634734
- Primary Topic
- Uterine Myomas and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00