Deep learning enables automated MRI-based estimation of uterine volume also in patients with uterine fibroids undergoing high-intensity focused ultrasound therapy

Abstract

Key points Deep learning methods enable accurate segmentation of the uterus in T2-weighted MRI. Automatic uterine volumetry is possible in patients with and without leiomyomas. Automated volumetry enables an objective assessment of response to high-intensity focused ultrasound therapy.

Keywords

• Deep learning
• Magnetic resonance imaging
• Uterus
• Leiomyoma