UMamba-Dual: A dual-branch model based on UMamba for cesarean scar disorder segmentation

Key Points

• This research aims to enhance the segmentation of cesarean scar disorder in ultrasound images using a new model.
• Developed a dual-branch model called UMamba-Dual.
• Applied the model to ultrasound images of cesarean scar disorders.
• Evaluated segmentation performance in cases with ambiguous boundaries.
• Achieved more accurate segmentation of CSDi regions.
• Demonstrated robustness in challenging anatomical structures.
• Indicated potential for reliable clinical application.

Abstract