Open access
Jul 2026
Enhanced MRI brain tumor segmentation with DNet and hybrid dice-weighted cross-entropy loss.
The proposed DNet framework provides a robust and efficient framework for medical image segmentation and achieves higher accuracy in small tumor regions by combining Dice loss and weighted cross-entropy (WCE) loss.
Mehmet Sevi, I. Aydin, D. Cetintas
· Scientific Reports · 0 citations