Region-wise loss for biomedical image segmentation

Juan Miguel Valverde, Jussi Tohka

Abstract: Highlights•Region-wise loss can simultaneously account for class imbalance and pixel importance.•Certain loss functions are special cases of Region-wise loss.•Region-wise loss fixes the optimization instability observed with Boundary loss.•Region-wise loss compares to or surpasses Dice, Focal, weighted Cross entropy, and Boundary loss.