3 papers
cs.CV2023
Noisy Image Segmentation With Soft-Dice
Marcus Nordström, Henrik Hult, Atsuto Maki +1
This paper presents a study on the soft-Dice loss, one of the most popular loss functions in medical image segmentation, for situations where noise is present in target labels. In…
cs.CV2023
Marginal Thresholding in Noisy Image Segmentation
Marcus Nordström, Henrik Hult, Atsuto Maki
This work presents a study on label noise in medical image segmentation by considering a noise model based on Gaussian field deformations. Such noise is of interest because it yiel…
cs.CV2022
On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice
Marcus Nordström, Henrik Hult, Jonas Söderberg +1
We study two of the most popular performance metrics in medical image segmentation, Accuracy and Dice, when the target labels are noisy. For both metrics, several statements relate…