Log In Sign Up

On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice

by   Marcus Nordström, et al.

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 related to characterization and volume properties of the set of optimal segmentations are proved, and associated experiments are provided. Our main insights are: (i) the volume of the solutions to both metrics may deviate significantly from the expected volume of the target, (ii) the volume of a solution to Accuracy is always less than or equal to the volume of a solution to Dice and (iii) the optimal solutions to both of these metrics coincide when the set of feasible segmentations is constrained to the set of segmentations with the volume equal to the expected volume of the target.


page 4

page 23


Multi-Modality Abdominal Multi-Organ Segmentation with Deep Supervised 3D Segmentation Model

To promote the development of medical image segmentation technology, AMO...

Towards a Guideline for Evaluation Metrics in Medical Image Segmentation

In the last decade, research on artificial intelligence has seen rapid g...

How precise are performance estimates for typical medical image segmentation tasks?

An important issue in medical image processing is to be able to estimate...

Roughness Index and Roughness Distance for Benchmarking Medical Segmentation

Medical image segmentation is one of the most challenging tasks in medic...

The Dice loss in the context of missing or empty labels: Introducing Φ and ε

Albeit the Dice loss is one of the dominant loss functions in medical im...