Icometrix (Belgium)

output

20192022

most citedTheoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty

18 citations

Showing cs.CVShow all

3 papers · 1 filter

cs.CV2022★ 18 cited

Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty

Jeroen Bertels, David Robben, Dirk Vandermeulen +1

The clinical interest is often to measure the volume of a structure, which is typically derived from a segmentation. In order to evaluate and compare segmentation methods, the simi…

cs.CV2022★ 2 cited

Comparison of different automatic solutions for resection cavity segmentation in postoperative MRI volumes including longitudinal acquisitions

Luca Canalini, Jan Klein, Nuno Pedrosa de Barros +3

In this work, we compare five deep learning solutions to automatically segment the resection cavity in postoperative MRI. The proposed methods are based on the same 3D U-Net archit…

cs.CV2022★ 6 cited

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

Sofie Tilborghs, Jeroen Bertels, David Robben +2

Albeit the Dice loss is one of the dominant loss functions in medical image segmentation, most research omits a closer look at its derivative, i.e. the real motor of the optimizati…

Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertainty

Comparison of different automatic solutions for resection cavity segmentation in postoperative MRI volumes including longitudinal acquisitions

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

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