Conference Proceedings

Learning Non-Unique Segmentation with Reward-Penalty Dice Loss

Jiabo He, Sarah Erfani, Sudanthi Wijewickrema, Stephen O'Leary, Kotagiri Ramamohanarao

Proceedings of the International Joint Conference on Neural Networks | IEEE | Published : 2020


Semantic segmentation is one of the key problems in the field of computer vision, as it enables computer image understanding. However, most research and applications of semantic segmentation focus on addressing unique segmentation problems, where there is only one gold standard segmentation result for every input image. This may not be true in some problems, e.g., medical applications. We may have non-unique segmentation annotations as different surgeons may perform successful surgeries for the same patient in slightly different ways. To comprehensively learn non-unique segmentation tasks, we propose the reward-penalty Dice loss (RPDL) function as the optimization objective for deep convolut..

View full abstract


Awarded by Australian Research Council

Funding Acknowledgements

We truly appreciated great cooperation with 7 anonymous surgeons at the Royal Victorian Eye and Ear Hospital, who helped us perform, validate and grade CM surgeries in the VRTBS simulator. We were grateful for 9 anonymous patients who provided their CT-scan temporal bone images for our research. This research was supported by the Melbourne Research Scholarship. This research was undertaken using the LIEF HPC-GPGPU Facility hosted at the University of Melbourne. This Facility was established with the assistance of LIEF Grant LE170100200.