Learning Non-Unique Segmentation with Reward-Penalty Dice Loss

2020-09-23 · Jiabo He, Sarah Erfani, Sudanthi Wijewickrema, Stephen O'Leary, Kotagiri Ramamohanarao

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 convolutional neural networks (DCNN). RPDL is capable of helping DCNN learn non-unique segmentation by enhancing common regions and penalizing outside ones. Experimental results show that RPDL improves the performance of DCNN models by up to 18.4% compared with other loss functions on our collected surgical dataset.

📄 PDF Abstract BibTeX arXiv:2009.10987

Code (1)

Jacobi93/Reward-penalty-Dice-loss 공식 구현 tf

Tasks

Medical Image Segmentation Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Dice Loss \begin{equation} DiceLoss\left( y, \overline{p} \right) = 1 - \dfrac{\left( 2y\overline{p} + 1 \right)} {\left( y+\overline{p } + 1 \right)} \end{equation}

DCNN Diffusion-convolutional neural networks (DCNN) is a model for graph-structured data. Through the introduction of a diffusion-convolution operation, diffusion-based representations…

Distance Map Loss Penalty Term for Semantic Segmentation

2019-08-10 · Francesco Caliva, Claudia Iriondo, Alejandro Morales Martinez, Sharmila Majumdar 외

Convolutional neural networks for semantic segmentation suffer from low performance at object boundaries. In medical imaging, accurate representation of tissue surfaces and volumes is important for tracking of disease bi…

Segmentation Semantic Segmentation

Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Losses

2021-04-18 · Bingyuan Liu, Jose Dolz, Adrian Galdran, Riadh Kobbi 외

Most segmentation losses are arguably variants of the Cross-Entropy (CE) or Dice losses. On the surface, these two categories of losses seem unrelated, and there is no clear consensus as to which category is a better cho…

Calibrating the Dice loss to handle neural network overconfidence for biomedical image segmentation

2021-10-31 · Michael Yeung, Leonardo Rundo, Yang Nan, Evis Sala 외

The Dice similarity coefficient (DSC) is both a widely used metric and loss function for biomedical image segmentation due to its robustness to class imbalance. However, it is well known that the DSC loss is poorly calib…

Image Segmentation Segmentation Semantic Segmentation

Support Vector Regression via a Combined Reward Cum Penalty Loss Function

2019-04-28 · Pritam Anand, Reshma Rastogi, Suresh Chandra

In this paper, we introduce a novel combined reward cum penalty loss function to handle the regression problem. The proposed combined reward cum penalty loss function penalizes the data points which lie outside the $\eps…

regression

Incorporating Boundary Uncertainty into loss functions for biomedical image segmentation

2021-10-31 · Michael Yeung, Guang Yang, Evis Sala, Carola-Bibiane Schönlieb 외

Manual segmentation is used as the gold-standard for evaluating neural networks on automated image segmentation tasks. Due to considerable heterogeneity in shapes, colours and textures, demarcating object boundaries is p…