2022
DOI: 10.1016/j.compmedimag.2021.102026
|View full text |Cite
|
Sign up to set email alerts
|

Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation

Abstract: Automatic segmentation methods are an important advancement in medical image analysis. Machine learning techniques, and deep neural networks in particular, are the state-of-the-art for most medical image segmentation tasks. Issues with class imbalance pose a significant challenge in medical datasets, with lesions often occupying a considerably smaller volume relative to the background. Loss functions used in the training of deep learning algorithms differ in their robustness to class imbalance, with direct con… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

2
150
0
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
8
1
1

Relationship

0
10

Authors

Journals

citations
Cited by 320 publications
(153 citation statements)
references
References 67 publications
2
150
0
1
Order By: Relevance
“…Lu et al reported concurring results for a similar loss function when applied to 3D stroke lesion segmentation in T1 weighted MR images [25] . In future work it would be of interest to evaluate the recently introduced “Unified Focal” loss function which performs well for highly imbalanced class segmentation [26] .…”
Section: Discussionmentioning
confidence: 99%
“…Lu et al reported concurring results for a similar loss function when applied to 3D stroke lesion segmentation in T1 weighted MR images [25] . In future work it would be of interest to evaluate the recently introduced “Unified Focal” loss function which performs well for highly imbalanced class segmentation [26] .…”
Section: Discussionmentioning
confidence: 99%
“…The Lovász-Softmax loss 46 is another way to obtain a surrogate function of the dice coefficient. There are also many extensions to dice loss 47,48 that could be considered in further work.…”
Section: Discussionmentioning
confidence: 99%
“…Recent works [42,43] have proved that the compound loss function, especially the dice-related compound loss function, is a better choice to improve the segmentation effect compared with a single loss function, so we deployed a combo loss function for segmentation supervision. The combo loss function in this paper consists of two parts: BCE (Binary Cross Entropy) loss and DSC (Dice Similarity Coefficient) loss.…”
Section: Combo Loss Functionmentioning
confidence: 99%