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

Yeung, Michael; Sala, Evis; Schönlieb, Carola‐Bibiane; Rundo, Leonardo

doi:10.1016/j.compmedimag.2021.102026

Cited by 320 publications

(153 citation statements)

References 67 publications

Supporting

Mentioning

150

Contrasting

Unclassified

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%

Optimising a 3D convolutional neural network for head and neck computed tomography segmentation with limited training data

Henderson¹,

Osorio²,

Herk³

et al. 2022

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Optimising a 3D convolutional neural network for head and neck computed tomography segmentation with limited training data

Henderson¹,

Osorio²,

Herk³

et al. 2022

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

“…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%

Effect of the output activation function on the probabilities and errors in medical image segmentation

Nieradzik,

Scheuermann,

Saur

et al. 2021

Preprint

View full text Add to dashboard Cite

The sigmoid activation is the standard output activation function in binary classification and segmentation with neural networks. Still, there exist a variety of other potential output activation functions, which may lead to improved results in medical image segmentation. In this work, we consider how the asymptotic behavior of different output activation and loss functions affects the prediction probabilities and the corresponding segmentation errors. For cross entropy, we show that a faster rate of change of the activation function correlates with better predictions, while a slower rate of change can improve the calibration of probabilities. For dice loss, we found that the arctangent activation function is superior to the sigmoid function. Furthermore, we provide a test space for arbitrary output activation functions in the area of medical image segmentation. We tested seven activation functions in combination with three loss functions on four different medical image segmentation tasks to provide a classification of which function is best suited in this application scenario.

show abstract

“…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%

SD-UNet: A Novel Segmentation Framework for CT Images of Lung Infections

Yin

Deng

et al. 2022

Electronics

View full text Add to dashboard Cite

Due to the outbreak of lung infections caused by the coronavirus disease (COVID-19), humans have to face an unprecedented and devastating global health crisis. Since chest computed tomography (CT) images of COVID-19 patients contain abundant pathological features closely related to this disease, rapid detection and diagnosis based on CT images is of great significance for the treatment of patients and blocking the spread of the disease. In particular, the segmentation of the COVID-19 CT lung-infected area can quantify and evaluate the severity of the disease. However, due to the blurred boundaries and low contrast between the infected and the non-infected areas in COVID-19 CT images, the manual segmentation of the COVID-19 lesion is laborious and places high demands on the operator. Quick and accurate segmentation of COVID-19 lesions from CT images based on deep learning has drawn increasing attention. To effectively improve the segmentation effect of COVID-19 lung infection, a modified UNet network that combines the squeeze-and-attention (SA) and dense atrous spatial pyramid pooling (Dense ASPP) modules) (SD-UNet) is proposed, fusing global context and multi-scale information. Specifically, the SA module is introduced to strengthen the attention of pixel grouping and fully exploit the global context information, allowing the network to better mine the differences and connections between pixels. The Dense ASPP module is utilized to capture multi-scale information of COVID-19 lesions. Moreover, to eliminate the interference of background noise outside the lungs and highlight the texture features of the lung lesion area, we extract in advance the lung area from the CT images in the pre-processing stage. Finally, we evaluate our method using the binary-class and multi-class COVID-19 lung infection segmentation datasets. The experimental results show that the metrics of Sensitivity, Dice Similarity Coefficient, Accuracy, Specificity, and Jaccard Similarity are 0.8988 (0.6169), 0.8696 (0.5936), 0.9906 (0.9821), 0.9932 (0.9907), and 0.7702 (0.4788), respectively, for the binary-class (multi-class) segmentation task in the proposed SD-UNet. The result of the COVID-19 lung infection area segmented by SD-UNet is closer to the ground truth compared to several existing models such as CE-Net, DeepLab v3+, UNet++, and other models, which further proves that a more accurate segmentation effect can be achieved by our method. It has the potential to assist doctors in making more accurate and rapid diagnosis and quantitative assessment of COVID-19.

show abstract

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

Cited by 320 publications

References 67 publications

Optimising a 3D convolutional neural network for head and neck computed tomography segmentation with limited training data

Optimising a 3D convolutional neural network for head and neck computed tomography segmentation with limited training data

Effect of the output activation function on the probabilities and errors in medical image segmentation

SD-UNet: A Novel Segmentation Framework for CT Images of Lung Infections

Contact Info

Product

Resources

About