Loss odyssey in medical image segmentation

Ma, Jun; Chen, Jianan; Ng, Matthew; Huang, Rui; Li, Yu; Li, Chen; Yang, Xiaoping; Martel, Anne L.

doi:10.1016/j.media.2021.102035

Cited by 343 publications

(210 citation statements)

References 17 publications

Supporting

Mentioning

173

Contrasting

Order By: Relevance

“…Researchers can obtain higher segmentation accuracy by selecting the appropriate loss functions to optimize the network model. According to the derivation of the loss function [46], they can be divided into four categories: distribution-based loss, region-based loss, boundary-based loss and compound loss. Cross-entropy is a common distribution-based loss and it optimized the networks by minimizing dissimilarity between two distributions.…”

Section: The Loss Function For Network Optimizationmentioning

confidence: 99%

Boundary Loss-Based 2.5D Fully Convolutional Neural Networks Approach for Segmentation: A Case Study of the Liver and Tumor on Computed Tomography

Han

Wang

et al. 2021

Algorithms

View full text Add to dashboard Cite

Image segmentation plays an important role in the field of image processing, helping to understand images and recognize objects. However, most existing methods are often unable to effectively explore the spatial information in 3D image segmentation, and they neglect the information from the contours and boundaries of the observed objects. In addition, shape boundaries can help to locate the positions of the observed objects, but most of the existing loss functions neglect the information from the boundaries. To overcome these shortcomings, this paper presents a new cascaded 2.5D fully convolutional networks (FCNs) learning framework to segment 3D medical images. A new boundary loss that incorporates distance, area, and boundary information is also proposed for the cascaded FCNs to learning more boundary and contour features from the 3D medical images. Moreover, an effective post-processing method is developed to further improve the segmentation accuracy. We verified the proposed method on LITS and 3DIRCADb datasets that include the liver and tumors. The experimental results show that the performance of the proposed method is better than existing methods with a Dice Per Case score of 74.5% for tumor segmentation, indicating the effectiveness of the proposed method.

show abstract

Section: The Loss Function For Network Optimizationmentioning

confidence: 99%

Boundary Loss-Based 2.5D Fully Convolutional Neural Networks Approach for Segmentation: A Case Study of the Liver and Tumor on Computed Tomography

Han

Wang

et al. 2021

Algorithms

View full text Add to dashboard Cite

show abstract

“…The traditional medical image segmentation approach uses basic loss functions such as MSE, CE, and Dice, which are also used in image classification and object detection. Many loss functions specializing in boundary distinctions have recently been researched [12]. For example, Kervadec et al [20] effectively distinguished the boundaries of brain tumors by calculating the difference between the area predicted by a neural network and the ground truth area using the differential framework.…”

Section: Related Workmentioning

confidence: 99%

“…Dice loss uses the Dice coefficient between the value predicted by the CNN and the ground truth for learning. Currently, novel loss functions based on the differential framework or distance maps are also being researched in addition to these traditional loss functions [12]. This paper proposes a loss function to facilitate effective discernment of the boundaries of organs and abnormal objects (e.g., tumor) in 2D images.…”

Section: Introductionmentioning

confidence: 99%

A Simple Generic Method for Effective Boundary Extraction in Medical Image Segmentation

Kim

Lee

2021

IEEE Access

View full text Add to dashboard Cite

Accurate identification of the shape and position of organs or abnormal objects (e.g., tumors) in medical images plays an important role in surgical planning as well as in the diagnosis and prognosis of diseases. However, this is difficult to achieve from two-dimensional medical images owing to their inaccurate and ambiguous organ boundaries. Further, traditional image processing-based boundary detection methods such as the Canny edge detector and Sobel operator exhibit low boundary detection performance for images with substantial noise. Recently, the use of deep learning has resulted in improvements in semantic segmentation in medical images. In this paper, we propose a generic boundary-aware loss function to facilitate effective discernment of the boundaries of organs and abnormal objects in medical images. Specifically, the proposed loss function introduces a boundary area and assigns higher weights on the loss of pixels located on the boundary area than pixels on nonboundary areas, thereby promoting effective learning in the boundary area. The results of experiments conducted using public medical datasets comprising colon polyp, skin lesion, and chest X-ray data indicate that the standard loss functions, such as cross entropy loss and Dice loss, combined with the proposed boundary-aware loss function achieve comparable or better performance than those without the boundary-aware loss function.

show abstract

“…Thus far, various types of loss functions [11][12][13][14][15][16][17] and loss weighting strategies [4,[18][19][20][21][22][23][24][25] have been proposed to alleviate the class imbalance problem. They can be applied for any medical image segmentation tasks in a plug-and-play fashion [26]. However, it is unclear which loss function and weighting strategy should be used in different situations.…”

Section: Introductionmentioning

confidence: 99%

“…In related works, Ma et al [26] performed a systematic study of the utility of 20 loss functions on typical segmentation tasks using public datasets and evaluated the performance of these loss functions in the imbalanced segmentation tasks. Moreover, Ma et al [27] compared and evaluated the boundary-based loss functions, which minimize the distance between boundaries of ground-truth and predicted segmentation labels, in an empirical study.…”

Section: Introductionmentioning

confidence: 99%

Loss Weightings for Improving Imbalanced Brain Structure Segmentation Using Fully Convolutional Networks

et al. 2021

View full text Add to dashboard Cite

Brain structure segmentation on magnetic resonance (MR) images is important for various clinical applications. It has been automatically performed by using fully convolutional networks. However, it suffers from the class imbalance problem. To address this problem, we investigated how loss weighting strategies work for brain structure segmentation tasks with different class imbalance situations on MR images. In this study, we adopted segmentation tasks of the cerebrum, cerebellum, brainstem, and blood vessels from MR cisternography and angiography images as the target segmentation tasks. We used a U-net architecture with cross-entropy and Dice loss functions as a baseline and evaluated the effect of the following loss weighting strategies: inverse frequency weighting, median inverse frequency weighting, focal weighting, distance map-based weighting, and distance penalty term-based weighting. In the experiments, the Dice loss function with focal weighting showed the best performance and had a high average Dice score of 92.8% in the binary-class segmentation tasks, while the cross-entropy loss functions with distance map-based weighting achieved the Dice score of up to 93.1% in the multi-class segmentation tasks. The results suggested that the distance map-based and the focal weightings could boost the performance of cross-entropy and Dice loss functions in class imbalanced segmentation tasks, respectively.

show abstract

Loss odyssey in medical image segmentation

Cited by 343 publications

References 17 publications

Boundary Loss-Based 2.5D Fully Convolutional Neural Networks Approach for Segmentation: A Case Study of the Liver and Tumor on Computed Tomography

Boundary Loss-Based 2.5D Fully Convolutional Neural Networks Approach for Segmentation: A Case Study of the Liver and Tumor on Computed Tomography

A Simple Generic Method for Effective Boundary Extraction in Medical Image Segmentation

Loss Weightings for Improving Imbalanced Brain Structure Segmentation Using Fully Convolutional Networks

Contact Info

Product

Resources

About