掷骰子
分割
计算机科学
人工智能
图像分割
卷积神经网络
特征(语言学)
模式识别(心理学)
尺度空间分割
图像(数学)
计算机视觉
基于分割的对象分类
功能(生物学)
医学影像学
数学
语言学
哲学
几何学
进化生物学
生物
出处
期刊:IEEE Signal Processing Letters
[Institute of Electrical and Electronics Engineers]
日期:2023-01-01
卷期号:: 1-5
标识
DOI:10.1109/lsp.2023.3329437
摘要
Medical image segmentation plays an important role in medical diagnosis, and has received extensive attention in recent years. A large number of convolutional neural network based methods have been proposed to achieve accurate segmentation results. Dice loss is the most popular loss function for medical image segmentation tasks. However, we found that Dice loss suffers from abnormal gradient changes, which causes the loss function to be unstable and difficult to converge. Therefore, we propose a gradient-optimized Dice loss (GODC) to solve this problem. GODC corrects the abnormal gradient changes in the segmentation loss, which accelerates the model convergence and can achieve better segmentation performance. Next, we propose a lateral feature alignment module (LFAM). LFAM adopts deformable convolutional network to align the features of different layers on the shortcut connections of U-Net to improve the segmentation performance. Finally, our method achieves state-of-the-art results on the LiTS dataset as well as our collected pancreatic tumor datasets.
科研通智能强力驱动
Strongly Powered by AbleSci AI