Towards Accurate Medical Image Segmentation With Gradient-Optimized Dice Loss
- 1 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 191-195
Abstract
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.Keywords
Funding Information
- IEEE Publication Technology Department
This publication has 31 references indexed in Scilit:
- The Liver Tumor Segmentation Benchmark (LiTS)Medical Image Analysis, 2022
- X-Net: Multi-branch UNet-like network for liver and tumor segmentation from 3D abdominal CT scansNeurocomputing, 2021
- A contour-aware feature-merged network for liver segmentation based on shape prior knowledgeNeurocomputing, 2021
- Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNetNeurocomputing, 2021
- MSN-Net: a multi-scale context nested U-Net for liver segmentationSignal, Image and Video Processing, 2021
- Automatic liver segmentation from abdominal CT volumes using improved convolution neural networksMultimedia Systems, 2020
- CT liver tumor segmentation hybrid approach using neutrosophic sets, fast fuzzy c-means and adaptive watershed algorithmArtificial Intelligence in Medicine, 2019
- BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation2018
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- Automatic 3D liver location and segmentation via convolutional neural network and graph cutInternational Journal of Computer Assisted Radiology and Surgery, 2016