Abstract
The segmentation of liver tumors is crucial for diagnosis, treatment planning and treatment evaluation. Due to the setbacks that the manual segmentation brings, automatic segmentation has recently gained a lot of attention. In this work, we explore various deep learning based approaches to address automatic liver tumor segmentation. We use the data from the Liver Tumor Segmentation challenge (LiTS). In particular, the considered models here are UNet-based architectures. In addition, we investigate the influence of incorporating extra elements to the pipeline such as attention mechanisms, model ensemble, test-time inference as well as an additional model to reject false positives, over the final performance. The obtained results show that the 3D-UNet architecture, together with ensemble learning methods, performs more accurate predictions than the other examined approaches.
Original language | English |
---|---|
Title of host publication | 2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) |
Publisher | IEEE |
Number of pages | 8 |
ISBN (Print) | 9780738133669 |
DOIs | |
Publication status | Published - 2021 |
Event | International Joint Conference on Neural Networks - Online, United States Duration: 18 Jul 2021 → 22 Jul 2021 https://www.ijcnn.org/ |
Conference
Conference | International Joint Conference on Neural Networks |
---|---|
Abbreviated title | IJCNN 2021 |
Country/Territory | United States |
Period | 18/07/21 → 22/07/21 |
Internet address |
Keywords
- Medical imaging
- Liver tumor segmentation
- Deep learning
- Convolutional neural network
- U-Net