Related Experiment Video
Updated: Sep 26, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.0K
Residual based attention-Unet combing DAC and RMP modules for automatic liver tumor segmentation in CT
Rongrong Bi1, Chunlei Ji1, Zhipeng Yang2
1Department of Software Engineering, Harbin University of Science and Technology, Rongcheng 264300, China.
Mathematical Biosciences and Engineering : MBE
|April 18, 2022
Summary
This study introduces ResCEAttUnet, a novel deep learning network for improved liver tumor segmentation from CT scans. The method enhances accuracy, offering a promising tool for clinical assistance in liver tumor detection.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Accurate liver tumor segmentation is crucial for clinical decision-making.
- Current segmentation methods struggle with the complex distribution of liver tumors in abdominal CT scans.
Purpose of the Study:
- To develop a novel end-to-end deep learning network to enhance the accuracy of liver tumor segmentation from CT images.
- To address the limitations of existing methods in capturing complex tumor structures.
Main Methods:
- Proposed a hybrid network, ResCEAttUnet, integrating residual blocks, context encoder (CE), and Attention-Unet.
- The CE module includes dense atrous convolution (DAC) for semantic information and residual multi-kernel pooling (RMP) for multi-scale feature extraction.
- Employed a hybrid loss function combining cross-entropy and Tversky loss for optimized training.
Main Results:
- The ResCEAttUnet model demonstrated significantly improved segmentation accuracy compared to state-of-the-art methods on the LiTS17 and 3DIRCADb datasets.
- Quantitative and qualitative analyses confirmed the effectiveness of the proposed method.
Conclusions:
- The ResCEAttUnet network offers a promising advancement in automated liver tumor segmentation.
- The method shows potential as a valuable tool for clinical assistance in liver cancer diagnosis and treatment planning.
