Related Experiment Video
Updated: Jul 2, 2025
04:48
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
Published on: July 5, 2024
401
CRMEFNet: A coupled refinement, multiscale exploration and fusion network for medical image segmentation
Zhi Wang1, Long Yu2, Shengwei Tian1
1College of Software, Xinjiang University, Urumqi, 830000, China; Key Laboratory of Software Engineering Technology, Xinjiang University, Urumqi, 830000, China.
Computers in Biology and Medicine
|February 25, 2024
Summary
A new deep learning model, the coupled refinement and multiscale exploration and fusion network (CRMEFNet), improves medical image segmentation by optimizing multiscale features. This enhances lesion identification for better disease diagnosis and clinical analysis.
Area of Science:
- Medical Image Analysis
- Deep Learning
- Computer Vision
Background:
- Accurate medical image segmentation is crucial for disease diagnosis.
- Existing deep learning methods struggle with multilevel features and complex boundaries.
Purpose of the Study:
- To propose a novel network, CRMEFNet, for enhanced medical image segmentation.
- To address limitations in modeling multilevel features and identifying complex textured pixels.
Main Methods:
- Introduced a coupled refinement module (CRM) to decouple and optimize low-frequency body and high-frequency edge features.
- Developed a multiscale exploration and fusion module (MEFM) with an attention mechanism for adaptive feature fusion.
- Designed a cascaded progressive decoder (CPD) for fine-grained pixel recognition and semantic information retention.
Main Results:
- CRMEFNet demonstrated state-of-the-art performance across five medical image segmentation tasks.
- Achieved superior results on twelve comparison models and ten datasets.
- Validated the model's interpretability, flexibility, and versatility.
Conclusions:
- CRMEFNet effectively models multilevel features and refines segmentation boundaries.
- The proposed network offers a robust and versatile solution for medical image segmentation.
- CRMEFNet advances the capabilities of deep learning in clinical analysis.
