A5004603487- Medical Imaging and Analysis
- Spine and Intervertebral Disc Pathology
- Brain Tumor Detection and Classification
Qingdao University of Science and Technology
2022
Lumbar spine segmentation is important to help doctors diagnose lumbar disc herniation (LDH) and patients' rehabilitation treatment. In order accurately segment the spine, a image algorithm based on improved Attention U-Net proposed. The U-Net, attention module multilevel feature map fusion adopted, two residual modules are introduced instead of original convolution blocks. hybrid loss function used for prediction during training process, finally, superposition process realized. this...
To realize the automatic symptom recognition and classification of MR images improve accuracy efficiency diagnosis lumbar intervertebral disc herniation (LDH), a method for disease is proposed in this paper. The mainly includes three steps: preprocessing, target segmentation, classification. Preprocessing performed by noise reduction interference removal methods blurred images. contour poles are used to determine four points tail vertebra order reduce wrong segmentation vertebra. A based on...