Multimodal 3D Brain Tumor Segmentation Using a 3D Volume Generative Adversarial Network (3D-vGAN) with Adversarial Training and Conditional Random Field
This research paper introduces 3D-vGAN, a novel deep learning model for accurate brain tumor segmentation in 3D MRI images, leveraging the strengths of V-Net, Generative Adversarial Networks (GANs), and Conditional Random Fields (CRFs) to achieve high accuracy.
Automatic Brain Tumor Segmentation in 2D Intra-operative Ultrasound Images: Utilizing MRI Tumor Annotations to Overcome Limited Annotated Datasets
MRI tumor annotations can be used as an effective substitute for US tumor annotations in training deep learning models for automatic brain tumor segmentation in intra-operative ultrasound images, particularly for larger tumors.
MBDRes-U-Net: A Lightweight 3D Brain Tumor Segmentation Network Using Multi-Branch Residual Blocks and Fused Attention
The MBDRes-U-Net model achieves accurate brain tumor segmentation from multimodal MRI images while significantly reducing computational complexity compared to traditional 3D U-Net models.
Automated and Editable Prompt Learning (AEPL) for Enhanced Brain Tumor Segmentation Using MRI
Integrating tumor grade prediction as automatically generated and editable prompts in a multi-task learning framework improves the accuracy and flexibility of brain tumor segmentation in MRI.
Enhancing Brain Tumor Segmentation with Multiscale Attention and Omni-Dimensional Dynamic Convolution in nnU-Net
The proposed algorithm utilizes a modified nnU-Net architecture with multiscale attention and Omni-Dimensional Dynamic Convolution (ODConv3D) layers to enhance the accuracy of brain tumor segmentation across diverse datasets, including Brain Metastases and BraTS-Africa.
SEDNet: A Computationally Efficient Shallow Encoder-Decoder Network for Accurate Brain Tumor Segmentation
The proposed SEDNet architecture, with its shallow encoder-decoder design and selective skip paths, achieves impressive brain tumor segmentation performance while being computationally efficient for real-time clinical diagnosis.
Optimizing Brain Tumor Segmentation Through CNN U-Net with Hybrid Image Enhancement Techniques
Hybrid image enhancement techniques, combining Histogram Equalization (HE) and Contrast Limited Adaptive Histogram Equalization (CLAHE), consistently outperform individual methods in improving the accuracy of CNN-based brain tumor segmentation using the U-Net architecture.
Brain Tumor Segmentation Using Deep Learning and Attention Mechanisms
Automated brain tumor segmentation using deep learning and attention mechanisms improves accuracy and reduces computation.
Attention-Enhanced Hybrid Feature Aggregation Network for 3D Brain Tumor Segmentation
Utilizing a hybrid U-Net-shaped model with attention-guided features, the GLIMS approach enhances 3D brain tumor segmentation performance.
© 2024 by Linnk AI