mlsanityData to 14 Oct 2026

Multimodal 3D Brain Tumor Segmentation with Adversarial Training and Conditional Random Field

arXiv 2411.14418 ↗First posted 21 Nov 2024eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate brain tumor segmentation remains a challenging task due to structural complexity and great individual differences of gliomas. Leveraging the pre-eminent detail resilience of CRF and spatial feature extraction capacity of V-net, we propose a multimodal 3D Volume Generative Adversarial Network (3D-vGAN) for precise segmentation. The model utilizes Pseudo-3D for V-net improvement, adds conditional random field after generator and use original image as supplemental guidance. Results, using the BraTS-2018 dataset, show that 3D-vGAN outperforms classical segmentation models, including U-net, Gan, FCN and 3D V-net, reaching specificity over 99.8%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 21 references that are in the map. First posted on arXiv 21 Nov 2024.

Builds on

10 of 21 references.

References · 10

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  5. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  6. 2017Learning Spatio-Temporal Representation with Pseudo-3D Residual Networkscited by 387
  7. 2015Conditional Random Fields as Recurrent Neural Networkscited by 214
  8. 2015Brain Tumor Segmentation with Deep Neural Networkscited by 137
  9. 2020Vox2Vox: 3D-GAN for Brain Tumour Segmentationcited by 30
  10. 20213D AGSE-VNet: An Automatic Brain Tumor MRI Data Segmentation Frameworkcited by 9

Built on by

Not cited yet.