Saved in:
Bibliographic Details
Main Authors: Jiang, Lan, Zheng, Yuchao, Yu, Miao, Zhang, Haiqing, Aladwani, Fatemah, Perelli, Alessandro
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.14418
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913582816428032
author Jiang, Lan
Zheng, Yuchao
Yu, Miao
Zhang, Haiqing
Aladwani, Fatemah
Perelli, Alessandro
author_facet Jiang, Lan
Zheng, Yuchao
Yu, Miao
Zhang, Haiqing
Aladwani, Fatemah
Perelli, Alessandro
contents 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%.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14418
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multimodal 3D Brain Tumor Segmentation with Adversarial Training and Conditional Random Field
Jiang, Lan
Zheng, Yuchao
Yu, Miao
Zhang, Haiqing
Aladwani, Fatemah
Perelli, Alessandro
Image and Video Processing
Computer Vision and Pattern Recognition
15-11
I.4.6; I.5.4
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%.
title Multimodal 3D Brain Tumor Segmentation with Adversarial Training and Conditional Random Field
topic Image and Video Processing
Computer Vision and Pattern Recognition
15-11
I.4.6; I.5.4
url https://arxiv.org/abs/2411.14418