.png){kind=icon}
返回
Artificial Intelligence Generated Data Augmentation for Abdominal Multi-Organ Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TCE.2024.3421266.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Artificial intelligence (AI) generation in medical image synthesis provides a more accurate and efficient method for medical image analysis. Medical image segmentation can assist doctors in identifying and locating lesions, organs, and tissues to improve the accuracy of disease diagnosis. However, medical images have issues such as scarcity, fuzzy boundaries and intra-class heterogeneity. In this paper, we propose a multi-organ segmentation algorithm for abdominal magnetic resonance imaging (MRI) images based on AI generation. The algorithm consists of a data augmentation module and a segmentation network. In the data augmentation part, traditional methods and an improved Pix2pix synthesize training images using the sample labels. The generated images and original samples are then put into the improved U-Net for training the segmentation model. Comparative experiments demonstrate the effectiveness and advantages of the proposed algorithm.
Keyword:
Image segmentation
Data augmentation
Training
Medical diagnostic imaging
Data models
Magnetic resonance imaging
Computational modeling
Multi-organ segmentation
AI generated Images
data augmentation
smart healthcare
affine transformations
期刊
IF:
10.9
论文数:
5.3K
被引数:
6.8K
机构
引用论文
Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏
分享收藏Cross-Modality LGE-CMR Segmentation Using Image-to-Image Translation Based Data Augmentation使用基于图像到图像转换的数据增强的跨模态lge-cmr分割
PREAI
分享收藏A Robust Deep Learning Framework Based on Spectrograms for Heart Sound Classification一种基于声谱图的鲁棒深度学习心音分类框架
PREAI
分享收藏
查看更多内容