相关实验视频

Updated: Jun 10, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

MG-Net:一种基于多尺度特征融合和图形卷积注意力机制的胎儿大脑组织细分方法

Keying Qi¹, Chenchen Yan², Donghao Niu¹

¹Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China; Department of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China.

Computer methods and programs in biomedicine

|October 12, 2024

概括

这项研究引入了用于胎儿大脑组织细分的自动深度学习模型,显著提高了医疗专业人员的准确性和效率. 这种新的方法增强了特征提取,以提供更好的诊断支持.

科学领域:

医疗成像医学成像
神经科学是一个神经科学.
人工智能的人工智能

背景情况:

胎儿大脑组织细分对于理解神经发育和先天性疾病至关重要.
手动细分是耗时且具有挑战性的,原因是胎儿解剖学和组织的变化.
需要自动化方法来提高临床工作流程的效率和准确性.

研究的目的:

开发一种自动化的深度学习模型,以实现高效准确的胎儿大脑组织细分.
通过改进的细分工作流程,提高医疗专业人员的诊断能力.
为应对发育期间胎儿大脑组织动态变化所带来的挑战.

主要方法:

一个新的深度学习模型,将双扩展注意力区块 (DDAB) 纳入编码器,用于局部特征提取.
在全球信息处理的瓶中整合一个多尺度可变形变压器 (MSDT).
在解码器中使用图形卷积注意区块 (GCAB) 来增强特征表示.

主要成果:

拟议的模型在FeTA 2021和FeTA 2022数据集上进行了训练和测试.
在Dice,IoU和MAE指标中表现优于最先进的模型 (nnFormer,SwinUNETR,3DUX-net).
取得了高绩效,例如,FeTA 2021上的Dise为0.8666和IoU为0.7646,FeTA 2022上的Dise为0.8552和IoU为0.7470

结论:

开发了一种基于多尺度特征融合和图形卷积注意力的新型3D胎儿大脑组织细分模型.
该模型显示了提高胎儿大脑组织细分速度和准确性的巨大潜力.
准确的细分对于准确的诊断和对胎儿神经发育的理解至关重要.

关键词:

深度学习是一种深度学习.双扩张的注意力阻断.胎儿的核磁共振成像图形的卷积阻断了注意力.医疗图像细分医疗图像细分多尺度可变形变压器多尺度可变形变压器

更多相关视频

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关概念视频

Association Areas of the Cortex

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...