相关实验视频

Updated: Jun 25, 2025

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

在神经/辐射瘤学中,使用无监督深度学习进行磁共振图像的可变形记录

Alexander F I Osman¹, Kholoud S Al-Mugren², Nissren M Tamam²

¹Department of Medical Physics, Al-Neelain University, Khartoum, 11121, Sudan. alexanderfadul@yahoo.com.

Radiation oncology (London, England)

|May 22, 2024

概括

一种新的深度学习方法,ConvUNet-DIR,准确地记录了质瘤患者的3D脑MRI. 这种自动化方法优于现有方法,提供高效和强大的可变形图像注册,无需人工干预.

科学领域:

医疗成像医学成像
人工智能的人工智能
神经科学是一个神经科学.

背景情况:

脑部MRI扫描与病理学的可变性注册是具有挑战性的,因为外观变化.
准确的图像记录对于跟踪质瘤患者的疾病进展和治疗反应至关重要.

研究的目的:

开发一种基于U-Net的自动化3D卷积可变形图像注册 (ConvUNet-DIR) 方法.
使用无监督学习在脑质瘤患者的基线手术前和随访MRI扫描之间建立对应.

主要方法:

使用3D U-Net架构进行特征学习和映射估计.
工作流包括一个网格生成器和空间转换层用于图像扭曲.
使用无监督学习与类似度作为损失函数和变形规范化的相似度.

主要成果:

在测试组中,ConvUNet-DIR实现了高准确度,平均子得分为0.975和SSIM为0.908.
该模型在Dice和SSIM指标上显著超过了VoxelMorph (VM1和VM2).
在CPU上,单个MRI对的注册在约1秒内完成.

结论:

开发的ConvUNet-DIR模型使得质瘤患者的3D脑MRI扫描能够进行端到端的自动可变形注册.
该方法提供了准确,高效和强大的注册,不需要预先调整或手动标签.
ConvUNet-DIR超越了最先进的VoxelMorph和其他基于深度学习的注册算法.

关键词:

卷积神经网络是一种卷积神经网络.可变形图像的注册方式质瘤是一种质瘤.这就是为什么MRI是MRI.神经/辐射瘤学没有监督的学习学习.

更多相关视频

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

相关概念视频

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...