相关实验视频

Updated: Jun 18, 2025

Training Dogs for Awake, Unrestrained Functional Magnetic Resonance Imaging

Training Dogs for Awake, Unrestrained Functional Magnetic Resonance Imaging

Published on: October 13, 2019

让UNet玩一个对抗游戏:研究对抗训练对提高低分辨率MRI功能的影响

Mohammad Javadi¹, Rishabh Sharma¹, Panagiotis Tsiamyrtzis^2,3

¹Medical Robotics and Imaging Lab, Department of Computer Science, University of Houston, 501, Philip G. Hoffman Hall, 4800 Calhoun Road, Houston, TX, 77204, USA.

Journal of imaging informatics in medicine

|July 31, 2024

概括

敌对训练通过改进低分辨率和低信号噪声比 (SNR) 数据来增强磁共振图像. 这种方法优化了图像质量指标,表明其对临床MRI增强管道的巨大潜力.

科学领域:

医疗成像医学成像
人工智能的人工智能
图像处理图像处理

背景情况:

对抗训练广泛用于图像现实主义,但在临床成像中尚未探索.
磁共振成像 (MRI) 通常存在低分辨率和低信号噪声比 (SNR).

研究的目的:

调查对抗训练对提高低分辨率和低SNRMRI的有效性.
优化对抗和感知损失权重,以改善临床图像.

主要方法:

在OASIS-1数据集上训练了206个网络,其知觉/对抗性损失权重和学习率各不相同.
引入了梯度错误 (GE),度和边缘对比错误 (ECE) 的指标.
评估了结构差异,边缘清晰度和像素分布扭曲.

主要成果:

优化对抗性损失减少了结构差异 (平均SSIM减少1.5%).
敌对训练显著降低了GE (p <0.05) 并增加了度.
在较低的感知损失重量时观察到ECE的减少,在较高的重量时没有显著的不良影响.

结论:

反对训练显著改善了MRI增强管道.
突出了在临床成像中对超参数优化和新型图像质量指标的需求.

关键词:

对抗性损失的损失.生成性的对抗性网络.混合效果建模混合效果建模真正的 - - 埃斯格兰.联合国网络联合国网络联合国网络

更多相关视频

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

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

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...