相关实验视频

Updated: Jul 27, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

基于深度学习方法的瘤PET成像定量准确性的比较研究

Yiyi Hu^1,2,3, Doudou Lv^1,2,3, Shaojie Jian^1,2,3

¹Department of Nuclear Medicine, First Hospital of Shanxi Medical University, Shanxi Medical University, Taiyuan, China.

Quantitative imaging in medicine and surgery

|June 7, 2023

概括

像3D Unet和P2P这样的深度学习模型可以通过减少扫描时间来显著提高[18F]氧糖 (FDG) PET/CT图像质量. 3D Unet 模型在瘤病变的对比度和噪声比率上表现出卓越的增强,满足了临床诊断需求.

科学领域:

医疗成像医学成像
放射学放射学是一门学科.
人工智能在医学中的应用

背景情况:

[18F]氧葡萄糖 (FDG) PET/CT对于瘤评估至关重要.
减少扫描时间和放射性追踪剂剂量是关键的挑战.
深度学习为优化PET/CT协议提供解决方案.

研究的目的:

评估深度学习模型,用于从低剂量采集中重建全剂量[18F]FDG PET/CT图像.
为了比较卷积神经网络 (CNN) 和生成对立网络 (GAN) 架构的性能.
为了确定加速PET/CT成像的最佳神经网络.

主要方法:

对接受[18F]FDG PET/CT的311名瘤患者的回顾性分析.
模拟低剂量PET图像使用15秒和30秒的每一个3分钟床上获取.
应用3D Unet (CNN) 和P2P (GAN) 来从低剂量输入中预测全剂量图像.
比较图像质量得分,噪声水平和定量瘤参数.

主要成果:

在所有深度学习组的图像质量得分中具有很高的一致性 (Kappa=0.719).
3D Unet 和 P2P 模型都降低了背景噪声和增加了信号对噪声比 (SNR).
与标准协议相比,3D Unet显著提高了对比度和噪声比率 (CNR),并保持了定量准确性 (SUVmean,SUVmax).

结论:

生成对抗网络 (GAN) 和卷积神经网络 (CNN) 模型有效地减少噪音并提高 [18F]FDG PET/CT.中的图像质量.
3D Unet在改善瘤病变的CNR,同时保持定量准确度方面表现出色,使其适用于缩短扫描时间的临床诊断.

关键词:

阳位子辐射断层扫描/计算机断层扫描 (PET/CT)深度学习是一种深度学习.低剂量成像的成像学量化量化量化量化量化量化量化量化量化量化量化量化量瘤的量化瘤的量化

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

Author Spotlight: Standardizing Mouse In Vivo PET Imaging with Body Conforming Molds and Automated Analysis

Author Spotlight: Standardizing Mouse In Vivo PET Imaging with Body Conforming Molds and Automated Analysis

Published on: October 25, 2024

相关概念视频

Positron Emission Tomography

Positron Emission Tomography

Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...