Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Enlarged Centrum Semiovale Perivascular Spaces as a Noninvasive Imaging Marker of Vascular Amyloid Deposition in Amyloid-Positive Individuals without Cerebral Amyloid Angiopathy-Related Hemorrhages.

Dementia and geriatric cognitive disorders extra·2026
Same author

Computerized Classification Method for Glioma Molecular Subtypes on Brain MR Images Using SAM-Med3D with Low-Rank Adaptation.

Journal of imaging informatics in medicine·2026
Same author

Self-folding graphene scaffolds with integrated electronics for cardiac tissue engineering.

Nanoscale·2026
Same author

In Vitro Reconstruction of Axonal Heat Sensing with a Photothermal Nerve-on-a-Chip.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Additional diagnostic value of lesion visibility on diffusion-weighted imaging for differentiating BI-RADS category 4 MRI-detected breast lesions.

Japanese journal of radiology·2026
Same author

Dual-encoder 3D transformer-based U-Net with temporal attention for non-mass enhancement segmentation in breast dynamic contrast-enhanced MRI.

Radiological physics and technology·2026

相关实验视频

Updated: Jul 1, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.5K

乳房DCE-MRI图像非质量的计算机化细分方法使用ResUNet++与切片序列学习和跨相卷积.

Akiyoshi Hizukuri1, Ryohei Nakayama2, Mariko Goto3

  • 1Department of Electronic and Computer Engineering, Ritsumeikan University, 1-1-1 Noji-Higashi, Kusatsu, Shiga, 525-8577, Japan. hizukuri@fc.ritsumei.ac.jp.

Journal of imaging informatics in medicine
|March 5, 2024
PubMed
概括

使用ResUNet++和十字相卷积的新计算机化方法在乳腺MRI扫描中准确地细分非质量. 这种方法增强了检测和形状分析,以改善差异诊断.

关键词:
乳房磁共振成像 乳房磁共振成像卷积神经网络是一种卷积神经网络.交相卷积的交相卷积是可以实现的.没有质量的非质量切片序列的学习学习

更多相关视频

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

490
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.4K

相关实验视频

Last Updated: Jul 1, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.5K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

490
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.4K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 在瘤学瘤学.

背景情况:

  • 在动态对比增强磁共振成像 (DCE-MRI) 中,准确的非质量细分对于乳腺癌诊断至关重要.
  • 现有的细分方法往往难以有效利用多相DCE-MRI中存在的时间信息.
  • 开发先进的计算工具对于提高非质量分析的准确性和效率至关重要.

研究的目的:

  • 开发和评估一种新的计算机化细分方法,用于乳房DCE-MRI中的非质量.
  • 将时间信息分析纳入使用切片序列学习和跨相卷积.
  • 为了提高非质量检测和形状表征的准确性.

主要方法:

  • 使用ResUNet++架构,增强了切片序列学习和跨相卷积.
  • 通过从不同MRI阶段的顺序ROI切片图像中创建3D张量器来捕获时间信息.
  • 在解码器中集成了一个卷积式长期短期记忆层,用于分析图像序列.

主要成果:

  • 拟议的方法实现了平均90.5%的非质量检测精度.
  • 性能指标包括Jaccard系数 (0.563),子相似系数 (0.712),正预测值 (0.714) 和灵敏度 (0.727) 超过了3D U-Net,V-Net和nnFormer的性能指标.
  • 该方法表现出高的检测和形状准确性,平均1.91个假阳性.

结论:

  • 开发的基于ResUNet++的方法通过利用时间信息,有效地对DCE-MRI中的非质量进行细分.
  • 跨相卷积和卷积LSTM的集成显著提高了细分性能.
  • 这种技术在临床实践中显示出有助于对非质量的差异诊断的前景.