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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

7.0K
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...
7.0K
Imaging Studies I: CT and MRI01:14

Imaging Studies I: CT and MRI

443
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
443

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

MSCs/EVs-based therapy targeting DAD: research progress and future perspectives from ARDS and COVID-19 to RP-ILD.

Stem cell research & therapy·2026
Same author

Structure-guided design of ionizable lipids with distinct amine headgroups for muscle-selective mRNA delivery and enhanced antitumor immunotherapy.

Colloids and surfaces. B, Biointerfaces·2026
Same author

Chronic Kidney disease and cognitive frailty in aging: molecular crosstalk and clinical implications.

Frontiers in aging neuroscience·2026
Same author

Single-cell technologies drive mechanistic insights and therapeutic translation in skeletal system research.

iScience·2026
Same author

Immunoprotective effect of recombinant ubiquitin-conjugating enzyme (UCE) and elongation factor 1-alpha (EF1α) in rabbits against Eimeria media.

Veterinary parasitology·2026
Same author

Effects of cueing interventions on online learning outcomes: a meta-analytic review of 40 studies.

Frontiers in psychology·2026
Same journal

Accurate Segmentation and Three-dimensional Reconstruction Algorithm of Spinal Cord Injury Lesions Based on Multimodal Magnetic Resonance Imaging.

Current medical imaging·2026
Same journal

A Comprehensive Review of Radiomics in Pulmonary Nodule Management: Clinical Applications and Standardization Dilemmas.

Current medical imaging·2026
Same journal

The Value of a Predictive Model Based on Multimodal Ultrasound Imaging Biomarkers Combined with Clinical Features in the Diagnosis of Thyroid Nodules.

Current medical imaging·2026
Same journal

The Prognostic and Mutational Characteristics of Multiple Early-stage Lung Cancers Manifesting as Subsolid Nodules.

Current medical imaging·2026
Same journal

Dual-Database Bibliometric Analysis Combined with Gephi-Based Network Visualization of Artificial Intelligence Applications in the Identification and Diagnosis of Thyroid Space-Occupying Lesions.

Current medical imaging·2026
Same journal

An Efficient and Cohesive System for Enhanced Accuracy in Malignant Brain Tumor Diagnosis.

Current medical imaging·2026
查看所有相关文章

相关实验视频

Updated: Sep 13, 2025

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

13.0K

微粒原型网络用于MRI序列分类.

Chunbao Yuan1, Xibin Jia1, Luo Wang1

  • 1School of Computer Science, Beijing University of Technology, Beijing, China.

Current medical imaging
|August 4, 2025
PubMed
概括
此摘要是机器生成的。

SequencesNet是一种新的深度学习模型,通过捕捉微妙的细节,准确地分类腹部磁共振成像 (MRI) 序列. 这种方法通过有效处理MRI序列类型内和之间的变异来提高诊断准确性.

关键词:
核磁共振成像 (MRI) 序列分类分类深度学习. 深度学习.细粒度的学习学习.原型学习学习的原型学习.

更多相关视频

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

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

Published on: September 25, 2019

48.4K
Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra
05:14

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Published on: September 8, 2021

3.7K

相关实验视频

Last Updated: Sep 13, 2025

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

13.0K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

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

Published on: September 25, 2019

48.4K
Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra
05:14

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Published on: September 8, 2021

3.7K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 磁共振成像 (MRI) 对于临床诊断至关重要,提供各种组织和结构信息.
  • 传统的深度学习方法在MRI序列识别方面遇到了困难,原因是高的类内变化和微妙的类间差异.
  • 现有的模型往往忽略了精细细节,这些细节对于准确的MRI序列分类至关重要.

研究的目的:

  • 提出SequencesNet,一个精细的原型网络,用于改进MRI序列分类.
  • 解决腹部MRI序列中微妙的类间差异和显著的类内变异的挑战.
  • 为了提高基于深度学习的MRI序列识别的准确性和可解释性.

主要方法:

  • 开发了SequencesNet,将卷积神经网络 (CNN) 与改进的视觉转换器集成,用于特征提取.
  • 在视觉变压器中集成了一个特征选择模块 (FSM),以使用融合的注意力权重选择细粒度的特征.
  • 使用原型分类模块 (PCM) 来根据提取的细粒度表示来分类MRI序列.

主要成果:

  • 序列网实现了最先进的准确性,在公共数据集上达到96.73%,在私人数据集上达到95.98%.
  • 该模型在分类任务中表现优于比较原型和细粒度模型.
  • 可视化证实了SequencesNet在捕获微细信息方面的卓越能力,这对于区分MRI序列至关重要.

结论:

  • SequencesNet在MRI序列分类方面表现出高性能,有效地管理了类内变化和类间微妙性.
  • 特性选择模块 (FSM) 通过专注于关键细粒度特征来提高临床解释性.
  • 序列网的模块化设计提供了扩展到其他医学成像任务的潜力,未来的工作重点是计算效率和概括.