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

Imaging Studies IV: Magnetic Resonance Imaging01:27

Imaging Studies IV: Magnetic Resonance Imaging

219
Introduction:Magnetic Resonance Imaging, or MRI, can include a specialized imaging technique of the urinary system known as Magnetic Resonance Urography (MRU). This radiation-free technique uses strong magnetic fields and radio waves to produce detailed images with the help of a computer. MRU is particularly effective for visualizing fluid-filled structures like the kidneys, ureters, and bladder.Applications of MRI in the Genitourinary SystemKidneys and Ureters: MRI detects tumors, cysts,...
219

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

Domain Generalization Mitigates Scanner-Induced Domain Shift in Medical Imaging.

Journal of imaging informatics in medicine·2026
Same author

Artificial intelligence-driven radiomics: developing valuable radiomics signatures with the use of artificial intelligence.

BJR artificial intelligence·2026
Same author

Radiomics Applicability Domain Analysis Classification Framework (RADAN-CF): A method for evaluating prediction reliability in radiomics.

Computer methods and programs in biomedicine·2026
Same author

From theory to practice: Re-identification Challenge to test imaging data pseudonymization effectiveness.

Scientific data·2026
Same author

Consistency of Radiological Staging in Resectable Mismatch-Repair Proficient Colon Cancer: An Interobserver Agreement Study.

Clinical colorectal cancer·2026
Same author

Reporting checklist for foundation and large language models in medical research (REFINE): an international consensus guideline.

Diagnostic and interventional radiology (Ankara, Turkey)·2026

相关实验视频

Updated: Jan 12, 2026

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
06:08

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

1.1K

自主监督学习可以提高前列腺双参数MRI分类中的表现.

José Guilherme de Almeida1, Ana Sofia Castro Verde1, Ana Mascarenhas Gaivão2

  • 1Champalimaud Foundation, Lisbon, Portugal.

Computers in biology and medicine
|November 5, 2025
PubMed
概括

二维自主监督学习 (SSL) 模型显示,从MRI扫描中进行前列腺癌分类的性能和数据效率有所提高. 这些在未标记数据上训练的模型,优于传统的监督方法,强调了大规模生物医学成像数据集的价值.

关键词:
多个实例的学习学习.前列腺多参数核磁共振成像自主监督学习学习

更多相关视频

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy
09:11

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Published on: April 9, 2019

22.3K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

1.1K

相关实验视频

Last Updated: Jan 12, 2026

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
06:08

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

1.1K
Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy
09:11

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Published on: April 9, 2019

22.3K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

1.1K

科学领域:

  • 人工智能的人工智能
  • 医疗成像医学成像
  • 机器学习 机器学习

背景情况:

  • 前列腺癌的诊断很大程度上依赖于体积成像,特别是双参数MRI (bpMRI).
  • 当前的监督学习模型需要大量的注释数据,这需要大量的劳动力来获取.
  • 自主监督学习 (SSL) 为利用大型未标记的医疗数据集提供了一个有希望的替代方案.

研究的目的:

  • 开发和评估2D自主监督学习 (SSL) 模型用于体积MRI分析.
  • 在使用bpmri的前列腺癌分类任务中证明这些ssl模型的有效性.
  • 将SSL模型的性能与完全监督学习 (FSL) 基线进行比较.

主要方法:

  • 在来自12个欧洲中心的前列腺多参数MRI (mpMRI) 大数据集上训练了两个不同的2D SSL方法.
  • 预训练的SSL模型被转移到使用基于注意力的多重实例学习 (MIL) 的体积前列腺bpMRI分类任务中.
  • 在三个任务中评估了表现:前列腺癌诊断,临床上显著的前列腺癌诊断和虚拟活检,使用AUC和交叉验证.

主要成果:

  • 在几个前列腺癌分类任务中,SSL模型的性能与FSL基线相当或优于FSL基线.
  • 对于bpMRI D-PCa,AUC为SSL的0.82而不是FSL的0.75 (p=0.017);对于T2 D-csPCa,AUC为SSL的0.73而不是FSL的0.68 (p=0.043).
  • SSL模型需要更少的训练数据来实现类似的性能,注意力得分与损伤位置相关.

结论:

  • 在未标记数据上训练的无监督SSL模型更有效地处理数据,并在体积前列腺MRI分类中比FSL模型表现更好.
  • 这些发现强调了大规模数据收集和注释努力在推进生物医学成像AI方面的关键重要性.
  • SSL 提供了一种可行的策略,以克服医疗图像分析中的数据限制.