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

Redefining clinical success in minimally invasive surgery for BPH: A composite endpoint integrating ejaculatory function, urinary improvement, and safety metrics.

Urologia·2026
Same author

Delphi consensus on ex vivo fluorescence confocal microscopy in robot-assisted radical prostatectomy.

BJU international·2026
Same author

Beyond satisfaction scores: quantifying communication quality in oncology care.

Prostate cancer and prostatic diseases·2026
Same author

External validation of the prostatic inflammation nomogram to predict prostatic inflammation in men with lower urinary tract symptoms.

Minerva urology and nephrology·2026
Same author

Beyond One-Size-Fits-All Active Surveillance for Low-Risk Prostate Cancer: Risk-Adapted Follow-Up, De-Escalation Pathways, and Focal Therapy as Tailored Strategy.

Diagnostics (Basel, Switzerland)·2026
Same author

Improved Early Urinary Continence After Robot-Assisted Radical Prostatectomy Using a Modified Vesicourethral Anastomosis with Posterior Musculofascial Reconstruction: A Prospective Comparative Study.

Journal of clinical medicine·2026

相关实验视频

Updated: Jul 23, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

基于机器学习的工具来预测目标前列腺活检结果:内部验证研究

Enrico Checcucci1, Samanta Rosati2, Sabrina De Cillis3

  • 1Department of Surgery, Candiolo Cancer Institute, FPO-IRCCS, Candiolo, 10060 Turin, Italy.

Journal of clinical medicine
|July 14, 2023
PubMed
概括
此摘要是机器生成的。

这项研究引入了一个个性化的预测模型,使用机器学习在活检之前识别前列腺癌 (PCa). 模糊逻辑 + 支持向量机器模型准确地预测PCa,可能避免不必要的程序.

关键词:
人工智能的人工智能是人工智能.机器学习是机器学习.前列腺活检 活检前列腺活检前列腺癌是前列腺癌.

更多相关视频

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

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

Published on: June 10, 2025

101
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

21.6K

相关实验视频

Last Updated: Jul 23, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:08

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

Published on: June 10, 2025

101
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

21.6K

科学领域:

  • 泌尿器科 泌尿器科 泌尿器科 泌尿器科
  • 医疗成像医学成像
  • 机器学习 机器学习

背景情况:

  • 前列腺癌 (PCa) 诊断通常涉及侵入性手术,如融合活检 (FB).
  • 准确的活检前风险分层对于患者管理和资源优化至关重要.

研究的目的:

  • 开发和验证使用机器学习 (ML) 的个性化预测模型 (PPM),用于在多参数MRI (mpMRI) 后识别疑似前列腺癌 (PCa) 的患者.
  • 评估模糊推理系统 (FIS) 与支持矢量机器 (SVM) 结合的性能,与其他ML方法和标准诊断工具相比.

主要方法:

  • 利用了1448名患者的数据集进行培训和181名患者进行验证,所有患者都接受了mpMRI和FB.
  • 开发并比较了四种ML方法:FIS,SVM,k-最近邻居 (KNN) 和自组织地图 (SOM).
  • 对逻辑回归 (LR) 和标准诊断工具进行模糊逻辑 (FL) + SVM 系统的评估,重点关注 AUC,NPV,特异性,灵敏度和准确性等指标.

主要成果:

  • FIS + SVM 模型在 AUC 中的性能与 LR 相似,但优于其他工具.
  • 在培训套件中,FIS + SVM实现了最高的NPV (78.5%) 和特异性 (92.1%与LR的83%相比).
  • 在验证组中,FIS + SVM的性能优于其他方法,NPV为60.7%,灵敏度为90.8%,准确度为69.1%.

结论:

  • 使用FIS + SVM的验证个性化预测模型 (PPM) 已成功开发,可以在FB之前预测PCa概率.
  • 在大约15%的病例中,这种工具可以帮助避免不必要的活检.
  • 该模型为改善疑似前列腺癌的诊断途径提供了一个有希望的方法.