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

Negative life events and mobile phone addiction among Chinese vocational college students: a chain-mediation model of perceived stress and psychological resilience.

Frontiers in psychology·2026
Same author

Safety and antibody responses to inactivated COVID-19 vaccines among elderly patients with COPD: a prospective cohort study.

Frontiers in immunology·2026
Same author

A Keap1-Nrf2 protein-protein interaction inhibitor 4-95 ameliorates cognitive dysfunction by suppressing neuronal ferroptosis.

Bioorganic chemistry·2026
Same author

Anatomical structure of pulmonary vessels and bronchi in the right upper lobe based on three-dimensional reconstruction.

BMC surgery·2026
Same author

Psychological-behavioral risk profiles of adolescents and their associations with suicidal behaviors.

Journal of affective disorders·2026
Same author

Synergistic immobilization of lead and enhanced Solanum nigrum growth by phosphogypsum coupled with phosphate-solubilizing Bacillus megaterium: Roles of Pb mineral transformation and rhizosphere microbiome restructuring.

Journal of hazardous materials·2026

相关实验视频

Updated: Jul 11, 2025

Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells
07:46

Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells

Published on: October 13, 2023

1.3K

对子宫内膜疾病进行自我监督的分类模型.

Yun Fang1, Yanmin Wei2, Xiaoying Liu1

  • 1Quzhou People's Hospital, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou, 324000, Zhejiang, China.

Journal of cancer research and clinical oncology
|November 10, 2023
PubMed
概括

一种新的计算机辅助诊断模型,BSEM,通过超声波帮助早期检测子宫内膜疾病. 这种自我监督的模型提高了放射科医生查子宫内膜病变的诊断准确性和效率.

关键词:
卷积神经网络是一种卷积神经网络.这是子宫内膜癌的癌症.自主监督学习学习通过阴道的超声波.

更多相关视频

Sentinel Lymph Node Mapping and Biopsy for Endometrial Cancer at Early Stage with Laparoscopy
05:52

Sentinel Lymph Node Mapping and Biopsy for Endometrial Cancer at Early Stage with Laparoscopy

Published on: August 19, 2021

11.5K
A Syngeneic Murine Model of Endometriosis using Naturally Cycling Mice
07:12

A Syngeneic Murine Model of Endometriosis using Naturally Cycling Mice

Published on: November 24, 2020

5.2K

相关实验视频

Last Updated: Jul 11, 2025

Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells
07:46

Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells

Published on: October 13, 2023

1.3K
Sentinel Lymph Node Mapping and Biopsy for Endometrial Cancer at Early Stage with Laparoscopy
05:52

Sentinel Lymph Node Mapping and Biopsy for Endometrial Cancer at Early Stage with Laparoscopy

Published on: August 19, 2021

11.5K
A Syngeneic Murine Model of Endometriosis using Naturally Cycling Mice
07:12

A Syngeneic Murine Model of Endometriosis using Naturally Cycling Mice

Published on: November 24, 2020

5.2K

科学领域:

  • 医疗成像医学成像
  • 医疗保健中的人工智能
  • 妇科瘤学 妇科瘤学

背景情况:

  • 超声波是早期子宫内膜疾病诊断的关键,因为它具有非侵入性和低成本.
  • 对子宫内膜损伤的超声波图像的准确解释严重依赖于放射科医生的专业知识.
  • 需要客观的计算机辅助诊断模型来支持放射科医生诊断子宫内膜疾病.

研究的目的:

  • 开发和评估一个稳定和客观的计算机辅助诊断模型,用于子宫内膜疾病的分类.
  • 用超声波图像帮助放射科医生准确有效地诊断子宫内膜病变.

主要方法:

  • 采用了来自734名患有子宫内膜息肉,增生和癌症的患者1875张阴道超声波图像的数据集.
  • 提出了一个自我监督的子宫内膜疾病分类模型 (BSEM),结合了联合原始和自我监督的任务.
  • 在BSEM模型中,采用了自蒸技术和组合策略,以提高诊断性能.

主要成果:

  • 通过五次交叉验证,BSEM模型获得了令人满意的性能,75.1%的准确性,87.3%的AUC,76.5%的精度,73.4%的回忆率和74.1%的F1得分.
  • 与基线模型 (ResNet,DenseNet,VGGNet,ConvNeXt,VIT,CMT) 相比,BSEM表现优越,主要指标提高了3.1-9.0%.
  • 该模型在准确性,AUC,精度,回忆和F1得分方面显著改进,与已建立的深度学习架构相比.

结论:

  • 通过超声波,BSEM模型作为一种有价值的辅助诊断工具,用于通过超声波早期检测子宫内膜疾病.
  • 它提高了放射科医生的精度和效率,以选癌前子宫内膜病变.
  • 拟议的模型为改善妇科成像诊断结果提供了一个有希望的方法.