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

FLOT vs CROSS Among Patients With Pathological Complete Response in Esophageal Adenocarcinoma.

JAMA surgery·2026
Same author

Automatic recognition of anatomical structures and surgical phases in robot-assisted minimally invasive esophagectomy (RAMIE) using deep learning: a retrospective cohort study.

Surgical endoscopy·2026
Same author

Evaluating human-AI interaction in optical diagnosis of early colorectal carcinoma through endoscopist responses to simulated artificial intelligence: a multinational online study.

Endoscopy·2026
Same author

Systemic therapy, gastrectomy, cytoreductive surgery, and hyperthermic intraperitoneal chemotherapy versus systemic therapy alone for gastric cancer with limited peritoneal metastases (PERISCOPE II): final results of a multicentre, randomised, controlled, phase 3 trial after an unplanned commissioned interim analysis.

The Lancet. Oncology·2026
Same author

Bridging perspectives: experiences and future directions for patient involvement in clinical registries - a survey-based study.

BMJ open quality·2026
Same author

Perioperative systemic therapy versus surgery alone for resectable colorectal peritoneal-only metastases (CAIRO6): a randomised, open-label, phase 3 trial.

The Lancet. Oncology·2026

相关实验视频

Updated: Jan 9, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

使用3D图像数据集估计医疗分类任务的难度.

Terese A E Thornblad, Eloy W R Schultz, Cris H B Claessens

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |December 3, 2025
    PubMed
    概括

    估计医疗深度学习数据集的难度至关重要. 轮分数 (SIL) 度量表现出与深度学习模型性能有很强的相关性,可能指导资源配置和模型开发.

    更多相关视频

    Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
    10:26

    Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

    Published on: May 19, 2023

    2.5K
    Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training
    09:57

    Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training

    Published on: January 18, 2021

    4.5K

    相关实验视频

    Last Updated: Jan 9, 2026

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.3K
    Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
    10:26

    Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

    Published on: May 19, 2023

    2.5K
    Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training
    09:57

    Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training

    Published on: January 18, 2021

    4.5K

    科学领域:

    • 医疗成像医学成像
    • 机器学习 机器学习
    • 无线电学 (Radiomics) 是一种无线电学.

    背景情况:

    • 深度学习在医疗应用中表现有希望,但性能各不相同.
    • 评估数据集难度通常是资源密集型,涉及到广泛的模型培训.
    • 早期预测性能可以优化开发和资源配置.

    研究的目的:

    • 开发一个指标来估计3D医学图像分类任务的难度.
    • 评估数据集难度指标与深度学习模型性能之间的预测能力.

    主要方法:

    • 应用于3D医学图像数据集中的放射性特征的轮得分 (SIL) 和Fréchet起始距离 (FID).
    • 将SIL和FID指标与两个深度学习模型的性能进行比较.
    • 分析了数据集难度指标与模型性能之间的相关性.

    主要成果:

    • 图形得分 (SIL) 显示出与深度学习模型性能最强的相关性.
    • 在医学成像任务中,SIL显示出作为数据集难度的可靠指标的潜力.
    • 对特征提取和难度指标的进一步分析可以完善数据集区分.

    结论:

    • 轮得分 (SIL) 可以作为一个有价值的工具来估计医疗数据集的难度.
    • 这种方法可以指导资源的有效分配,并为数据策划策略提供信息.
    • 这些发现支持通过预测任务挑战和数据需求来改进计算机辅助诊断.