Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Imaging Studies II: Ultrasonography

Imaging Studies II: Ultrasonography

IntroductionUltrasonography, or renal ultrasound, is a noninvasive medical imaging technique that uses high-frequency sound waves to visualize the kidneys, ureters, bladder, and surrounding tissues.Indications for Urinary System UltrasonographyUrinary system ultrasonography is indicated in various clinical scenarios, such as:Kidney Stones (Urolithiasis): To detect and monitor the size and presence of kidney or urinary tract stones.Hydronephrosis: To assess the dilation of the renal pelvis and...

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

Applications of Artificial Intelligence in Urodynamic Data Interpretation: A Narrative Review.

Neurourology and urodynamics·2026

Same author

Optimal Selection of the Effective Echo Time (TE<sub>eff</sub>) for T2-Weighted Fast-Spin-Echo MRI of the Prostate at 3.0 T: Effect on Lesion Conspicuity.

Journal of magnetic resonance imaging : JMRI·2026

Same author

BWS-Net: An Optimal Deep Learning Architecture for the Anterior Bladder Wall Segmentation using Ultrasound Imaging.

IEEE journal of biomedical and health informatics·2026

Same author

Treatment Monitoring of Carpal Tunnel Syndrome Using Shear Wave Elastography: A Pilot In Vivo Study.

Cureus·2026

Same author

Fertility Preservation in Female Cancer Patients: Comprehensive Clinical, Surgical, and Radiologic Guide for Radiologists.

Radiographics : a review publication of the Radiological Society of North America, Inc·2026

Same author

Deep learning-based classification of thyroid nodules using uncertainty-aware multi-modal ultrasound imaging.

Scientific reports·2026

Search research articles

相关实验视频

Updated: Jul 16, 2026

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

使用超声波成像对乳腺病变进行分类的变化模式定向深度学习框架.

Manali Saini¹, Sara Hassanzadeh¹, Bushira Musa²

¹Department of Radiology, Mayo Clinic College of Medicine and Science, Rochester, MN, 55905, USA.

Scientific reports

|April 24, 2025

概括

这项研究引入了一个新的AI框架,用于使用超声波检测乳腺癌. 它提高了分类病变的准确性和可解释性,提供了更有效和可靠的诊断工具.

关键词:

卷积层是一种卷积层.深度学习是一种深度学习.混合聚合混合聚合混合聚合超声波超声波是指超声波的使用.变化模式分解的变化模式分解

更多相关视频

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

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

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

Published on: November 30, 2022

相关实验视频

Last Updated: Jul 16, 2026

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

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

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

Published on: November 30, 2022

科学领域:

医疗成像医学成像
人工智能的人工智能
在瘤学瘤学.

背景情况:

乳腺癌是妇女死亡的主要原因,需要早期检测.
目前用于基于超声波的乳腺病变检测的深度学习方法面临着可解释性,细分性和计算成本的挑战.

研究的目的:

开发一种新的基于超声波的乳腺病变分类框架.
提高深度学习模型用于乳腺癌检测的可解释性和效率.

主要方法:

使用二维变量模式分解 (2D-VMD) 来提取自我解释的特征.
采用卷积神经网络 (CNN),混合聚合和注意力机制,以2D-VMD特征为指导.
评估了公共和内部乳房超声波数据集的框架,而不需要病变细分.

主要成果:

实现了高分类准确度:98%和93%在两个公共数据集上,89%在一个内部数据集上.
在ROC (5%) 和精度回忆 (10%) 曲线下显示了改进的区域.
与现有方法相比,展示了显著的计算效率,减少了浮点运算.

结论:

拟议的2D-VMD引导的CNN框架为乳腺病变分类提供了一个高度准确,可解释和计算高效的解决方案.
这种方法克服了现有方法的局限性,提供了可解释的特性,消除了对细分的需求.
该框架有望改善早期发现乳腺癌并降低死亡率.