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

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

Automated detection of lumbar disc herniation at L4-L5 and L5-S1 levels on sagittal MRI using a YOLO-based deep learning model.

BMC musculoskeletal disorders·2026

Same author

Comparison of the effectiveness of dry needling and balneotherapy on pain, mood, anxiety, kinesiophobia, disability, and quality of life of patients with myofascial pain syndrome: A prospective, single-blind, randomized study.

Turkish journal of physical medicine and rehabilitation·2025

Same author

Automated detection and segmentation of chondromalacia patella on axial knee MRI using YOLOv11 and a custom CNN: a deep learning-based diagnostic model.

BMC musculoskeletal disorders·2025

Same author

The comparison of the efficacy of extracorporeal shockwave therapy and high-intensity laser therapy in the treatment of de Quervain tenosynovitis.

Turkish journal of physical medicine and rehabilitation·2025

Same author

Differences of microbial growth and biofilm formation among periprosthetic joint infection-causing species: an animal study.

International microbiology : the official journal of the Spanish Society for Microbiology·2025

Same author

Tibiotalocalcaneal ankle arthrodesis with posterior approach arthroscopic-assisted hindfoot nailing.

Journal of orthopaedic surgery (Hong Kong)·2024

Search research articles

相关实验视频

Updated: Jun 21, 2025

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

通过使用先进的深度学习模型与相对较小的数据集,在阴茎撕裂检测中实现高精度.

Erdal Güngör¹, Husam Vehbi², Ahmetcan Cansın³

¹Department of Orthopaedics and Traumatology, Medipol University Esenler Hospital, Istanbul, Turkey.

Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA

|July 17, 2024

概括

先进的深度学习模型,YOLOv8和EfficientNetV2,在MRI扫描上有效地检测阴茎撕裂. 这种人工智能系统有助于更快的诊断,并减少医生的工作量,即使数据有限.

关键词:

这就是YOLOv8的意义.深度学习是一种深度学习.磁共振成像技术的使用阴茎撕裂检测器阴茎撕裂检测器对象检测检测对象检测对象检测

更多相关视频

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Published on: July 6, 2022

A Simple Critical-sized Femoral Defect Model in Mice

A Simple Critical-sized Femoral Defect Model in Mice

Published on: March 15, 2015

相关实验视频

Last Updated: Jun 21, 2025

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

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Published on: July 6, 2022

A Simple Critical-sized Femoral Defect Model in Mice

A Simple Critical-sized Femoral Defect Model in Mice

Published on: March 15, 2015

科学领域:

骨科成像分析骨科成像分析
放射学中的人工智能
深度学习用于医学诊断.

背景情况:

阴茎撕裂是常见的膝盖损伤,需要准确的诊断.
磁共振成像 (MRI) 对于可视化阴茎病理至关重要.
当前的诊断方法可能耗时,需要专门的专业知识.

研究的目的:

评估YOLOv8和EfficientNetV2在MRI上检测阴茎撕裂的有效性.
用有限的数据集评估这些深度学习模型的性能.
确定人工智能的潜力,以提高半径撕裂诊断的效率.

主要方法:

利用了642个膝盖MRI扫描的数据集,由骨科外科医生进行注释.
采用了两阶段的深度学习方法:YOLOv8用于半月板局部化和EfficientNetV2用于撕裂检测.
训练并验证了在斜腰和冠状MRI视图上的模型.

主要成果:

YOLOv8在阴茎局部化方面取得了高性能,mAP@50得分为0.98 (斜面) 和0.985 (冠状).
EfficientNetV2表现出优异的阴茎撕裂检测能力,AUC分数为0.97 (松下) 和0.98 (冠状).
这些模型在识别和定位半径撕裂方面表现出极高的准确性.

结论:

最先进的深度学习模型 (YOLOv8,EfficientNetV2) 显示出在MRI上检测阴茎撕裂的前景,尽管数据集很小.
人工智能系统产生即时的,结构化的报告,提高诊断速度和解释.
这项技术可以增强临床决策,减轻医生在骨科放射学中的工作负担.