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

Search research articles

相关实验视频

Updated: Sep 17, 2025

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

使用视觉变压器进行头脑测量地标检测,具有直接坐标预测的视觉变压器.

Filipe Laitenberger¹, Hannah T Scheuer², Hanna A Scheuer³

¹University of Amsterdam, Department of Artificial Intelligence, Amsterdam, Netherlands.

Journal of cranio-maxillo-facial surgery : official publication of the European Association for Cranio-Maxillo-Facial Surgery

|July 2, 2025

概括

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

In vitro analysis of a glass solder matrix on ATZ-ceramic-samples using human dental pulp cells and L929 mouse fibroblasts.

International journal of implant dentistry·2026

Same author

The position of the mental foramen on panoramic radiographs of patients with neurofibromatosis type 1.

Journal of cranio-maxillo-facial surgery : official publication of the European Association for Cranio-Maxillo-Facial Surgery·2026

Same author

Combined Soft and Hard Tissue Facial Lesions In Early Childhood Pioneering the Diagnosis of the Tumor Predisposition Syndrome Neurofibromatosis Type 1.

Cancer diagnosis & prognosis·2026

Same author

Ossification of Mandibular Central Giant Cell Granuloma (CGCG) in Neurofibromatosis Type 1 Patients.

Cancer diagnosis & prognosis·2026

Same author

Clinical Parameters and Radiomics of Vestibular Schwannomas in NF2-related Schwannomatosis.

Anticancer research·2026

Same author

Long-term Stable Unilateral Mandibular Deformity Associated With Ipsilateral Skull-base Soft-tissue Lesion and Degenerated Pterygoid Muscles in Neurofibromatosis Type 1.

Cancer diagnosis & prognosis·2026

有直接坐标预测的视觉变压器 (ViT) 显著提高了正牙X射线中头脑测量地标检测 (CLD) 的准确性. 这种新的方法优于目前的方法,为临床应用提供了更强大的解决方案.

科学领域:

医疗成像医学成像
计算机视觉计算机视觉
矯正牙科矯正牙科是一種矯正牙科.

背景情况:

脑仪地标检测 (CLD) 对于正牙诊断和治疗规划至关重要.
目前的深度学习方法,特别是使用热图预测的卷积神经网络 (CNN),对于大规模的临床应用来说表现不够好.

研究的目的:

引入一种使用视觉变换器 (ViTs) 进行直接坐标预测的CLD的新方法.
评估ViTs与当代CNN架构和基于热图的方法的性能.

主要方法:

利用视觉变压器 (ViTs) 进行直接坐标预测,绕过内存密集的热图生成.
进行了广泛的除研究,将ViTs与ConvNeXt V2 (CNN) 和Segformer (基于热图) 进行比较.

主要成果:

具有直接坐标预测的ViT实现了卓越的性能,平均辐射误差超过2毫米,超过了最先进的CLD方法.
不适应的CNN表现不佳,而现有方法的概括性有限,特别是在稀疏的数据集上.

结论:

具有直接坐标预测的视觉变压器显示出对推进CLD和医疗计算机视觉的重大前景.
拟议的方法为临床正义牙科应用提供了更好的准确性和概括能力.

关键词:

头脑测量地标检测检测器计算机视觉计算机视觉计算机视觉深度学习是一种深度学习.医学成像医学成像矯正牙科矯正牙科是一種矯正牙科.视觉变压器视觉变压器

更多相关视频

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关实验视频

Last Updated: Sep 17, 2025

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

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024