Search research articles

Search research articles

相关实验视频

Updated: Sep 15, 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

通过使用深度学习的超广场图像识别形态模式来诊断病态近视.

Yang Liu¹, Keming Zhao^1,2, Lihui Luo¹

¹Institute of Biopharmaceutics and Health Engineering, Tsinghua Shenzhen International Graduate School, Shenzhen, China.

NPJ digital medicine

|July 13, 2025

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

Association between metal co-exposure and frailty: exploring the potential explanatory pathway of inflammation.

Biometals : an international journal on the role of metal ions in biology, biochemistry, and medicine·2026

Same author

Brain network construction and analysis for epilepsy: A methodology review.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

High-temporal-resolution slope-aspect deformation extraction and evolution analysis of the Xiongba landslide group based on time-series InSAR and unscented Kalman filter.

Scientific reports·2026

Same author

Mechanism of palytoxin-induced ferroptosis in HaCaT cells via targeting TrxR1.

Cell biology and toxicology·2026

Same author

Altered neurodevelopmental trajectories of brain structure in Tourette syndrome and Chronic Tic Disorders.

medRxiv : the preprint server for health sciences·2026

Same author

MarkerMatch: a proximity-based probe-matching algorithm for joint analysis of copy-number variants from different genotyping arrays.

Bioinformatics (Oxford, England)·2026

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

概括

本研究介绍了RealMNet,这是一种轻量级的人工智能框架,用于使用超广场图像诊断病态近视. 它可以准确地识别后部葡萄瘤和近视性黄斑病,改善视力障碍的临床解释性.

科学领域:

眼科医生眼科眼科
医疗成像医学成像
人工智能的人工智能

背景情况:

病态近视是视力丧失的主要原因.
目前用于近视检测的深度学习方法缺乏临床解释性.
超广场 (UWF) 成像为诊断近视相关并发症提供了视网膜的更广泛视图.

研究的目的:

开发一种可解释的AI模型,用于诊断病态近视.
为了识别特定的形态模式,如后部葡萄瘤和近视性黄斑病.
为了利用UWF图像增强诊断能力.

主要方法:

策划了一个大规模的,多来源的UWF近视数据集 (PSMM).
推出了RealMNet,一个端到端的轻量级深度学习框架 (2100万个参数).
在三个实验协议中评估了RealMNet的性能.

主要成果:

RealMNet实现了高诊断准确度:F1评分为0.7970,mAP为0.8497,AUROC为0.9745.0 的结果是可以实现的.
在不同的测试条件下证明了稳定性和通用性.
该型号的轻量级设计有助于在医疗设备上部署.

更多相关视频

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Inducement and Evaluation of a Murine Model of Experimental Myopia

Inducement and Evaluation of a Murine Model of Experimental Myopia

Published on: January 22, 2019

相关实验视频

Last Updated: Sep 15, 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

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

Inducement and Evaluation of a Murine Model of Experimental Myopia

Inducement and Evaluation of a Murine Model of Experimental Myopia

Published on: January 22, 2019

结论:

使用UWF图像,RealMNet有效地识别了病态近视的关键形态模式.
与现有方法相比,该框架提供了更好的临床解释性.
在诊断和管理由于近视的视力障碍方面,RealMNet对临床应用具有显著的希望.