相关实验视频

Updated: Jul 20, 2026

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

可解释的深度学习系统用于使用面部图像自动检测甲状腺眼病

Xiaodan Sui¹, Kenneth Ka Hei Lai², Richard Wai Chak Choy³

¹From the Multimedia Laboratory (X.D.S. and H.S.L.), The Chinese University of Hong Kong, Hong Kong, China; School of Information Science and Engineering (X.D.S. and Y.J.Z.), Shandong Normal University, Jinan, Shandong Province, China.

American journal of ophthalmology

|May 29, 2025

概括

一个可解释的深度学习系统使用面部图像准确地检测甲状腺眼病 (TED). 这种人工智能工具表现出高度的灵敏度和特异性,有助于早期诊断和转介给渐进式TED.

科学领域:

眼科医生眼科眼科
人工智能的人工智能
医疗成像医学成像

背景情况:

甲状腺眼部疾病 (TED) 是一种影响眼部区域的自身免疫性疾病.
早期检测和准确的诊断对于管理TED和预防视力丧失至关重要.

研究的目的:

开发和验证一个可解释的深度学习 (XDL) 系统,用于从面部图像中自动检测TED.
评估XDL系统在识别TED时的准确性和通用性.

主要方法:

一项前性研究对302个TED和289个健康受试者的面部图像进行了XDL模型的训练.
该XDL系统包括一个周期性地标本地化网络和TED检测网络 (TDN).
评估涉及三重交叉验证和对100个TED患者图像的独立队列的验证.

主要成果:

在训练队列中,XDL系统实现了ROC曲线下的面积为99.7%,灵敏度为99.7%,特异性为94.5%.
热图突出显示眼是TED检测的关键区域.
独立验证队列显示ROC曲线下的面积为98.9%,灵敏度为92%和特异性为93%.

结论:

在从面部图像中检测TED时,XDL系统表现出卓越的准确性和可解释性.
建议在不同的临床环境中进行进一步评估,包括非专业的环境,以尽早发现渐进性TED.
这种人工智能驱动的方法有可能通过及时诊断和转诊来改善患者的治疗结果.

更多相关视频

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

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

相关概念视频

Graves' Disease I: Introduction

Graves' Disease I: Introduction

Graves' disease is an autoimmune disorder that causes hyperthyroidism, or overactivity of the thyroid gland. It results from autoantibodies called thyroid-stimulating immunoglobulins (TSIs), which bind to thyroid-stimulating hormone (TSH) receptors, leading to overstimulation of hormone production and a hypermetabolic state.EtiologyAlthough considered idiopathic, Graves’ disease has well-established contributing factors. There is a strong genetic component, with increased prevalence in...

Graves Disease II: Pathophysiology

Graves Disease II: Pathophysiology

Graves’ disease is an autoimmune disorder characterized by the production of thyroid-stimulating immunoglobulins (TSI) that activate TSH receptors, leading to excessive synthesis and release of thyroid hormones (T3 and T4) and resulting in hyperthyroidism.Among all causes of hyperthyroidism, Graves’ disease is the most common and can happen at any age, though it is more frequent in women. It produces a hypermetabolic state with features such as weight loss, tachycardia, tremor, and heat...