相关实验视频

Updated: Jun 22, 2026

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

GKE-TUNet:嵌入式TransUNet模型用于视网膜血管细分,考虑到解剖学拓

Yunlong Qiu, Haifeng Zhang, Chonghui Song

IEEE journal of biomedical and health informatics

|August 13, 2024

概括

一个新的几何知识嵌入式TransUNet (GKE-TUNet) 模型通过整合解剖拓学来增强自动视网膜血管细分. 这提高了复杂结构的检测,以更好地通过计算机辅助诊断和查.

科学领域:

医疗成像医学成像
计算机视觉计算机视觉
人工智能的人工智能

背景情况:

自动视网膜血管细分对于诊断视网膜病变等眼睛疾病至关重要.
深度学习模型在密集的视网膜区域中与复杂的血管结构和小血管作斗争.

研究的目的:

引入一种新的细分模型,GKE-TUNet,它嵌入了视网膜血管解剖拓.
为了提高自动视网膜血管细分的准确性,特别是在具有挑战性的血管模式中.

主要方法:

一个骨架提取网络预训练以捕获船舶拓.
图形注意网络 (GAT) 在TransUNet架构中处理拓特征.
图形特征与密集特征地图融合,以增强细分.

主要成果:

在DRIVE,CHASE-DB1和STARE数据集上,GKE-TUNet模型表现出具有竞争力的性能.
该方法有效地提取复杂的交织结构和微妙的小血管.
拓知识的整合提高了细分精度.

结论:

GKE-TUNet模型提供了一种可靠的方法来实现视网膜血管自动细分.
嵌入明确的解剖学知识可以提高医疗成像任务的深度学习模型性能.
这种方法对推进计算机辅助诊断和视网膜病变查有前途.

更多相关视频

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

相关概念视频

Anatomy of Blood Vessels

Anatomy of Blood Vessels

The vascular system, an integral part of the circulatory system, comprises various blood vessels that play crucial roles in maintaining the body's homeostasis. These blood vessels form a complex and efficient circulatory network. The three primary categories of blood vessels are the arteries, veins, and capillaries.
Arteries
Arteries circulate oxygenated blood from the heart, except the pulmonary artery, which transports deoxygenated blood to the lungs. Large arteries, such as the aorta, have...