相关实验视频

Updated: May 10, 2026

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

LHU-VT:一个轻量级的超复杂U-Net,具有用于视网膜血管细分的血管厚度导向子损失

Waqar Ahmed¹, Panos Liatsis²

¹Silo AI, Helsinki, Finland; Department of Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates.

Computers in biology and medicine

|December 12, 2024

概括

一个新的轻量级AI模型,LHU-VT,准确地对视网膜血管进行细分,以早期检测疾病. 这种高效的解决方案提高了诊断能力,特别是在资源有限的环境中.

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:

视力丧失经常与视网膜疾病有关,如与年龄相关的黄斑变性和糖尿病视网膜病变.
这些疾病的早期检测依赖于识别视网膜血管的微妙变化,如微动脉瘤和出血.

研究的目的:

为早期诊断视网膜疾病开发一种准确且计算效率高的视网膜血管细分方法.
为了应对复杂的血管结构,低对比度和视网膜图像中的类不平衡的挑战,特别是边缘部署.

主要方法:

介绍了一种新的轻型超复杂U-Net (LHUN) 模型,利用超复杂的八子来捕获复杂的血管模式并减少计算负载.
整合一个船舶厚度导向子损失 (VTDL) 以减轻类不平衡,提高分段精度.
在四个基准数据集 (CHASE,DRIVE,STARE,HRF) 上评估拟议的LHU-VT模型.

主要成果:

LHU-VT模型在现有方法上取得了显著的改进,实现了高达2.4×更少的FLOP,4.4×更少的参数和2.6×更小的模型大小.
获得了高的曲线下面积 (AUC) 分数:0.9938 (追逐),0.9879 (驱动),0.9988 (STARE) 和0.9808 (HRF).
该模型的轻量级设计使其能够在资源有限的环境中部署.

结论:

拟议的LHU-VT模型为视网膜血管细分提供了高效和准确的解决方案.
这一进步对早期诊断和对视力威胁的视网膜疾病的管理具有重大潜力.
超复杂的方法和指导损失函数有效地解决了医学成像中的细分挑战.

关键词:

超复杂数是一个超复杂的数.轻量化轻量化轻量化轻量化轻量化视网膜血管细分视网膜血管细分根据厚度指导的子损失.这就是U-Net.

更多相关视频

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

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

相关概念视频

Reducing Line Loss

Reducing Line Loss

In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss in...

Imaging Studies VII: Vascular Imaging

Imaging Studies VII: Vascular Imaging

DefinitionRenal angiography, also known as renal arteriography, is an imaging technique used to obtain a comprehensive view of blood flow and the vascular structure of blood vessels in the kidneys and surrounding areas.PurposeRenal angiography detects blood vessel abnormalities in the kidneys, such as aneurysms, stenosis, thrombosis, vascular tumors, and renal artery stenosis. It evaluates kidney function and guides interventional treatments like angioplasty or stent placement.Pre-Procedure...