相关实验视频

Updated: Aug 4, 2026

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

胆管Seg-ViT:基于混合注意力特征增强机制的胆管层分割的变压器模型

Zhaolin Lu¹, Tao Liu², Yewen Ni^1,3

¹The Affiliated Xuzhou Municipal Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China.

Translational vision science & technology

|September 5, 2024

概括

一种新的视觉变压器模型,ChoroidSeg-ViT,在光学连贯性断层图像中精确地分割着胆道层,实现了最先进的性能,并实现了自动胆道分析.

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:

在光学连贯断层扫描 (OCT) 图像中精确分离胆道层对于诊断和监测各种眼睛疾病至关重要.
现有的细分方法在精度和自动化方面可能面临挑战.

研究的目的:

开发一个先进的视觉转换器 (ViT) 模型,命名为ChoroidSeg-ViT,用于在OCT图像中增强胆层细分.
用混合注意力特征增强机制来提高胆层细分的精度和自动化.

主要方法:

使用了100张OCTB扫描图像的数据集,专家眼科医生精心注释了基本事实.
设计了一个端到端的ChoroidSeg-ViT模型,集成了本地增强的特征提取和语义特征融合路径.
用标准指标来评估细分性能,例如mDice,mIoU和mAcc.

主要成果:

合金Seg-ViT表现出优越的细分性能,达到mDice的98.31%,mIoU的96.62%,mAcc的98.29%.
拟议的模型在状层细分方面表现优于其他深度学习方法.
废除和泛化实验证实了模型设计模块的有效性.

结论:

开发了一种新型的变压器模型,ChoroidSeg-ViT,用于精确和自动的胸膜层细分,实现了最先进的结果.
胆管Seg-ViT模型提供了胆管层的精确和流的细分.
这种模型可以作为一个自动化状腺分析系统的基础,推进眼科研究.

更多相关视频

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关概念视频

Vision

Vision

Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.