一种适用于角膜形变区域的精准分割算法
A precise segmentation algorithm suitable for corneal deformation regions
李婧 1李明悦 1赖雨晴 1白金帅1
作者信息
- 1. 天津理工大学计算机视觉与系统教育部重点实验室和天津市智能计算及软件新技术重点实验室,天津 300384
- 折叠
摘要
分割在圆锥角膜的计算机辅助诊断中起着至关重要的作用.本文针对角膜受力形变的视频图像中如何精准分割角膜区域的问题提出了一种基于全卷积架构融合注意力机制(attention mechanism,AM)的角膜形变区域精准分割算法.它包括3个关键技术:跳过连接(skip connec-tion,SC)、残差卷积(residual convolutional,RC)和融入全局AM的全卷积架构.SC有效增强了模型学习复杂轮廓细节的能力,RC则允许在保留基本图像特征的同时构建更深层次的特征模型.全局AM则通过从每个卷积和反卷积块中提取精细化的特征映射,从而提高模型的分割精度.通过增强并突出关键区域,实践表明角膜形变区域的更精确分割有效提升圆锥角膜的早期诊断准确率.
Abstract
Segmentation plays a crucial role in the computer-aided diagnosis of keratoconus.This paper proposes an accurate segmentation algorithm for the corneal deformation area in video images of corneal force deformation,based on a fully convolutional architecture integrated with an attention mechanism(AM).It includes three key technologies:skip connections(SC),residual convolution(RC),and a fully convolutional architecture integrated with global AM.Skip connections effectively enhance the model's ability to learn complex contour details,while RC allows for the construction of deeper feature models while retaining basic image features.The global AM improves the segmentation accuracy of the model by extracting refined feature maps from each convolutional and deconvolutional block.By enhancing and highlighting key areas,it has been demonstrated that more accurate segmentation of the corneal deformation area effectively improves the early diagnosis accuracy of keratoconus.
关键词
语义分割/角膜形变区域/全卷积/注意力机制(AM)/残差卷积(RC)/圆锥角膜Key words
semantic segmentation/corneal deformation areas/fully convolution/attention mechanism(AM)/residual convolution(RC)/keratoconus引用本文复制引用
基金项目
南开大学眼科学研究院开放基金(NKYKD202209)
出版年
2024
NETL
NSTL
万方数据