[1]王振华,刘阳星,赵晓雨,等.结合上下文和注意力机制改进的视盘分割模型[J].中国医学物理学杂志,2023,40(1):47-53.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.008]
 WANG Zhenhua,LIU Yangxing,ZHAO Xiaoyu,et al.Optic disc segmentation model improved by contextual information and attention mechanism[J].Chinese Journal of Medical Physics,2023,40(1):47-53.[doi:DOI:10.3969/j.issn.1005-202X.2023.01.008]
点击复制

结合上下文和注意力机制改进的视盘分割模型()
分享到:

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
40卷
期数:
2023年第1期
页码:
47-53
栏目:
医学影像物理
出版日期:
2023-01-07

文章信息/Info

Title:
Optic disc segmentation model improved by contextual information and attention mechanism
文章编号:
1005-202X(2023)01-0047-07
作者:
王振华刘阳星赵晓雨张书台
上海海洋大学信息学院, 上海 201306
Author(s):
WANG Zhenhua LIU Yangxing ZHAO Xiaoyu ZHANG Shutai
School of Information, Shanghai Ocean University, Shanghai 201306, China
关键词:
视盘分割青光眼上下文信息注意力机制Transformer
Keywords:
Keywords: optic disc segmentation glaucoma contextual information attention mechanism Transformer
分类号:
R318;TP391.41
DOI:
DOI:10.3969/j.issn.1005-202X.2023.01.008
文献标志码:
A
摘要:
青光眼为多发性眼底疾病,是致盲的主要原因之一。眼底图像来源广,质量参差不齐,且视盘区域具有多尺度性特征,融合上下文信息有利于准确分割多尺度视盘边界。以U-Net为基础,结合上下文信息和卷积注意力模块(CBAM),提出了一种改进的视盘分割模型,包括:(1)使用实例-批处理归一化(IBN)模块与注意力机制改进主干网络ResNet34,提升分割模型的泛化性和图像通道特征的提取能力;(2)提出一种多层次上下文信息提取(MCE)模块处理主干网络输出的特征,融合上下文信息增强分割模型对视盘边缘特征的提取能力;(3)使用Transformer机制替换U-Net中的跳跃连接和上采样,进一步提高视盘多尺度特征和图像通道特征的提取能力。将改进的分割模型与U-Net、U-Net++、DeeplabV3+、FCN和PSPNet分割模型进行视盘分割精度比较,结果表明提出的分割模型具有更好的分割效果,Dice、MIoU、MPA和FPS指标分别为98.18%、96.45%、98.11%和17.56 Img/s。该研究成果可为青光眼的早期诊断提供技术支撑。 【关键词】视盘分割;青光眼;上下文信息;注意力机制;Transformer
Abstract:
Abstract: Glaucoma which is one of the main causes of blindness is a multiple fundus disease. Considering that fundus images come from a wide range of sources and vary in quality, and that the optic disc region has multi-scale nature, contextual information is beneficial to accurately segmenting the multi-scale optic disc. Based on U-Net, an improved optic disc segmentation model is proposed by combining contextual information and convolutional block attention module (CBAM). The backbone network (ResNet34) is improved by attention mechanism and instance-batch normalization module for enhancing the generalization of segmentation model and the ability to extract image channel features. A multi-level context extraction (MCE) module is proposed for processing the features output from the backbone network and enhancing the ability of the segmentation model to extract the edge features the optic disc. The extraction of the multi-scale features of the optic disc and image channel features is further improved by replacing skip connections and up-sampling with Transformer mechanism. The optic disc segmentation performance of the proposed model is compared with different segmentation models, such as U-Net, U-Net++, DeeplabV3+, FCN and PSPNet. The results show that the proposed segmentation model has better optic disc segmentation results, and achieves Dice, MIoU, MPA and FPS of 98.18%, 96.45%, 98.11% and 17.56 Img/s respectively. The study can provide technical support for the early diagnosis of glaucoma.

相似文献/References:

[1]张迪,宋丽君,刘迪,等.视神经三维结构可视化及定量测量[J].中国医学物理学杂志,2016,33(6):609.[doi:10.3969/j.issn.1005-202X.2016.06.015]
 [J].Chinese Journal of Medical Physics,2016,33(1):609.[doi:10.3969/j.issn.1005-202X.2016.06.015]
[2]曹宏健,刘志成,钱秀清.视乳头的结构和力学特性对筛板变形的影响[J].中国医学物理学杂志,2020,37(10):1317.[doi:DOI:10.3969/j.issn.1005-202X.2020.10.018]
 CAO Hongjian,LIU Zhicheng,QIAN Xiuqing,et al.Effects of mechanical properties and structure of optic nerve head on the deformation of lamina cribrosa[J].Chinese Journal of Medical Physics,2020,37(1):1317.[doi:DOI:10.3969/j.issn.1005-202X.2020.10.018]

备注/Memo

备注/Memo:
【收稿日期】2022-07-10 【基金项目】国家自然科学基金(41501419);上海市科委地方能力建设项目(19050502100) 【作者简介】王振华,博士,副教授,研究方向:大数据的处理及应用,E-mail: zh-wang@shou.edu.cn 【通信作者】张书台,博士,讲师,研究方向:图像处理,E-mail: stzhang @shou.edu.cn
更新日期/Last Update: 2023-01-07