结合Attention U-Net与瓶颈检测的肺部细胞图像分割方法

邵虹; 左常升; 张萍

doi:10.11959/j.issn.2096-6652.202207

您当前的位置：

首页 >

文章列表页 >

结合Attention U-Net与瓶颈检测的肺部细胞图像分割方法

学术论文 | 更新时间：2024-06-05

- 结合Attention U-Net与瓶颈检测的肺部细胞图像分割方法
- Lung cell image segmentation method combining Attention U-Net and bottleneck detection
- 智能科学与技术学报 2022年4卷第4期页码：610-616
- 作者机构：
  
  1. 沈阳工业大学信息科学与工程学院，辽宁沈阳 110870
  2. 沈阳工业大学软件学院，辽宁沈阳 110870
- 作者简介：
  
  [ "邵虹（1974− ），女，博士，沈阳工业大学信息科学与工程学院教授，主要研究方向为图像处理与模式识别、智能信息处理" ]
  [ "左常升（1996− ），男，沈阳工业大学软件学院硕士生，主要研究方向为智能信息处理" ]
  [ "张萍（1996− ），女，沈阳工业大学信息科学与工程学院硕士生，主要研究方向为智能信息处理" ]
- 基金信息：
- DOI：10.11959/j.issn.2096-6652.202207
  中图分类号： TP3
- 网络出版日期：2022-12，
  
  纸质出版日期：2022-12-15
- 稿件说明：
移动端阅览
邵虹, 左常升, 张萍. 结合Attention U-Net与瓶颈检测的肺部细胞图像分割方法[J]. 智能科学与技术学报, 2022,4(4):610-616.

Hong SHAO, Changsheng ZUO, Ping ZHANG. Lung cell image segmentation method combining Attention U-Net and bottleneck detection[J]. Chinese journal of intelligent science and technology, 2022, 4(4): 610-616.
邵虹, 左常升, 张萍. 结合Attention U-Net与瓶颈检测的肺部细胞图像分割方法[J]. 智能科学与技术学报, 2022,4(4):610-616. DOI： 10.11959/j.issn.2096-6652.202207.

Hong SHAO, Changsheng ZUO, Ping ZHANG. Lung cell image segmentation method combining Attention U-Net and bottleneck detection[J]. Chinese journal of intelligent science and technology, 2022, 4(4): 610-616. DOI： 10.11959/j.issn.2096-6652.202207.

摘要

肺部病理图像具有边界模糊、细胞重叠交织等特点，为了解决细胞分割问题，提出结合Attention U-Net与瓶颈检测的肺部细胞图像分割方法。首先对采集到的图像进行双边滤波和拉普拉斯锐化处理，在去除噪声的同时突出细胞边缘细节，加大目标物与背景的对比；然后对Attention U-Net进行训练，利用训练的模型对病理图像进行分割，得到细胞区域；在模型分割结果的基础上，以面积、周长、圆度为筛选条件建立判别模型，区分单个细胞和重叠细胞；对细胞重叠区域采用瓶颈检测方法确定分离点，采用椭圆拟合方法进行边界修正，得到最终分割结果。实验结果表明，该方法能够对复杂的肺部细胞病理图像进行分割（包括单个细胞与重叠细胞），取得了较好的分割结果。

Abstract

Lung pathological images are characterized by fuzzy boundary and overlapping and interweining cells.In order to solve the problem of cell segmentation

a lung cell image segmentation method combining Attention U-Net and bottleneck detection was proposed.Firstly

bilateral filtering and Laplacian sharpening were performed on the collected images to highlight the details of cell edges and increase the contrast between the target and the background while removing the noise.Then the Attention U-Net was trained

and the pathological images were segmented using the trained model to obtain the cell regions.Based on the segmentation results of the model

the discriminant model was established with area

circumference and roundness as screening conditions to distinguish single cell from overlapping cells.The bottleneck detection method was used to determine the separation point in the overlapping region of cells

and the ellipse fitting method was used to modify the boundary

and the final segmentation result was obtained.Experimental results show that this method can segment complex lung cell pathological images (including single cell and overlapping cells) and achieve good segmentation results.

关键词

Keywords

references

FERNANDES K , CHICCO D , CARDOSO J S , et al . Supervised deep learning embeddings for the prediction of cervical cancer diagnosis [J ] . PeerJ Computer Science , 2018 ,4:e154.

SUN H F , YANG J H , FAN R B , et al . Stepwise local stitching ultrasound image algorithms based on adaptive iterative threshold harris corner features [J ] . Medicine , 2020 , 99 ( 37 ): e22189 .

HSU W Y , LU C C , HSU Y Y . Improving segmentation accuracy of CT kidney cancer images using adaptive active contour model [J ] . Medicine , 2020 , 99 ( 47 ): e23083 .

何安良 , 程兴保 , 廖龙长 , 等 . 耦合H-minima与数学形态学的分水岭遥感图像分割方法 [J ] . 东华理工大学学报(自然科学版) , 2020 , 43 ( 4 ): 396 - 400 .

HE A L , CHENG X B , LIAO L C , et al . An improved watershed method for remote sensing image segmentation coupling H-minima with mathematical morphology [J ] . Journal of East China University of Technology (Natural Science) , 2020 , 43 ( 4 ): 396 - 400 .

CHO M . Performance comparison of two ellipse fitting-based cell separation algorithms [J ] . Journal of Information and Communication Convergence Engineering , 2015 , 13 ( 3 ): 215 - 219 .

KOYUNCU C F , AKHAN E , ERSAHIN T , et al . Iterative H-minima-based marker-controlled watershed for cell nucleus segmentation [J ] . Cytometry Part A , 2016 , 89 ( 4 ): 338 - 349 .

廖苗 , 赵于前 , 曾业战 , 等 . 基于支持向量机和椭圆拟合的细胞图像自动分割 [J ] . 浙江大学学报(工学版) , 2017 , 51 ( 4 ): 722 - 728 .

LIAO M , ZHAO Y Q , ZENG Y Z , et al . Automatic segmentation for cell images based on support vector machine and ellipse fitting [J ] . Journal of Zhejiang University (Engineering Science) , 2017 , 51 ( 4 ): 722 - 728 .

杨秀杰 , 李法平 . 基于曲率和活动轮廓模型的重叠细胞分割算法 [J ] . 西南师范大学学报(自然科学版) , 2018 , 43 ( 4 ): 41 - 47 .

YANG X J , LI F P . Overlapping cells segmentation algorithm based on curvature and active contour model [J ] . Journal of Southwest China Normal University (Natural Science Edition) , 2018 , 43 ( 4 ): 41 - 47 .

何国生 , 施露露 , 邹爽爽 , 等 . 基于自适应阈值的间充质干细胞分割方法研究 [J ] . 电子测量与仪器学报 , 2019 , 33 ( 6 ): 18 - 23 .

HE G S , SHI L L , ZOU S S , et al . Research on mesenchymal stem cells segmentation based on adaptive threshold [J ] . Journal of Electronic Measurement and Instrumentation , 2019 , 33 ( 6 ): 18 - 23 .

FABIJAŃSKA A . Segmentation of corneal endothelium images using a U-Net-based convolutional neural network [J ] . Artificial Intelligence in Medicine , 2018 , 88 : 1 - 13 .

NASR-ESFAHANI E , RAFIEI S , JAFARI M H , et al . Dense pooling layers in fully convolutional network for skin lesion segmentation [J ] . Computerized Medical Imaging and Graphics , 2019 ,78:101658.

SAQIB Q , HAI J , RAN Z , et al . A variant form of 3D-UNet for infant brain segmentation [J ] . Future Generation Computer Systems , 2020 , 108 ( 7 ): 613 - 623 .

SHIMAA E-B , AHMAD A-K , MAHA S . A two-stage framework for automated malignant pulmonary nodule detection in CT scans [J ] . Diagnostics , 2020 , 10 ( 3 ): e131 .

LIU Z . Construction and verification of color fundus image retinal vessels segmentation algorithm under BP neural network [J ] . The Journal of Supercomputing , 2021 , 77 ( 7 ): 7171 - 7183 .

崔文成 , 张鹏霞 , 邵虹 . 基于深度可分离卷积网络的皮肤镜图像病灶分割方法 [J ] . 智能科学与技术学报 , 2020 , 2 ( 4 ): 385 - 393 .

CUI W C , ZHANG P X , SHAO H . Dermoscopic image lesion segmentation method based on deep separable convolutional network [J ] . Chinese Journal of Intelligent Science and Technology , 2020 , 2 ( 4 ): 385 - 393 .

王涛 , 陈凡胜 , 苏晓锋 . 基于各向异性双边滤波红外背景抑制方法研究 [J ] . 湖南大学学报(自然科学版) , 2018 , 45 ( 2 ): 119 - 126 .

WANG T , CHEN F S , SU X F . Research of infrared background suppression method based on anisotropic bilateral filtering [J ] . Journal of Hunan University (Natural Sciences) , 2018 , 45 ( 2 ): 119 - 126 .

王浩 , 张叶 , 沈宏海 , 等 . 图像增强算法综述 [J ] . 中国光学 , 2017 , 10 ( 4 ): 438 - 448 .

WANG H , ZHANG Y , SHEN H H , et al . Review of image enhancement algorithms [J ] . Chinese Optics , 2017 , 10 ( 4 ): 438 - 448 .

OKTAY O , SCHLEMPER J , FOLGOC L L , et al . Attention U-Net:learning where to look for the pancreas [J ] . arXiv preprint , 2018 ,arXiv:1804.03999.

WANG H , ZHANG H , RAY N . Clump splitting via bottleneck detection and shape classification [J ] . Pattern Recognition , 2012 , 45 ( 7 ): 2780 - 2787 .

浏览量

485

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于稠密块和注意力机制的肺部病理图像异常细胞分割