综合应用Faster R-CNN和U-net的心脏MRI图像分割

doi:10.11896/jsjkx.220600047

计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220600047-9.doi: 10.11896/jsjkx.220600047

• 图像处理&多媒体技术 • 上一篇下一篇

综合应用Faster R-CNN和U-net的心脏MRI图像分割

韩俊玲¹, 李博², 康晓东¹, 杨靖怡¹, 刘汉卿¹, 王笑天¹

1 天津医科大学医学影像学院天津 300202;
2 天津医科大学三中心临床学院天津 300170

出版日期:2023-06-10 发布日期:2023-06-12
通讯作者: 康晓东(kxd2004@126.com)
作者简介:(hjl19893381889@163.com)
基金资助:
京津冀协同创新项目(17YEXTZC00020)

Cardiac MRI Image Segmentation Based on Faster R-CNN and U-net

HAN Junling¹, LI Bo², KANG Xiaodong¹, YANG Jingyi¹, LIU Hanqing¹, WANG Xiaotian¹

1 School of Medical Image,Tianjin Medical University,Tianjin 300202,China;
2 Department of the Third Central Clinical College of Tianjin Medical University,Tianjin 300170,China

Online:2023-06-10 Published:2023-06-12
About author:HAN Junling,born in 1999,undergra-duate.Her main research interest is medical image processing. KANG Xiaodong,born in 1964,Ph.D, professor,is a member of China Computer Federation.His main research interests include medical image proces-sing and medical information system integration.
Supported by:
Beijing Tianjin Hebei Collaborative Innovation Project(17YEXTZC00020).

摘要/Abstract

摘要： 为解决现有MRI神经网络分割中存在因输入端图像信息多样导致分割精度下降的问题,提出了引入Faster R-CNN和U-net机制的MRI图像分割方法。选择公开心脏MRI分割挑战赛数据集ACDC和SCD,清洗和修改数据集格式后送入后续神经网络。首先,应用Faster R-CNN对目标图像进行检测,以对原始输入图像进行预处理,并去掉冗杂的背景信息。其次,对预处理后的图像进行U-net分割,同时为检验引入Faster R-CNN后,对分割网络的性能和精度是否提高,采用了消融实验和对比实验。消融实验去掉了U-net分割网络中的检测裁剪模块,选择U-net及其改进网络分别做一组消融实验结果。实验结果表明,新方法的平均交并比和Dice系数在ACDC数据集上为0.89和0.94,分别提高了7.3%和5%,在SCD数据集上为0.96和0.98,分别提高了5%和3%,实现了MRI图像的自动预处理和分割。

关键词: U-net, Faster R-CNN, MRI, 分割算法, 深度学习

Abstract: In order to solve the problem that the segmentation accuracy of the existing MRI neural network is reduced due to the diversity of input image information.An MRI image segmentation method using Faster R-CNN and U-net mechanism is proposed.Selecting the public cardiac MRI segmentation challenge datasets ACDC and SCD,cleaning and modifing the format of the dataset and sending them to the subsequent neural network.First,Faster R-CNN is applied to target image detection to preprocess the original input image and remove redundant background information.Second,performing U-net segmentation on the preprocessed images.At the same time,in order to test whether the performance and accuracy of the segmentation network are improved after the introduction of Faster R-CNN,ablation experiments and comparison experiments are conducted.In the ablation experiment,the detection and cropping module in the U-net segmentation network is removed,and the U-net and its improved network are selected to do a set of ablation experiments respectively.Experiments show that the average intersection ratio and Dice coefficient of the new method is 0.89 and 0.94 on the ACDC dataset,respectively,which is 7.3% and 5% higher.On the SCD dataset,it is 0.96 and 0.98,which is 5% and 3% higher,respectively.Automatic preprocessing and segmentation of MRI images is achieved.

Key words: U-net, Faster R-CNN, MRI, Segmentation algorithm, Deep learning

中图分类号:

TP391

韩俊玲, 李博, 康晓东, 杨靖怡, 刘汉卿, 王笑天. 综合应用Faster R-CNN和U-net的心脏MRI图像分割[J]. 计算机科学, 2023, 50(6A): 220600047-9. https://doi.org/10.11896/jsjkx.220600047

HAN Junling, LI Bo, KANG Xiaodong, YANG Jingyi, LIU Hanqing, WANG Xiaotian. Cardiac MRI Image Segmentation Based on Faster R-CNN and U-net[J]. Computer Science, 2023, 50(6A): 220600047-9. https://doi.org/10.11896/jsjkx.220600047

参考文献

[1]KANG X D.Medical Image Processing[M].People’s MedicalPublishing House.2009:200.
[2]SUTTON R T,PINCOCK D,BAUMGART D C,et al.An overview of clinical decision support systems:benefits,risks,and strategies for success[J].Npj Digital Medicine,2020,17(2020):3.
[3]HESAMIAN M H,JIA W,HE X,et al.Deep Learning Tech-niques for Medical Image Segmentation:Achievements and Challenges[J].Journal of Digital Imaging,2019,32(4):582-96.
[4]KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNetClassification with Deep Convolutional Neural Networks[J].Communications of the ACM,2012,60(6):84-90.
[5]HAVAEI M,DAVY A,WARDE-FARLEY D,et al.Braintumor segmentation with Deep Neural Networks[J].Medical Image Analysis,2017,35:18-31.
[6]SHELHAMER E,LONG J,DARRELL T.Fully Convolutional Networks for Semantic Segmentation[J].Ieee Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-51.
[7]CHRIST P F,ELSHAER M,ETTLINGER F,et al.Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields[C]//proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention-MICCAI.2016:415-423.
[8]RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolu-tional Networks for Biomedical Image Segmentation[J].Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015 Lecture Notes in Computer Science,2015,9351:234-241.
[9]TIAN X,WANG L,DING Q.Overview of Image Semantic Segmentation Methods Based on Deep Learning[J].Journal of Software Science,2019,30(2):440-468.
[10]WANG B,YUAN F Q,CHEN Z R,et al.Automatic segmentation method for multi-level U-Net thyroid ultrasound images[J].Computer Engineering and Applications,2023,59(5):205-212.
[11]IOFFE S,SZEGEDY C.Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift[J].JMLRorg,2015,37:448-56.
[12]AMMAR A,BOUATTANE O,YOUSSFI M.Automatic cardiac cine MRI segmentation and heart disease classification[J].Comput Med Imaging Graph,2021,88:101864.
[13]WANG X Y,YANG S,FANG Y Q,et al.SK-Unet:An Im-proved U-Net Model With Selective Kernel for the Segmentation of LGE Cardiac MR Images[J].IEEE Sensors Journal,2021,21(10):11643-53.
[14]LIU C,LIN N,CAO Y J,et al.Seg-CapNet:Neural Network Model for Cardiac MRI Image Segmentation[J].Chinese Journal of Imaging and Graphics,2021,26(2):452-463.
[15]ZOU Z,SHI Z,GUO Y,et al.Object Detection in 20 Years:A Survey[J].arXiv:1905.05055,2019.
[16]LIU T,TIAN Y,ZHAO S F,et al.Automatic Whole Heart Segmentation Using a Two-Stage U-Net Framework and an Adaptive Threshold Window[J].IEEE Access,2019,7:83628-83636.
[17]REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:To-wards Real-Time Object Detection with Region Proposal Networks[J].Ieee Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[18]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[J].IEEE,2016:1063-6919.
[19]YANG H J,WANG E S,SUI Y X,et al.Simplified residual structure and fast deep residual network[J].Journal of Jilin University(Engineering Edition),2022,52(6):1413-1421.
[20]HINTON G E,KRIZHEVSKY A,WANG S D.Transforming Auto-Encoders[C]//Proceedings of the Artificial Neural Networks and Machine Learning-ICANN 2011-21st International Conference on Artificial Neural Networks.Berlin:Springer,2011,6791:44-51.
[21]ZHANG X Y,WANG B,AN W C,et al.3D U-Net++ glioma segmentation network based on fusion loss function[J].Computer Science,2021,48(9):187-193.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

综合应用Faster R-CNN和U-net的心脏MRI图像分割

Cardiac MRI Image Segmentation Based on Faster R-CNN and U-net

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 0