skip to main content
10.1145/3364836.3364869acmotherconferencesArticle/Chapter ViewAbstractPublication PagesisicdmConference Proceedingsconference-collections
research-article

Expanded Mask R-CNN's Retinal Edema Detection Network

Published: 24 August 2019 Publication History

Abstract

To better assist doctors in rapid recognition of lesions in OTC edema images, an expended Mask R-CNN method was proposed to detect and recognize the retinal edema. We also design a software to label 8960 images automatically. A large number of images can be labeled in a few minutes. For the backbone of Resnet101, we add a parallel 1*1 convolution to the basic residual block, the residual blocks are widens in its width, the receptive field of feature maps are enlarged, and more richer feature information can be extracted. By adding the filters with the size of 1*1, the outputs of the filters are equivalent to multiplying a coefficient for feature maps, which can enhance the representation of feature maps and facilitate the location of the edema area. In our experiments, 8960 retinal edema images were used to train the model and 1920 images were kept to test. Compared with Faster R-CNN and Mask R-CNN, the expended Mask R-CNN achieved more accurate location of the edema lesion area. The recognition accuracy of the expanded Mask R-CNN, Faster R-CNN and Mask R-CNN can reach are 92.27%,87.95%,90.65%, respectively.

References

[1]
He K, Zhang X, Ren S, et al. Spatial Pyramid Pooling In Deep Convolutional Networks for Visual Recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 37(9):1904--16.
[2]
Girshick R. Fast R-CNN[C]// IEEE International Conference on Computer Vision. Santiago,IEEE, 2015: 1440--1448.
[3]
Ren S, Girshick R, Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection With Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137--1149.
[4]
He K, Gkioxari G, Dollar P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, PP(99):1--1.
[5]
Russakovsky O, Deng J, Su H, et al. ImageNet Large Scale Visual Recognition Challenge[J]. International Journal of Computer Vision, 2014, 115(3):211--252.
[6]
Lin T Y, Maire M, Belongie S, et al. Microsoft COCO: Common Objects In Context[C] // ECCV, Zurich,2014, Switzerland, Springer, Cham,2014: pp. 740--755.
[7]
He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[C] //CVPR, Las Vegas, NV, United States,2016, pp: 770--778.
[8]
Lin T Y, Dollár, Piotr, Girshick R, et al. Feature Pyramid Networks For Object Detection[C]// CVPR, Hawaii Convention Center,2017: 936--944.
[9]
Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking The Inception Architecture For Computer Vision[C]//CVPR, Las Vegas, NV, United States 2016, pp: 2818--2826.
[10]
Ioffe S, Szegedy C. Batch Normalization: Accelerating Deep Network Training By Reducing Internal Covariate Shift[J]. International Conference on International Conference on Machine Learning. 2015.
[11]
Pan S J, Yang Q. A Survey on Transfer Learning[J]. IEEE Transactions on Knowledge & Data Engineering, 2010, 22(10):1345--1359.

Cited By

View all
  • (2022)OCT Retinal and Choroidal Layer Instance Segmentation Using Mask R-CNNSensors10.3390/s2205201622:5(2016)Online publication date: 4-Mar-2022

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ISICDM 2019: Proceedings of the Third International Symposium on Image Computing and Digital Medicine
August 2019
370 pages
ISBN:9781450372626
DOI:10.1145/3364836
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

  • Xidian University

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 24 August 2019

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Width expansion
  2. automatic labeling
  3. retinal edema detection

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

ISICDM 2019

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)4
  • Downloads (Last 6 weeks)0
Reflects downloads up to 08 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2022)OCT Retinal and Choroidal Layer Instance Segmentation Using Mask R-CNNSensors10.3390/s2205201622:5(2016)Online publication date: 4-Mar-2022

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media