Group and Shuffle Convolutional Neural Networks with Pyramid Pooling Module for Automated Pterygium Segmentation
Abstract
:1. Introduction
2. Related Works
2.1. Automated Pterygium Screening
2.2. Convolutional Neural Networks-Based Semantic Segmentation
3. Methods
3.1. FC-DenseNet
3.2. Group-PPM-Net
4. Experimental Results and Discussion
4.1. Dataset
4.2. Experimental Setup
4.3. Performance Metrics
4.4. Performance Benchmark with the State-of-the-Art CNN Segmentation Models
4.5. Ablation Study of the Group-PPM-Net
5. Conclusions and Future Works
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Conflicts of Interest
Abbreviations
PPM | Pyramid Pooling Module |
CNN | Convolutional Neural Networks |
ILSVRC | ImageNet Large Scale Visual Recognition Challenge |
ASPP | Atrous Spatial Pyramid Pooling |
ReLU | Rectified Linear Unit |
GIMP2 | GNU Image Manipulation Program 2 |
FC-DenseNet | Fully Convolutional Dense Network |
FCN | Fully Convolutional Network |
PSP-Net | Pyramid Scene Parsing Network |
SegNet | Semantic Pixel-Wise Segmentation Network |
TD | Transition Down |
TU | Transition Up |
References
- Zulkifley, M.A.; Abdani, S.R.; Zulkifley, N.H. Pterygium-net: A deep learning approach to pterygium detection and localization. Multimed. Tools Appl. 2019, 78, 34563–34584. [Google Scholar] [CrossRef]
- Abdani, S.R.; Zulkifley, M.A.; Hussain, A. Compact convolutional neural networks for pterygium classification using transfer learning. In Proceedings of the IEEE International Conference on Signal and Image Processing Applications, Kuala Lumpur, Malaysia, 17–19 September 2019; pp. 140–143. [Google Scholar]
- Zhou, W.; Zhu, Y.; Zhang, B.; Qiu, W.; Yao, Y. The role of ultraviolet radiation in the pathogenesis of pterygia (review). Mol. Med. Rep. 2016, 14, 3–15. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Sekelj, S.; Dekaris, J.; Kondza-Krstonijevic, E.; Gabric, N.; Predovic, J.; Mitrovic, S. Ultraviolet light and pterygium. Coll. Antropol. 2007, 31, 45–47. [Google Scholar] [PubMed]
- Hashemi, H.; Khabazkhoob, M.; Yekta, A.; Jafarzadehpour, E.; Ostadimoghaddam, H.; Kangari, H. The prevalence and determinants of pterygium in rural areas. J. Curr. Ophthalmol. 2016, 29, 194–198. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Fonseca, E.C.; Rocha, E.M.; Arruda, G.V. Comparison among adjuvant treatments for primary pterygium: A network meta-analysis. Br. J. Ophthalmol. 2018, 102, 748–756. [Google Scholar] [CrossRef] [PubMed]
- Twelker, J.D.; Bailey, I.L.; Mannis, M.J.; Satariano, W.A. Evaluating pterygium severity: A survey of corneal specialists. Cornea 2000, 19, 292–296. [Google Scholar] [CrossRef] [PubMed]
- Bochkovskiy, A.; Wang, C.; Liao, H.M. Yolov4: Optimal speed and accuracy of object detection. ar**. J. Kejuruter. 2020, 32, 91–97. [Google Scholar]
- Abdani, S.R.; Zulkifley, M.A.; Moubark, A.M. Pterygium tissues segmentation using densely connected deeplab. In Proceedings of the 2020 IEEE 10th Symposium on Computer Applications Industrial Electronics (ISCAIE), Penang, Malaysia, 18–19 April 2020; pp. 229–232. [Google Scholar]
- Simonyan, K.; Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition; Technical Report; University of Oxford: Oxford, UK, 2014. [Google Scholar]
- Zulkifley, M.A.; Trigoni, N. Multiple-model fully convolutional neural networks for single object tracking on thermal infrared video. IEEE Access 2018, 6, 42790–42799. [Google Scholar] [CrossRef]
- Rochan, M.; Ye, L.; Wang, Y. Video summarization using fully convolutional sequence networks. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 347–363. [Google Scholar]
- Zulkifley, M.A.; Mohamed, N.A.; Zulkifley, N.H. Squat angle assessment through tracking body movements. IEEE Access 2019, 7, 48635–48644. [Google Scholar] [CrossRef]
- Long, J.; Shelhamer, E.; Darrell, T. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015; pp. 3431–3440. [Google Scholar]
- Chen, L.-C.; Yang, Y.; Wang, J.; Xu, W.; Yuille, A.L. Attention to scale: Scale-aware semantic image segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 3640–3649. [Google Scholar]
- Yu, F.; Koltun, V. Multi-scale context aggregation by dilated convolutions. In Proceedings of the International Conference on Learning Representations (ICLR), San Juan, Puerto Rico, 2–4 May 2016. [Google Scholar]
- Noh, H.; Hong, S.; Han, B. Learning deconvolution network for semantic segmentation. In Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7–13 December 2015; pp. 1520–1528. [Google Scholar]
- Badrinarayanan, V.; Kendall, A.; Cipolla, R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 2481–2495. [Google Scholar] [CrossRef] [PubMed]
- Ronneberger, O.; Fischer, P.; Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015; Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F., Eds.; Springer International Publishing: Cham, Switzerland, 2015; pp. 234–241. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. ar**v 2015, ar**v:1512.03385. [Google Scholar]
- Cao, D.; Yin, H.; Chen, J.; Tang, F.; Peng, M.; Li, R.; **e, H.; Wei, X.; Zhao, Y.; Sun, G. Clinical analysis of 10 pregnant women with covid-19 in wuhan, china: A retrospective study. Int. J. Infect. Dis. 2020, 95, 294–300. [Google Scholar] [CrossRef] [PubMed]
- Shah, S.; Ghosh, P.; Davis, L.S.; Goldstein, T. Stacked u-nets: A no-frills approach to natural image segmentation. ar**v 2018, ar**v:1804.10343. [Google Scholar]
- Chen, L.; Papandreou, G.; Schroff, F.; Adam, H. Rethinking atrous convolution for semantic image segmentation. ar**v 2017, ar**v:1706.05587. [Google Scholar]
- Chen, L.-C.; Zhu, Y.; Papandreou, G.; Schroff, F.; Adam, H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Computer Vision–ECCV 2018; Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y., Eds.; Springer International Publishing: Cham, Switzerland, 2018; pp. 833–851. [Google Scholar]
- Tai, S.-K.; Dewi, C.; Chen, R.-C.; Liu, Y.-T.; Jiang, X.; Yu, H. Deep learning for traffic sign recognition based on spatial pyramid pooling with scale analysis. Appl. Sci. 2020, 10, 6997. [Google Scholar] [CrossRef]
- Jose, A.; Lopez, R.D.; Heisterklaus, I.; Wien, M. Pyramid Pooling of Convolutional Feature Maps for Image Retrieval. In Proceedings of the 2018 25th International Conference on Image Processing (ICIP), Athens, Greece, 7–10 October 2018; pp. 480–484. [Google Scholar]
- Abdani, S.R.; Zulkifley, M.A.; Siham, M.N.; Abiddin, N.Z.; Aziz, N.A.A. Paddy Fields Segmentation using Fully Convolutional Network with Pyramid Pooling Module. In Proceedings of the 2020 IEEE 5th International Symposium on Telecommunication Technologies (ISTT), Shah Alam, Malaysia, 9–11 November 2020; pp. 30–34. [Google Scholar]
- Zhu, R.; Mao, X.; Zhu, Q.; Li, N.; Yang, Y. Text detection based on convolutional neural networks with spatial pyramid pooling. In Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, 25–28 September 2016; pp. 1032–1036. [Google Scholar]
- Ioannou, Y. A Tutorial on Filter Groups (Grouped Convolution). 2017. Available online: https://blog.yani.io/filter-group-tutorial/ (accessed on 23 May 2021).
- Bernard, O.; Lalande, A.; Zotti, C.; Cervenansky, F.; Yang, X.; Heng, P.A.; Cetin, I.; Lekadir, K.; Camara, O.; Ballester, M.A.G.; et al. Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? IEEE Trans. Med. Imaging 2018, 37, 2514–2525. [Google Scholar] [CrossRef] [PubMed]
- Dewi, C.; Chen, R.C.; Liu, Y.T.; Tai, S.K. Synthetic Data generation using DCGAN for improved traffic sign recognition. Neural Comput. Appl. 2021, 1–16. [Google Scholar] [CrossRef]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations, Banff, AB, Canada, 14–16 April 2014. [Google Scholar]
Method | Image/Second | Parameters | ||||
---|---|---|---|---|---|---|
DeepLab V3+ [36] | 0.7683 | 0.5575 | 64.6621 | 0.2077 | 2.4778 | 41,051,088 |
Stacked U-Net [34] | 0.8046 | 0.6420 | 41.4411 | 0.608 | 3.7186 | 3,035,650 |
PSP-Net [10] | 0.8884 | 0.7824 | 35.1803 | 0.6882 | 2.3976 | 27,838,400 |
FCN [26] | 0.9047 | 0.8110 | 15.2212 | 0.6909 | 2.5622 | 134,393,428 |
FC-DenseNet [9] | 0.9117 | 0.8239 | 13.2491 | 0.7512 | 2.7242 | 14,594,658 |
U-Net [31] | 0.9128 | 0.8251 | 13.9372 | 0.7255 | 4.0951 | 31,032,834 |
DeepLab V2 [35] | 0.9169 | 0.8327 | 22.5102 | 0.7158 | 2.5927 | 71,419,720 |
SegNet [30] | 0.9185 | 0.8354 | 14.6579 | 0.7386 | 3.9844 | 29,444,166 |
Group-PPM-Net | 0.9329 | 0.8632 | 11.9989 | 0.7946 | 2.6295 | 13,219,138 |
Method | Image/Second | ||||
---|---|---|---|---|---|
FC-DenseNet | 0.9117 | 0.8239 | 13.2491 | 0.7512 | 2.7242 |
FC-DenseNet + Group | 0.8623 | 0.7508 | 18.3827 | 0.6826 | 2.7023 |
FC-DenseNet + Shuffle | 0.6774 | 0.7269 | 27.2436 | 0.6294 | 2.6866 |
FC-DenseNet + PPM | 0.9190 | 0.8402 | 11.4322 | 0.7795 | 2.6215 |
FC-DenseNet + Group + PPM | 0.8504 | 0.7324 | 19.2126 | 0.669 | 2.6844 |
FC-DenseNet + Shuffle + PPM | 0.9099 | 0.8243 | 14.7687 | 0.7556 | 2.6789 |
FC-DenseNet + Group + Shuffle | 0.9186 | 0.8348 | 14.1382 | 0.7368 | 2.6635 |
Group-PPM-Net (Encoder) | 0.9330 | 0.8640 | 11.5474 | 0.7966 | 2.6108 |
Group-PPM-Net (Decoder) | 0.9327 | 0.8626 | 10.3480 | 0.7949 | 2.6269 |
Group-PPM-Net (Both sides) | 0.9329 | 0.8632 | 11.9989 | 0.7946 | 2.5823 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Abdani, S.R.; Zulkifley, M.A.; Zulkifley, N.H. Group and Shuffle Convolutional Neural Networks with Pyramid Pooling Module for Automated Pterygium Segmentation. Diagnostics 2021, 11, 1104. https://doi.org/10.3390/diagnostics11061104
Abdani SR, Zulkifley MA, Zulkifley NH. Group and Shuffle Convolutional Neural Networks with Pyramid Pooling Module for Automated Pterygium Segmentation. Diagnostics. 2021; 11(6):1104. https://doi.org/10.3390/diagnostics11061104
Chicago/Turabian StyleAbdani, Siti Raihanah, Mohd Asyraf Zulkifley, and Nuraisyah Hani Zulkifley. 2021. "Group and Shuffle Convolutional Neural Networks with Pyramid Pooling Module for Automated Pterygium Segmentation" Diagnostics 11, no. 6: 1104. https://doi.org/10.3390/diagnostics11061104