Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network
Abstract Background Glaucoma is an eye disease that causes vision loss and even blindness. The cup to disc ratio (CDR) is an important indicator for glaucoma screening and diagnosis. Accurate segmentation for the optic disc and cup helps obtain CDR. Although many deep learning-based methods have bee...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-01-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-020-00528-6 |
| _version_ | 1818615790718418944 |
|---|---|
| author | Bingyan Liu Daru Pan Hui Song |
| author_facet | Bingyan Liu Daru Pan Hui Song |
| author_sort | Bingyan Liu |
| collection | DOAJ |
| description | Abstract Background Glaucoma is an eye disease that causes vision loss and even blindness. The cup to disc ratio (CDR) is an important indicator for glaucoma screening and diagnosis. Accurate segmentation for the optic disc and cup helps obtain CDR. Although many deep learning-based methods have been proposed to segment the disc and cup for fundus image, achieving highly accurate segmentation performance is still a great challenge due to the heavy overlap between the optic disc and cup. Methods In this paper, we propose a two-stage method where the optic disc is firstly located and then the optic disc and cup are segmented jointly according to the interesting areas. Also, we consider the joint optic disc and cup segmentation task as a multi-category semantic segmentation task for which a deep learning-based model named DDSC-Net (densely connected depthwise separable convolution network) is proposed. Specifically, we employ depthwise separable convolutional layer and image pyramid input to form a deeper and wider network to improve segmentation performance. Finally, we evaluate our method on two publicly available datasets, Drishti-GS and REFUGE dataset. Results The experiment results show that the proposed method outperforms state-of-the-art methods, such as pOSAL, GL-Net, M-Net and Stack-U-Net in terms of disc coefficients, with the scores of 0.9780 (optic disc) and 0.9123 (optic cup) on the DRISHTI-GS dataset, and the scores of 0.9601 (optic disc) and 0.8903 (optic cup) on the REFUGE dataset. Particularly, in the more challenging optic cup segmentation task, our method outperforms GL-Net by 0.7 $$\%$$ % in terms of disc coefficients on the Drishti-GS dataset and outperforms pOSAL by 0.79 $$\%$$ % on the REFUGE dataset, respectively. Conclusions The promising segmentation performances reveal that our method has the potential in assisting the screening and diagnosis of glaucoma. |
| first_indexed | 2024-12-16T16:39:30Z |
| format | Article |
| id | doaj.art-03111b86afb34f7d82b219686c56e65e |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-12-16T16:39:30Z |
| publishDate | 2021-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-03111b86afb34f7d82b219686c56e65e2022-12-21T22:24:21ZengBMCBMC Medical Imaging1471-23422021-01-0121111210.1186/s12880-020-00528-6Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep networkBingyan Liu0Daru Pan1Hui Song2South China Normal UniversitySouth China Normal UniversitySouth China Normal UniversityAbstract Background Glaucoma is an eye disease that causes vision loss and even blindness. The cup to disc ratio (CDR) is an important indicator for glaucoma screening and diagnosis. Accurate segmentation for the optic disc and cup helps obtain CDR. Although many deep learning-based methods have been proposed to segment the disc and cup for fundus image, achieving highly accurate segmentation performance is still a great challenge due to the heavy overlap between the optic disc and cup. Methods In this paper, we propose a two-stage method where the optic disc is firstly located and then the optic disc and cup are segmented jointly according to the interesting areas. Also, we consider the joint optic disc and cup segmentation task as a multi-category semantic segmentation task for which a deep learning-based model named DDSC-Net (densely connected depthwise separable convolution network) is proposed. Specifically, we employ depthwise separable convolutional layer and image pyramid input to form a deeper and wider network to improve segmentation performance. Finally, we evaluate our method on two publicly available datasets, Drishti-GS and REFUGE dataset. Results The experiment results show that the proposed method outperforms state-of-the-art methods, such as pOSAL, GL-Net, M-Net and Stack-U-Net in terms of disc coefficients, with the scores of 0.9780 (optic disc) and 0.9123 (optic cup) on the DRISHTI-GS dataset, and the scores of 0.9601 (optic disc) and 0.8903 (optic cup) on the REFUGE dataset. Particularly, in the more challenging optic cup segmentation task, our method outperforms GL-Net by 0.7 $$\%$$ % in terms of disc coefficients on the Drishti-GS dataset and outperforms pOSAL by 0.79 $$\%$$ % on the REFUGE dataset, respectively. Conclusions The promising segmentation performances reveal that our method has the potential in assisting the screening and diagnosis of glaucoma.https://doi.org/10.1186/s12880-020-00528-6Deep leariningOptic disc segmentationOptic cup segmentationDepthwise separable convolutionDensely connected |
| spellingShingle | Bingyan Liu Daru Pan Hui Song Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network BMC Medical Imaging Deep learining Optic disc segmentation Optic cup segmentation Depthwise separable convolution Densely connected |
| title | Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network |
| title_full | Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network |
| title_fullStr | Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network |
| title_full_unstemmed | Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network |
| title_short | Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network |
| title_sort | joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network |
| topic | Deep learining Optic disc segmentation Optic cup segmentation Depthwise separable convolution Densely connected |
| url | https://doi.org/10.1186/s12880-020-00528-6 |
| work_keys_str_mv | AT bingyanliu jointopticdiscandcupsegmentationbasedondenselyconnecteddepthwiseseparableconvolutiondeepnetwork AT darupan jointopticdiscandcupsegmentationbasedondenselyconnecteddepthwiseseparableconvolutiondeepnetwork AT huisong jointopticdiscandcupsegmentationbasedondenselyconnecteddepthwiseseparableconvolutiondeepnetwork |