Multi-Modal Self-Supervised Pre-Training for Joint Optic Disc and Cup Segmentation in Eye Fundus Images

Hervella, Álvaro S.; Ramos, Lucía; Rouco, José; Novo, Jorge

doi:10.1109/icassp40776.2020.9053551

“…While Aĺvaro S. Hervella etl. [24] propose a novel selfsupervised pre-training method to improve the segmentation of the optic disc and cup which also achieved a good result. All of the above methods have achieved good segmentation results, but through experimental comparison, our proposed method achieves a higher score than them, especially in OC segmentation task.…”

Section: Discussionmentioning

confidence: 96%

“…In order to verify that our method is better than other methods, we compare our proposed method with the state-of-the-art approaches, such as pOSAL framework [19], GL-Net [20], M-Net [16], Stack-U-Net [21], WGAN [22], two-stage Mask R-CNN [23], multi-modal self-supervised pretraining network [24], Shuang Yu [25] and A. Sevastopolsky [10]. Additionally, we compare with the Fully convolutional network U-Net [15].…”

Section: Discussionmentioning

confidence: 99%

“…Because GAN-based methods and other deep learning networks also achieve satisfactory segmentation results in OD and OC segmentation task. Therefore, we then compared the use of generative adversarial ideas, WGAN [19], GL-Net [20] and pOSAL framework [22] and other deep learning methods [23], [24]. From Table 5 and Table 6, we can see that our proposed method is still performs better than these methods.…”

Section: Compared With Other Networkmentioning

confidence: 95%

“…The first row is the input image, the second is the ground truth, the third rows is the simple DDSC-Net segmentation results, fourth row is the DDSC-Net without multi input,fifth row is the results of DDSC-Net and sixth row is the reprocess result,where the white region denote the background, and the gray and black region denote the OD and OC segmentations. Tables Table 1 Localization accuracy [15] 0.950 0.820 --M-Net [16] 0.959 0.866 --Stack-U-Net [21] 0.970 0.890 --A. Sevastopolsky [10] -0.850 -0.750 Shuang Yu [25] 0.973 0.887 --MULTI-MODEL-PRE-TRAINING [24] 0.960 0.902 0.924 0.823 WGAN [22] 0.954 0.840 0.912 0.724 pOSAL [22] 0.965 0.858 --GL-Net [20] 0.971 0.905 --Proposed 0.978 0.912 0.957 0.844…”

Section: Loss Functionmentioning

confidence: 99%

See 2 more Smart Citations

Joint Optic Disc and Dup Segmentation Based on Densely Connected Depthwise Separable Convolution Deep Network

Liu

¹

,

Pan

²

,

Song

³

2020

Preprint

0

View full text Add to dashboard Cite

Background: Glaucoma is an eye disease that causes vision loss and even blindness. The cup to disc ratio is the main indicator used to screen and diagnose glaucoma, optic disc and optic cup segmentation can assist computer in diagnosing glaucoma.Therefore, accurate segmentation of optic disc and optic cup is beneficial to the screening and diagnosis of glaucoma and helps patients diagnose and treat early. Method: In this paper, we consider the segmentation of the optic disc and the optic cup as a multi-category semantic segmentation task, and proposed a deep learning-based model model named DDSC-Net(densely connected depthwise separable convolution network) to extract the optic disc and the optic cup. The backbone network is composed of densely connected deep separable convolution blocks to form a deeper network and the image pyramid input is introduce into the input layer to widen the network. In the post-process, we apply the morphological method to refine the output segmentation results. Result: The proposed method is evaluated on two publicly available datasets, DRISHTI-GS dataset and REFUGE dataset. And the experiment results show that our DDSC-Net outperforms state-of-the-art optic disc and cup segmentation methods in terms of disc coefficients and Jaccard score. Furthermore,our method achieves the best result on the more challenging optic cup segmentation task. Conclusion: The promising segmention performances reveal that our method has potential in assisting the screening and diagnosis of the glaucoma.

show abstract

“…In order to verify that our method is better than other methods, we compare our proposed method with the state-of-the-art approaches, such as pOSAL framework [27], GL-Net [28], M-Net [16], Stack-U-Net [29], WGAN [30], two-stage Mask R-CNN [31], multi-modal self-supervised pretraining network [32], Shuang Yu [33] and A. Sevastopolsky [10]. Additionally, we compare with the Fully convolutional network U-Net [15].…”

Section: Discussionmentioning

confidence: 99%

Joint Optic Disc and Dup Segmentation Based on Densely Connected Depthwise Separable Convolution Deep Network

Liu

¹

,

Pan

²

,

Song

³

2020

Preprint

0

View full text Add to dashboard Cite

Background: Glaucoma is an eye disease that causes vision loss and even blindness. The cup to disc ratio is the main indicator used to screen and diagnose glaucoma, optic disc and optic cup segmentation can assist computer in diagnosing glaucoma.Therefore, accurate segmentation of optic disc and optic cup is beneficial to the screening and diagnosis of glaucoma and helps patients diagnose and treat early. Method: In this paper, we consider the segmentation of the optic disc and the optic cup as a multi-category semantic segmentation task, and proposed a deep learning-based model model named DDSC-Net(densely connected depthwise separable convolution network) to extract the optic disc and the optic cup. The backbone network is composed of densely connected deep separable convolution blocks to form a deeper network and the image pyramid input is introduce into the input layer to widen the network. In the post-process, we apply the morphological method to refine the output segmentation results. Result: The proposed method is evaluated on two publicly available datasets, DRISHTI-GS dataset and REFUGE dataset. And the experiment results show that our DDSC-Net outperforms state-of-the-art optic disc and cup segmentation methods in terms of disc coefficients and Jaccard score. Furthermore,our method achieves the best result on the more challenging optic cup segmentation task. Conclusion: The promising segmention performances reveal that our method has potential in assisting the screening and diagnosis of the glaucoma.

show abstract

RMSDSC‐Net: A robust multiscale feature extraction with depthwise separable convolution network for optic disc and cup segmentation

Zhou

¹

,

Yuhan

²

,

Ji

³

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Glaucoma is an eye disease that leads to irreversible vision loss. Accurate Optic Disc (OD) and Optic Cup (OC) segmentation can effectively facilitate ophthalmologist in glaucoma diagnosis. Recently, a series of deep learning approaches attain promising performance in OD and OC segmentation but still face the challenge to precisely segment OC boundary with enhanced computational efficiency. To address this issue, we propose a novel network named Robust Multiscale Feature Extraction with Depthwise Separable Convolution (RMSDSC‐Net), which can better solve the challenging tradeoff between segmentation performance and network cost. The proposed RMSDSC‐Net is mainly composed of Multiscale Input (MSI), Depthwise Separable Convolution Unit (DSCU), Dilated Convolution Block (DCB), and External Residual Connection (ERC). First, the introduction of MSI can reduce the information loss due to the pooling layers used in the network for capturing rich feature representations. Next, to enhance segmentation performance and computational efficiency, this paper designs DSCU and DCB modules to avoid spatial information loss from minor details of the image and preserve more high‐level semantic features. Finally, this paper develops ERC established between the encoding layers and decoding layers to minimize the feature degradation problem. Hence, a high segmentation performance can be achieved using a shallow network. To evaluate the performance of the proposed network, extensive experiments have been enforced on two publicly available databases, DRISHTI‐GS and REFUGE. Our approach outperforms the state‐of‐the‐art approaches with the Dice Coefficient of (0.978, 0.919) and (0.965, 0.910) for OD and OC segmentation on DRISHTI‐GS and REFUGE databases, respectively. As a result, the proposed approach has a strong potential in analyzing fundus images for glaucoma diagnosis.

show abstract

Multi-Modal Self-Supervised Pre-Training for Joint Optic Disc and Cup Segmentation in Eye Fundus Images

Cited by 25 publications

References 16 publications

Joint Optic Disc and Dup Segmentation Based on Densely Connected Depthwise Separable Convolution Deep Network

Joint Optic Disc and Dup Segmentation Based on Densely Connected Depthwise Separable Convolution Deep Network

Joint Optic Disc and Dup Segmentation Based on Densely Connected Depthwise Separable Convolution Deep Network

RMSDSC‐Net: A robust multiscale feature extraction with depthwise separable convolution network for optic disc and cup segmentation

Contact Info

Product

Resources

About