A Fundus Retinal Vessels Segmentation Scheme Based on the Improved Deep Learning U-Net Model

Pan, Xiuqin; Zhang, Qinrui; Zhang, Hong; Li, Sumin

doi:10.1109/access.2019.2935138

Cited by 59 publications

(22 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model was based on a deeper U-net [26]. Pan et al also proposed an improved deep learning U-net model for retinal vessel segmentation by enhancing input images [27]. Gu et al proposed a dense atrous convolution (DAC) block that could capture wider and deeper semantic features with multi-scale atrous convolutions and a residual multi-kernel pooling (RMP) motivated from spatial pyramid pooling.…”

Section: B Deep Learning-based Segmentation Methodsmentioning

confidence: 99%

“…However, the previous methods using the deeper FCN have an imbalanced learning problem such as a higher false-positive rate causing fake branches or higher false-negative rate, causing thinner branches than the ground truth [22], [36]. In other words, there are still inherent problems in retinal blood vessel segmentation, such as wrong segmentation of pathological information and low microvascular segmentation [27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

M-GAN: Retinal Blood Vessel Segmentation by Balancing Losses Through Stacked Deep Fully Convolutional Networks

2020

View full text Add to dashboard Cite

Until now, the human expert segments retinal blood vessels manually in fundus images to inspect human retinal-related diseases, such as diabetic retinopathy and vascular occlusion. Recently, many studies were conducted for automatic retinal vessel segmentation from fundus images through supervised and unsupervised methods to minimize user intervention. However, most of them lack in segmentation robustness and cannot optimize loss functions so that results of the segmentation have made lots of fake or thin branches. This article proposes a new conditional generative adversarial network called M-GAN to conduct accurate and precise retinal vessel segmentation by balancing losses through stacked deep fully convolutional networks. It consists of a newly designed M-generator with deep residual blocks for more robust segmentation and an M-discriminator with a deeper network for more efficient training of the adversarial model. In particular, a multi-kernel pooling block is added between the stacked layers to support the scale-invariance of vessel segmentations of different sizes. The M-generator has down-sampling layers to extract features and up-sampling layers to make segmented retinal blood vessel images from the extracted features. The M-discriminator also has a deeper network similar to the down-sampling of the Mgenerator, but the final layer is constructed as a fully connected layer for decision making. We conduct pre-processing of the input image using automatic color equalization (ACE) to make the retinal vessels of the input fundus image more clear and perform post-processing that makes the vessel branches smooth and reduces false-negatives using a Lanczos resampling method. To verify the proposed method, we used DRIVE, STARE, HRF, and CHASE-DB1datasets and compared the proposed M-GAN with other studies. We measured accuracy, the intersection of union (IoU), F 1 score, and Matthews correlation coefficient (MCC) for comparative analysis. Results of comparison proved that the proposed M-GAN derived superior performance than other studies.INDEX TERMS Retinal blood vessel segmentation, medical imaging, generative adversarial networks (GAN), conditional GAN, stacked deep fully convolutional networks.

show abstract

Section: B Deep Learning-based Segmentation Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

M-GAN: Retinal Blood Vessel Segmentation by Balancing Losses Through Stacked Deep Fully Convolutional Networks

2020

View full text Add to dashboard Cite

show abstract

“…Besides being used for optical cup segmentation, the U-Net model is also employed for segmenting the fundus retinal vessels. This study was conducted by Pan et al [11]. The U-Net model was used to solve several problems experienced by existing methods for retinal vascular segmentation, such as low microvascular segmentation and incorrect pathological information segmentation.…”

Section: Related Workmentioning

confidence: 99%

Optic Cup Segmentation using U-Net Architecture on Retinal Fundus Image

Prastyo

Sumi²,

Nuraini³

2020

j.inf.tech.comp.eng

View full text Add to dashboard Cite

Retinal fundus images are used by ophthalmologists to diagnose eye disease, such as glaucoma disease. The diagnosis of glaucoma is done by measuring changes in the cup-to-disc ratio. Segmenting the optic cup helps petrify ophthalmologists calculate the CDR of the retinal fundus image. This study proposed a deep learning approach using U-Net architecture to carry out segmentation task. This proposed method was evaluated on 650 color retinal fundus image. Then, U-Net was configured using 160 epochs, image input size = 128x128, Batch size = 32, optimizer = Adam, and loss function = Binary Cross Entropy. We employed the Dice Coefficient as the evaluator. Besides, the segmentation results were compared to the ground truth images. According to the experimental results, the performance of optic cup segmentation achieved 98.42% for the Dice coefficient and loss of 1,58%. These results implied that our proposed method succeeded in segmenting the optic cup on color retinal fundus images.

show abstract

“…Experimental results demonstrate that the algorithm is robust even in the case of a low signal-to-noise ratio, but its drawback is the high misclassification rate of fundus optic discs. Although the unsupervised methods performed well in the detection of retinal vessels according to the structure of vessels without using a priori labeling information, the effectiveness on thin tiny vessels and low contrast images still has a lot of room for improvement [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

A Multi-Scale Feature Fusion Method Based on U-Net for Retinal Vessel Segmentation

Yang

Liu

Ren

et al. 2020

Entropy

View full text Add to dashboard Cite

Computer-aided automatic segmentation of retinal blood vessels plays an important role in the diagnosis of diseases such as diabetes, glaucoma, and macular degeneration. In this paper, we propose a multi-scale feature fusion retinal vessel segmentation model based on U-Net, named MSFFU-Net. The model introduces the inception structure into the multi-scale feature extraction encoder part, and the max-pooling index is applied during the upsampling process in the feature fusion decoder of an improved network. The skip layer connection is used to transfer each set of feature maps generated on the encoder path to the corresponding feature maps on the decoder path. Moreover, a cost-sensitive loss function based on the Dice coefficient and cross-entropy is designed. Four transformations—rotating, mirroring, shifting and cropping—are used as data augmentation strategies, and the CLAHE algorithm is applied to image preprocessing. The proposed framework is tested and trained on DRIVE and STARE, and sensitivity (Sen), specificity (Spe), accuracy (Acc), and area under curve (AUC) are adopted as the evaluation metrics. Detailed comparisons with U-Net model, at last, it verifies the effectiveness and robustness of the proposed model. The Sen of 0.7762 and 0.7721, Spe of 0.9835 and 0.9885, Acc of 0.9694 and 0.9537 and AUC value of 0.9790 and 0.9680 were achieved on DRIVE and STARE databases, respectively. Results are also compared to other state-of-the-art methods, demonstrating that the performance of the proposed method is superior to that of other methods and showing its competitive results.

show abstract

A Fundus Retinal Vessels Segmentation Scheme Based on the Improved Deep Learning U-Net Model

Cited by 59 publications

References 15 publications

M-GAN: Retinal Blood Vessel Segmentation by Balancing Losses Through Stacked Deep Fully Convolutional Networks

M-GAN: Retinal Blood Vessel Segmentation by Balancing Losses Through Stacked Deep Fully Convolutional Networks

Optic Cup Segmentation using U-Net Architecture on Retinal Fundus Image

A Multi-Scale Feature Fusion Method Based on U-Net for Retinal Vessel Segmentation

Contact Info

Product

Resources

About