Structure-preserving guided retinal image filtering for optic disc analysis

Cheng, Jun; Li, Zhengguo; Gu, Zaiwang; Fu, Huazhu; Wong, Damon Wing Kee; Liu, Jiang

doi:10.1016/b978-0-08-102816-2.00011-3

Cited by 12 publications

(19 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The guided filter module can be formulated as a fully differentiable layer and we jointly training the guided filter module with backbone network to get direct supervision from sideoutput layers. However, the guided filter is not optimal for retinal image processing due to it often smooth away some fine structures close to flat [16]. In our guided image filter module, the guided image filter is performed on the feature map in order to incorporate more fine structure information from the guidance image to the feature map.…”

Section: B Guided Filter Modulementioning

confidence: 99%

“…Such as additive white Gaussian noise (AWGN) [12], speckle noise [13], salt and pepper noise [14], rician noise [15], etc. The fundus images are also often corrupted by clouding [16]. The human eye is an optical system and the light received by the fundus camera is often attenuated along the path of the light.…”

Section: Introductionmentioning

confidence: 99%

“…Image filters such as bilateral filter [21] and guided image filter [22] play an important role in medical image processing [23]. Guided image filter is an efficient tool to denoise the positron emission tomography (PET) image [24] and fundus image [16]. The guided image filter (GIF) is an edge-preserving filter and computes the filtering output by considering the content of a guidance image.…”

Section: Introductionmentioning

confidence: 99%

“…GIF can make the filtering output more structured and less smoothed than the input with the help of a guidance image. GIF is effective in denoising the fundus image and helps improve the performance for optic disc, optic cup segmentation and vessel segmentation [16].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Guidance Network for Biomedical Image Segmentation

et al. 2020

View full text Add to dashboard Cite

Segmentation of 2D images is a fundamental problem for biomedical image analysis. The most widely used architecture for biomedical image segmentation is U-Net. U-Net introduces skipconnections to restore the spatial information loss caused by down-sampling operations. However, for some tasks such as the retinal vessel segmentation, the loss information of structure can not be fully recovered since the vessels is merely a curve line that can not be detected after several convolutions. In this paper, we introduce a deep guidance network to segment the biomedical image. Our proposed network consists of a guided image filter module to restore the structure information through the guidance image. Our method enables end to end training and fast inference (43ms for one image). We conduct extensive experiments for the task of vessel segmentation and optic disc and cup segmentation. The experiments on four publicly available datasets: ORIGA, REFUGE, DRIVE, and CHASEDB1 verify the effectiveness of our method.

show abstract

Section: B Guided Filter Modulementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Guidance Network for Biomedical Image Segmentation

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The manual assessment of CDR is tedious and exorbitant, and it is not reasonable for large-scale screening. Extricating the region of interest (ROI) takes lesser time to measure the optic cup (OC) and optic disc (OD) region [11]. For glaucoma recognition, the illness pattern in retinal fundus image is unpredictable and covered up, which is not similar to the natural images.…”

Section: Introductionmentioning

confidence: 99%

Improved OD and OC Fragmentation using Deep Learning for the Progression Recognition of Glaucoma

Shanmugam¹,

Raja²,

Pitchai³

2021

Preprint

View full text Add to dashboard Cite

Glaucoma is one of the most hazardous diseases, proceeding to impact and burden an extensive bit of our general population. Appropriately, the initial stage of identification of glaucoma is significant to prevent the permanent vision misfortune. The CDR is the important factor for glaucoma recognition. The precise fragmentation of optic disc and cup is yet an evolving issue. Most of the segmentation based glaucoma recognition methods depends on the handcrafted features. It affects the overall performance of the glaucoma recognition. To resolve this issue, an efficient deep learning based optic cup and disc segmentation using technique multi-label segmentation Au-net has been developed in this paper. The proposed method focusing on the optic cup-to-disc ratio for the recognition of glaucoma, which may be the best system for building a capable, energetic, and accurate structure for glaucoma analysis. This system has been simulated on DRISHTI datasets. The exploratory outcomes indicates the proposed strategy performs well to the best with state-of-the-art methodologies accomplishing a 99% of Accuracy, 88% of Sensitivity and 95.5% of Specificity on the DRISHTI GS1 dataset individually.

show abstract