ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks

Roy, Abhijit Guha; Conjeti, Sailesh; Karri, Sri Phani Krishna; Sheet, Debdoot; Katouzian, Amin; Wachinger, Christian; Navab, Nassir

doi:10.1364/boe.8.003627

Cited by 501 publications

(403 citation statements)

References 27 publications

Supporting

Mentioning

380

Contrasting

Order By: Relevance

“…U-Net has shown promising results on the neuronal structures segmentation in electron microscopic recordings and cell segmentation in light microscopic images. It has becomes a popular neural network architecture for biomedical image segmentation tasks [42], [43], [44], [45]. Sevastopolsky et al [43] applied U-Net to directly segment the optic disc and optic cup in retinal fundus images for glaucoma diagnosis.…”

mentioning

confidence: 99%

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Cheng

et al. 2019

IEEE Trans. Med. Imaging

1,503

775

View full text Add to dashboard Cite

Medical image segmentation is an important step in medical image analysis. With the rapid development of convolutional neural network in image processing, deep learning has been used for medical image segmentation, such as optic disc segmentation, blood vessel detection, lung segmentation, cell segmentation, etc. Previously, U-net based approaches have been proposed. However, the consecutive pooling and strided convolutional operations lead to the loss of some spatial information. In this paper, we propose a context encoder network (referred to as CE-Net) to capture more high-level information and preserve spatial information for 2D medical image segmentation. CE-Net mainly contains three major components: a feature encoder module, a context extractor and a feature decoder module. We use pretrained ResNet block as the fixed feature extractor. The context extractor module is formed by a newly proposed dense atrous convolution (DAC) block and residual multi-kernel pooling (RMP) block. We applied the proposed CE-Net to different 2D medical image segmentation tasks. Comprehensive results show that the proposed method outperforms the original U-Net method and other state-of-the-art methods for optic disc segmentation, vessel detection, lung segmentation, cell contour segmentation and retinal optical coherence tomography layer segmentation.

show abstract

mentioning

confidence: 99%

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Cheng

et al. 2019

IEEE Trans. Med. Imaging

1,503

775

View full text Add to dashboard Cite

show abstract

“…From Fig. 5 and Table 1, our network outperformed the current deep learning [11,17,14] and traditional approaches [6,10] respectively. Paired t-tests conducted between our approach and every baseline established that for each metric our results were statistically significant (p < 0.05).…”

Section: Discussionmentioning

confidence: 88%

“…The MADLBP error (in pixels) and mean Hausdorff distance (in microns) across 6×6mm datasets from Device 1 (Tables 2 and 3, top halves) for the expert grader is slightly lower when contrasted against the trained grader. We attribute this to the diffuse appearance of corneal interfaces [4,6,11] and lower axial resolution of Device 1 (3.4µm), thereby causing an expected deviation between the grader annotations, which is reflected in the inter-grader MADLBP error. Similar measures on the MADLBP error (in pixels) and mean Hausdorff distance (in microns) across 3×3mm and 6×6mm datasets from Device 2 ( Tables 2 and 3, bottom halves) were observed.…”

Section: Discussionmentioning

confidence: 99%

Learning To Segment Corneal Tissue Interfaces In Oct Images

Mathai

Lathrop

Galeotti

2019

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

View full text Add to dashboard Cite

Accurate and repeatable delineation of corneal tissue interfaces is necessary for surgical planning during anterior segment interventions, such as Keratoplasty. Designing an approach to identify interfaces, which generalizes to datasets acquired from different Optical Coherence Tomographic (OCT) scanners, is paramount. In this paper, we present a Convolutional Neural Network (CNN) based framework called CorNet that can accurately segment three corneal interfaces across datasets obtained with different scan settings from different OCT scanners. Extensive validation of the approach was conducted across all imaged datasets. To the best of our knowledge, this is the first deep learning based approach to segment both anterior and posterior corneal tissue interfaces. Our errors are 2× lower than non-proprietary state-of-the-art corneal tissue interface segmentation algorithms, which include image analysis-based and deep learning approaches.

show abstract

“…The contour evolution driven by (7) and (8) can become irregular as the MS functional uses only local pixel intensities. To further improve the MS functional we propose to impose some constraint for the functional to control contour evolution.…”

Section: Integrating Shape Constraint To Intensity-based Msmentioning

confidence: 99%

“…Next, we correct the original OCT shape using (9) with the projected b and warping the corrected version back to the original location. In this way, the original irregular OCT shape is pulled back to a regular one used for the next iteration of (7) and (8). The whole process is repeated until convergence.…”

Section: Integrating Shape Constraint To Intensity-based Msmentioning

confidence: 99%

OCT Segmentation: Integrating Open Parametric Contour Model of the Retinal Layers and Shape Constraint to the Mumford-Shah Functional

Duan

Xie

Liu

et al. 2018

Shape in Medical Imaging

View full text Add to dashboard Cite

In this paper, we propose a novel retinal layer boundary model for segmentation of optical coherence tomography (OCT) images. The retinal layer boundary model consists of 9 open parametric contours representing the 9 retinal layers in OCT images. An intensity-based Mumford-Shah (MS) variational functional is first defined to evolve the retinal layer boundary model to segment the 9 layers simultaneously. By making use of the normals of open parametric contours, we construct equal sized adjacent narrowbands that are divided by each contour. Regional information in each narrowband can thus be integrated into the MS energy functional such that its optimisation is robust against different initialisations. A statistical prior is also imposed on the shape of the segmented parametric contours for the functional. As such, by minimising the MS energy functional the parametric contours can be driven towards the true boundaries of retinal layers, while the similarity of the contours with respect to training OCT shapes is preserved. Experimental results on real OCT images demonstrate that the method is accurate and robust to low quality OCT images with low contrast and high-level speckle noise, and it outperforms the recent geodesic distance based method for segmenting 9 layers of the retina in OCT images.

show abstract

ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks

Cited by 501 publications

References 27 publications

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Learning To Segment Corneal Tissue Interfaces In Oct Images

OCT Segmentation: Integrating Open Parametric Contour Model of the Retinal Layers and Shape Constraint to the Mumford-Shah Functional

Contact Info

Product

Resources

About