Pathological OCT Retinal Layer Segmentation Using Branch Residual U-Shape Networks

Apostolopoulos, Stefanos; Zanet, Sandro De; Ciller, Carlos; Wolf, Sebastián; Sznitman, Raphael

doi:10.1007/978-3-319-66179-7_34

Cited by 74 publications

(69 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a formal definition of an ensemble, the interested reader could refer to Supplementary Material Section 1. Given a set of manually annotated B-scans, we trained four different U-shaped FCNN models: three of them are inspired in the U-Net 18 , the BRU-Net 19 and the All-Dropout 20 architectures, while the fourth one corresponds to our U2-Net 21 . The U-Net was selected due to its standard design, whereas the BRU-Net was chosen based on its performance for retinal layer segmentation in pathological OCT scans.…”

Section: Manual Annotation Protocol and Data Organizationmentioning

confidence: 99%

Automated Quantification of Photoreceptor alteration in macular disease using Optical Coherence Tomography and Deep Learning

Orlando

Gerendas

Riedl

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Diabetic macular edema (DME) and retina vein occlusion (RVO) are macular diseases in which central photoreceptors are affected due to pathological accumulation of fluid. Optical coherence tomography allows to visually assess and evaluate photoreceptor integrity, whose alteration has been observed as an important biomarker of both diseases. However, the manual quantification of this layered structure is challenging, tedious and time-consuming. In this paper we introduce a deep learning approach for automatically segmenting and characterising photoreceptor alteration. The photoreceptor layer is segmented using an ensemble of four different convolutional neural networks. En-face representations of the layer thickness are produced to characterize the photoreceptors. The pixel-wise standard deviation of the score maps produced by the individual models is also taken to indicate areas of photoreceptor abnormality or ambiguous results. Experimental results showed that our ensemble is able to produce results in pair with a human expert, outperforming each of its constitutive models. No statistically significant differences were observed between mean thickness estimates obtained from automated and manually generated annotations. Therefore, our model is able to reliable quantify photoreceptors, which can be used to improve prognosis and managment of macular diseases.

show abstract

Section: Manual Annotation Protocol and Data Organizationmentioning

confidence: 99%

Automated Quantification of Photoreceptor alteration in macular disease using Optical Coherence Tomography and Deep Learning

Orlando

Gerendas

Riedl

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…To enhance the feature learning ability of U-Net, some new modules have been proposed to replace the original blocks. Stefanos et al [48] proposed a branch residual U-network (BRU-net) to segment pathological OCT retinal layer for agerelated macular degeneration diagnosis. BRU-net relies on residual connection and dilated convolutions to enhance the final OCT retinal layer segmentation.…”

mentioning

confidence: 99%

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

Cheng

et al. 2019

IEEE Trans. Med. Imaging

1,623

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

“…With dense connections, each layer is connected to all its preceding layers by feature map concatenation, allowing discernible features of faint boundaries to be retrieved across multiple scales. But, this comes at a cost of increased computation [22,23], and we empirically determined that a densely connected network at a depth of 6 levels provides a good balance between segmentation accuracy and computational efficiency [14,23]. Additionally, max pooling was better at maintaining features of interest through the network over average pooling and convolutions of stride 2 [23].…”

Section: Methodsmentioning

confidence: 97%

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

Pathological OCT Retinal Layer Segmentation Using Branch Residual U-Shape Networks

Cited by 74 publications

References 14 publications

Automated Quantification of Photoreceptor alteration in macular disease using Optical Coherence Tomography and Deep Learning

Automated Quantification of Photoreceptor alteration in macular disease using Optical Coherence Tomography and Deep Learning

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

Learning To Segment Corneal Tissue Interfaces In Oct Images

Contact Info

Product

Resources

About