ReLayNet: Retinal Layer and Fluid Segmentation of Macular Optical Coherence Tomography using Fully Convolutional Network

By Abhijit Guha Roy, Sailesh Conjeti, S. Karri, Debdoot Sheet, A. Katouzian, Christian Wachinger, Nassir Navab. Biomedical Optics Express, 2017

577 citations recorded by the source corpus.

Optical coherence tomography (OCT) is used for non-invasive diagnosis of diabetic macular edema assessing the retinal layers. In this paper, we propose a new fully convolutional deep architecture, termed ReLayNet, for end-to-end segmentation of retinal layers and fluid masses in eye OCT scans. ReLayNet uses a contracting path of convolutional blocks (encoders) to learn a hierarchy of contextual features, followed by an expansive path of convolutional blocks (decoders) for semantic segmentation. ReLayNet is trained to optimize a joint loss function comprising of weighted logistic regression and Dice overlap loss. The framework is validated on a publicly available benchmark dataset with comparisons against five state-of-the-art segmentation methods including two deep learning based approaches to substantiate its effectiveness.

Subfields: Biomedical Engineering, Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/6bbf2cfffd8858418786e4a93f53eecb509b2653

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Huan Fu
2. Alberto Garcia-Garcia
3. Victor Villena-Martinez
4. Nassir Navab
5. Sergiu Oprea
6. Shenghua Gao
7. Jose García Rodríguez
8. Christian Wachinger

In Ophthalmology

1. Huan Fu
2. Jiang Liu
3. Jun Cheng

In Radiology, Nuclear Medicine and Imaging

1. Huan Fu
2. Jiang Liu
3. Jun Cheng
4. Nassir Navab
5. Christian Wachinger
6. Danijel Skocaj

Citations in the corpus

• Recalibrating Fully Convolutional Networks With Spatial and Channel “Squeeze and Excitation” Blocks (2018, methodology): “On the third retinal OCT dataset, we use ReLayNet [14] architecture, which is similar to SD-Net [5].”
• Artificial intelligence in retina. (2018, background): “Roy et al. proposed ReLayNet, a deep learning network architecture inspired by U-Net with a modified connection between the layers for segmentation (Roy et al., 2017).”
• A survey on deep learning techniques for image and video semantic segmentation (2018, methodology): “For example, ReLayNet [118] is trained to optimize a joint loss function comprising of weighted categorical cross-entropy and Dice similarity score.”
• CE-Net: Context Encoder Network for 2D Medical Image Segmentation (2019, background): “Roy et al. [44] used a similar network for retinal layer segmentation in optical coherence tomography (OCT) images.”