High-Accuracy Retinal Layer Segmentation for Optical Coherence Tomography Using Tracking Kernels Based on Gaussian Mixture Model

We introduce a method based on Gaussian mixture model (GMM) clustering and level-set to automatically detect intraretina fluid on diabetic retinopathy (DR) from spectral domain optical coherence tomography (SD-OCT) images in this paper. First, each B-scan is segmented using GMM clustering. The original clustering results are refined using location and thickness information. Then, the spatial information among every consecutive five B-scans is used to search potential fluid. Finally, the improved level-set method is used to obtain the accurate boundaries. The high sensitivity and accuracy demonstrated here show its potential for detection of fluid.

Download Full-text

An approach to automated retinal layer segmentation in SDOCT images

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i2.25.12371 ◽

2018 ◽

Vol 7 (2.25) ◽

pp. 56

Author(s):

Mohandass G ◽

Hari Krishnan G ◽

Hemalatha R J

Keyword(s):

Optical Coherence Tomography ◽

Imaging Technique ◽

Retinal Layer ◽

Optical Coherence ◽

Seed Point ◽

Deformable Contour ◽

Gradient Based ◽

Oct Imaging ◽

Layer Segmentation ◽

Region Growth

The optical coherence tomography (OCT) imaging technique is a precise and well-known approach to the diagnosis of retinal layers. The pathological changes in the retina challenge the accuracy of computational segmentation approaches in the evaluation and identification of defects in the boundary layer. The layer segmentations and boundary detections are distorted by noise in the computation. In this work, we propose a fully automated segmentation algorithm using a denoising technique called the Boisterous Obscure Ratio (BOR) for human and mammal retina. First, the BOR is derived using noise detection, i.e., from the Robust Outlyingness Ratio (ROR). It is then applied to edge and layer detection using a gradient-based deformable contour model. Second, the image is vectorised. In this method, a cluster and column intensity grid is applied to identify and determine the unsegmented layers. Using the layer intensity and a region growth seed point algorithm, segmentation of the prominent layers is achieved. The automatic BOR method is an image segmentation process that determines the eight layers in retinal spectral domain optical coherence tomography images. The highlight of the BOR method is that the results produced are accurate, highly substantial, and effective, although time consuming.

Download Full-text

Loosely coupled level sets for retinal layer segmentation in optical coherence tomography

2013 IEEE 10th International Symposium on Biomedical Imaging ◽

10.1109/isbi.2013.6556648 ◽

2013 ◽

Cited By ~ 7

Author(s):

Jelena Novosel ◽

Koenraad A. Vermeer ◽

Gijs Thepass ◽

Hans G. Lemij ◽

Lucas J. van Vliet

Keyword(s):

Optical Coherence Tomography ◽

Level Sets ◽

Retinal Layer ◽

Optical Coherence ◽

Loosely Coupled ◽

Layer Segmentation

Download Full-text

Loosely coupled level sets for simultaneous 3D retinal layer segmentation in optical coherence tomography

Medical Image Analysis ◽

10.1016/j.media.2015.08.008 ◽

2015 ◽

Vol 26 (1) ◽

pp. 146-158 ◽

Cited By ~ 29

Author(s):

Jelena Novosel ◽

Gijs Thepass ◽

Hans G. Lemij ◽

Johannes F. de Boer ◽

Koenraad A. Vermeer ◽

...

Keyword(s):

Optical Coherence Tomography ◽

Level Sets ◽

Retinal Layer ◽

Optical Coherence ◽

Loosely Coupled ◽

Layer Segmentation

Download Full-text

A Method for Aero-Engine Gas Path Anomaly Detection Based on Markov Transition Field and Multi-LSTM

Aerospace ◽

10.3390/aerospace8120374 ◽

2021 ◽

Vol 8 (12) ◽

pp. 374

Author(s):

Langfu Cui ◽

Chaoqi Zhang ◽

Qingzhen Zhang ◽

Junle Wang ◽

Yixuan Wang ◽

...

Keyword(s):

Anomaly Detection ◽

Gaussian Mixture Model ◽

Mixture Model ◽

Gaussian Mixture ◽

High Accuracy ◽

High Dimensional ◽

True Value ◽

Markov Transition ◽

Aero Engine ◽

Transition Field

There are some problems such as uncertain thresholds, high dimension of monitoring parameters and unclear parameter relationships in the anomaly detection of aero-engine gas path. These problems make it difficult for the high accuracy of anomaly detection. In order to improve the accuracy of aero-engine gas path anomaly detection, a method based on Markov Transition Field and LSTM is proposed in this paper. The correlation among high-dimensional QAR data is obtained based on Markov Transition Field and hierarchical clustering. According to the correlation analysis of high-dimensional QAR data, a multi-input and multi-output LSTM network is constructed to realize one-step rolling prediction. A Gaussian mixture model of the residuals between predicted value and true value is constructed. The three-sigma rule is applied to detect outliers based on the Gaussian mixture model of the residuals. The experimental results show that the proposed method has high accuracy for aero-engine gas path anomaly detection.

Download Full-text