Unsupervised Segmentation of Choroidal Neovascularization for Optical Coherence Tomography Angiography by Grid Tissue-Like Membrane Systems

Accurate segmentation of choroidal neovascularization (CNV) patterns is vital for precise lesion size quantification in age-related macular degeneration. In this paper, we develop a method for unsupervised and parallel segmentation of CNV in optical coherence tomography based on a grid tissue-like membrane (GTM) system. A GTM system incorporates a modified Clustering In QUEst (CLIQUE) algorithm into tissue-like membrane systems. Exploiting CLIQUE’s aptitude for unsupervised clustering, GTM systems can detect CNV of different shapes, positions and density without the need of a training stage. The average dice ratio is 0.84±0.04, outperforms both baseline and the state-of-the-art methods. Besides, being a parallel computational paradigm, GTM systems can handle all scans under analysis simultaneously and therefore they are less time consuming, completing CNV detection on 48 scans in 0.56 seconds.

[1]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[2]  Gheorghe Paun,et al.  Computing with Membranes , 2000, J. Comput. Syst. Sci..

[3]  Alfonso Rodríguez-Patón,et al.  Tissue P systems , 2003, Theor. Comput. Sci..

[4]  Dimitrios Gunopulos,et al.  Automatic Subspace Clustering of High Dimensional Data , 2005, Data Mining and Knowledge Discovery.

[5]  Joan W. Miller,et al.  Age-related macular degeneration. , 2008, The New England journal of medicine.

[6]  Pedro Real Jurado,et al.  Segmentation in 2D and 3D Image Using Tissue-Like P System , 2009, CIARP.

[7]  Xiyu Liu,et al.  A CLIQUE algorithm using DNA computing techniques based on closed-circle DNA sequences , 2011, Biosyst..

[8]  Il Hong Suh,et al.  Dynamic multi-objective optimization based on membrane computing for control of time-varying unstable plants , 2011, Inf. Sci..

[9]  Martin F. Kraus,et al.  Split-spectrum amplitude-decorrelation angiography with optical coherence tomography , 2012, Optics express.

[10]  James G. Fujimoto,et al.  Motion correction in optical coherence tomography volumes on a per A-scan basis using orthogonal scan patterns , 2012, Biomedical optics express.

[11]  Qi Meng,et al.  A hybrid approach based on differential evolution and tissue membrane systems for solving constrained manufacturing parameter optimization problems , 2013, Appl. Soft Comput..

[12]  Xiyu Liu,et al.  Lattice based communication P systems with applications in cluster analysis , 2013, Soft Computing.

[13]  Martin F. Kraus,et al.  Quantitative optical coherence tomography angiography of choroidal neovascularization in age-related macular degeneration. , 2014, Ophthalmology.

[14]  Yanjun Liu,et al.  Computational power of tissue P systems for generating control languages , 2014, Inf. Sci..

[15]  Simon S. Gao,et al.  Automated choroidal neovascularization detection algorithm for optical coherence tomography angiography. , 2015, Biomedical optics express.

[16]  S. Sadda,et al.  Methodological remarks concerning the recent meta-analysis on the effect of intravitral bevacizumab in central serous chorioretinopathy , 2015, Eye.

[17]  R. Spaide.  Optical Coherence Tomography Angiography Signs of Vascular Abnormalization With Antiangiogenic Therapy for Choroidal Neovascularization. , 2015, American journal of ophthalmology.

[18]  Xiyu Liu,et al.  Rhombic Grid Based Clustering Algorithm with Spiking Neural P Systems , 2016 .

[19]  Xiyu Liu,et al.  A Cluster Splitting Technique by Hopfield Networks and P Systems on Simplices , 2017, Neural Processing Letters.

[20]  Ruikang K. Wang,et al.  Automated Quantitation of Choroidal Neovascularization: A Comparison Study Between Spectral-Domain and Swept-Source OCT Angiograms , 2017, Investigative ophthalmology & visual science.

[21]  Hong Peng,et al.  Multiobjective fuzzy clustering approach based on tissue-like membrane systems , 2017, Knowl. Based Syst..

[22]  Xiyu Liu,et al.  Automatic quantification of choroidal neovascularization lesion area on OCT angiography based on density cell-like P systems with active membranes. , 2018, Biomedical optics express.

[23]  A. V. Barros,et al.  Choroidal neovascularization due to choroidal rupture after blunt ocular trauma – OCT Angiography better than fluorescein angiography for diagnosis and treatment follow-up – A Case Report , 2018 .

[24]  Chunming Wu,et al.  PAME: Evolutionary membrane computing for virtual network embedding , 2018, J. Parallel Distributed Comput..

[25]  Peng Shi,et al.  Fault Diagnosis of Power Systems Using Intuitionistic Fuzzy Spiking Neural P Systems , 2018, IEEE Transactions on Smart Grid.

[26]  K. G. Subramanian,et al.  An Overview of 2D Picture Array Generating Models Based on Membrane Computing , 2018, Reversibility and Universality.

[27]  Hong Peng,et al.  Membrane computing and image processing: a short survey , 2019, J. Membr. Comput..

[28]  Xiyu Liu,et al.  Deep membrane systems for multitask segmentation in diabetic retinopathy , 2019, Knowl. Based Syst..

[29]  C. Rivolta,et al.  Mineralocorticoid receptor antagonism limits experimental choroidal neovascularization and structural changes associated with neovascular age-related macular degeneration , 2019, Nature Communications.

[30]  Agustín Riscos-Núñez,et al.  A path to computational efficiency through membrane computing , 2019, Theor. Comput. Sci..

[31]  Marcelino Campos,et al.  Simulating Multilevel Dynamics of Antimicrobial Resistance in a Membrane Computing Model , 2018, mBio.

[32]  Min Xie,et al.  A Cross-Entropy-Based Hybrid Membrane Computing Method for Power System Unit Commitment Problems , 2019 .