Simultaneous Segmentation of Retinal OCT Images Using Level Set

Medical images play a vital role in clinical diagnosis and treatments of various diseases. In the field of ophthalmology, Optical coherence tomography (OCT) has become an integral part of the non-invasive advanced eye examination by providing images of the retina in high resolution. Reliable identification of the retinal layers is necessary for the extraction of clinically useful information used for tracking the progress of medication and diagnosing various ocular diseases because changes to retinal layers highly correlate with the manifestation of eye diseases. Owing to the complexity of retinal structures and the cumbersomeness of manual segmentation, many computer-based methods are proposed to aid in extracting useful layer information. Additionally, image artefacts and inhomogeneity of pathological structures of the retina pose challenges by significantly degrading the performance of these computational methods. To handle some of these challenges, this paper presents a fully automated method for segmenting retinal layers in OCT images using a level set method. The method starts by establishing a specific Region of interest (ROI), which aids in handling over- and under-segmentation of the target layers by allowing only the layer and image features to influence the curve evolution. An appropriate level set initiation is devised by refining the edges from the image gradient. Then the prior understanding of the OCT image is utilised in constraining the evolution process to segment seven layers of the retina simultaneously. Promising experimental results have been achieved on 225 OCT images, which show the method converges close to the actual layer boundaries compared to the ground truth images.

[1]  Zidong Wang,et al.  Automated Layer Segmentation of 3D Macular Images Using Hybrid Methods , 2015, ICIG.

[2]  Yue Zhao,et al.  3D Automatic Segmentation Method for Retinal Optical Coherence Tomography Volume Data Using Boundary Surface Enhancement , 2015, ArXiv.

[3]  Jelena Novosel,et al.  Loosely coupled level sets for retinal layer segmentation in optical coherence tomography , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[4]  Xiaohui Liu,et al.  Retinal OCT Image Segmentation Using Fuzzy Histogram Hyperbolization and Continuous Max-Flow , 2017, 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS).

[5]  Luc Vincent,et al.  Morphological Area Openings and Closings for Grey-scale Images , 1994 .

[6]  Peter A. Calabresi,et al.  Multi-layer fast level set segmentation for macular OCT , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[7]  J. Aster,et al.  The Role of Notch Receptors in Transcriptional Regulation , 2015, Journal of cellular physiology.

[8]  Xiaohui Liu,et al.  Level Set Segmentation of Retinal OCT Images , 2019, BIOIMAGING.

[9]  J. Duker,et al.  Optical coherence tomography – current and future applications , 2013, Current Opinion in Ophthalmology.

[10]  Edsger W. Dijkstra,et al.  A note on two problems in connexion with graphs , 1959, Numerische Mathematik.

[11]  Kim L. Boyer,et al.  Retinal thickness measurements from optical coherence tomography using a Markov boundary model , 2001, IEEE Transactions on Medical Imaging.

[12]  Xiaohui Liu,et al.  Min-Cut Segmentation of Retinal OCT Images , 2018, BIOSTEC.

[13]  W. Clem Karl,et al.  A fast level set method without solving PDEs [image segmentation applications] , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[14]  Joseph A. Izatt,et al.  Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation , 2010, Optics express.

[15]  Kim L. Boyer,et al.  Automatic recovery of the optic nervehead geometry in optical coherence tomography , 2006, IEEE Transactions on Medical Imaging.

[16]  Xiaohui Liu,et al.  Graph-Cut Segmentation of Retinal Layers from OCT Images , 2018, BIOIMAGING.

[17]  Yan Lindsay Sun,et al.  Automated layer segmentation of optical coherence tomography images , 2011, 2011 4th International Conference on Biomedical Engineering and Informatics (BMEI).

[18]  J. Fujimoto,et al.  Optical Coherence Tomography , 1991 .

[19]  Jerry L Prince,et al.  Retinal layer segmentation of macular OCT images using boundary classification , 2013, Biomedical optics express.

[20]  Allan Tucker,et al.  Retinal OCT Segmentation Using Fuzzy Region Competition and Level Set Methods , 2019, 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS).

[21]  Li Bai,et al.  Automated segmentation of retinal layers from optical coherence tomography images using geodesic distance , 2016, Pattern Recognit..

[22]  B. Aisbett,et al.  Sleep Restriction during Simulated Wildfire Suppression: Effect on Physical Task Performance , 2015, PloS one.

[23]  Anthony J. Yezzi,et al.  Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation, and magnification , 2001, IEEE Trans. Image Process..

[24]  Kim L. Boyer,et al.  The active geometric shape model: A new robust deformable shape model and its applications , 2012, Comput. Vis. Image Underst..

[25]  Gábor Márk Somfai,et al.  Real-Time Automatic Segmentation of Optical Coherence Tomography Volume Data of the Macular Region , 2015, PloS one.

[26]  Ghassan Hamarneh,et al.  Segmentation of Intra-Retinal Layers From Optical Coherence Tomography Images Using an Active Contour Approach , 2011, IEEE Transactions on Medical Imaging.

[27]  Mahmoud Al-Ayyoub,et al.  Accelerating 3D medical volume segmentation using GPUs , 2016, Multimedia Tools and Applications.

[28]  Shijian Lu,et al.  Automated layer segmentation of optical coherence tomography images , 2010, 2010 5th IEEE Conference on Industrial Electronics and Applications.

[29]  Mona Kathryn Garvin,et al.  Automated 3-D segmentation and analysis of retinal optical coherence tomography images , 2008 .