Automatic Identification of Pathology-Distorted Retinal Layer Boundaries Using SD-OCT Imaging

• Published in: IEEE transactions on biomedical engineering Vol. 64; no. 7; pp. 1638 - 1649
• Main Authors: Hussain, Md Akter, Bhuiyan, Alauddin, Turpin, Andrew, Luu, Chi D., Smith, R. Theodore, Guymer, Robyn H., Kotagiri, Ramamohanrao
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Approximation; Atrophy; Australia; Biomarkers; Biomedical optical imaging; Boundaries; Diseases; Humans; Identification; Image Interpretation, Computer-Assisted - methods; Image segmentation; layer segmentation; Machine Learning; Methods; Optical Coherence Tomography; Pathology; Pattern Recognition, Automated - methods; Pixels; Reproducibility of Results; Retina; Retina - pathology; Retinal Diseases - diagnostic imaging; Retinal Diseases - pathology; Sensitivity and Specificity; shortest path problem; Shortest-path problems; spectral domain optical coherence tomography (SD-OCT); Standard deviation; State of the art; Tomography, Optical Coherence - methods; Weight
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2016.2619120

Objective: We propose an effective automatic method for identification of four retinal layer boundaries from the spectral domain optical coherence tomography images in the presence and absence of pathologies and morphological changes due to disease. Methods: The approach first finds an approximate location of three reference layers and then uses these to bound the search space for the actual layers, which is achieved by modeling the problem as a graph and applying Dijkstra's shortest path algorithm. The edge weight between nodes is determined using pixel distance, slope similarity to a reference, and nonassociativity of the layers, which is designed to overcome the distorting effects that pathology can play in the boundary determination. Results: The accuracy of our method was evaluated on three different datasets. It outperforms the current five state-of-the-art methods. On average, the mean and standard deviation of the root-mean-square error in the form of mean ± standard deviation in pixels for our method is 1.57 ± 0.69, which is lower than compared to the existing top five methods of 16.17 ± 22.64, 6.66 ± 9.11, 5.70 ± 10.54, 3.69 ± 2.04, and 2.29 ± 1.54. Conclusion: Our method is highly accurate, robust, reliable, and consistent. This identification can enable to quantify the biomarkers of the retina in largescale study for assessing, monitoring disease progression, as well as early detection of retinal diseases. Significance: Identification of these boundaries can help to determine the loss of neuroretinal cells or layers and the presence of retinal pathology, which can be used as features for the automatic determination of the stages of retinal diseases.