TY - JOUR
T1 - Real-time automatic segmentation of optical coherence tomography volume data of the macular region
AU - Tian, Jing
AU - Varga, Boglárka
AU - Somfai, Gábor Márk
AU - Lee, Wen-Hsiang
AU - Smiddy, William E.
AU - DeBuc, Delia Cabrera
N1 - Funding Information:
This study was supported in part by a NIH Grant No. NIH R01EY020607, a NIH Center Grant No. P30-EY014801, by an unrestricted grant to the University of Miami from Research to Prevent Blindness, Inc., and by an Eotvos Scholarship of the Hungarian Scholarship Fund. The authors gratefully acknowledge Sina Farsiu, Ph.D. and Stephanie Chiu, Ph.D at Duke University for facilitating their complete study dataset and manual markings. We would also like to thank Milan Sonka, Ph.D. from the University of Iowa, for facilitating the online interactions with the IOWA Reference algorithm. Thanks to Sandra Pineda, B.S. for her assistance with the recruitment of healthy subjects and clinical coordination.
Publisher Copyright:
© 2015 Tian et al.
PY - 2015/8/10
Y1 - 2015/8/10
N2 - Optical coherence tomography (OCT) is a high speed, high resolution and non-invasive imaging modality that enables the capturing of the 3D structure of the retina. The fast and automatic analysis of 3D volume OCT data is crucial taking into account the increased amount of patient-specific 3D imaging data. In this work, we have developed an automatic algorithm, OCTRIMA 3D (OCT Retinal IMage Analysis 3D), that could segment OCT volume data in the macular region fast and accurately. The proposed method is implemented using the shortestpath based graph search, which detects the retinal boundaries by searching the shortest-path between two end nodes using Dijkstra's algorithm. Additional techniques, such as inter-frame flattening, inter-frame search region refinement, masking and biasing were introduced to exploit the spatial dependency between adjacent frames for the reduction of the processing time. Our segmentation algorithm was evaluated by comparing with themanual labelings and three state of the art graph-based segmentationmethods. The processing time for the whole OCT volume of 496×644×51 voxels (captured by Spectralis SD-OCT) was 26.15 seconds which is at least a 2-8-fold increase in speed compared to other, similar reference algorithms used in the comparisons. The average unsigned error was about 1 pixel (∼4 microns), which was also lower compared to the reference algorithms.We believe that OCTRIMA 3D is a leap forward towards achieving reliable, real-time analysis of 3D OCT retinal data.
AB - Optical coherence tomography (OCT) is a high speed, high resolution and non-invasive imaging modality that enables the capturing of the 3D structure of the retina. The fast and automatic analysis of 3D volume OCT data is crucial taking into account the increased amount of patient-specific 3D imaging data. In this work, we have developed an automatic algorithm, OCTRIMA 3D (OCT Retinal IMage Analysis 3D), that could segment OCT volume data in the macular region fast and accurately. The proposed method is implemented using the shortestpath based graph search, which detects the retinal boundaries by searching the shortest-path between two end nodes using Dijkstra's algorithm. Additional techniques, such as inter-frame flattening, inter-frame search region refinement, masking and biasing were introduced to exploit the spatial dependency between adjacent frames for the reduction of the processing time. Our segmentation algorithm was evaluated by comparing with themanual labelings and three state of the art graph-based segmentationmethods. The processing time for the whole OCT volume of 496×644×51 voxels (captured by Spectralis SD-OCT) was 26.15 seconds which is at least a 2-8-fold increase in speed compared to other, similar reference algorithms used in the comparisons. The average unsigned error was about 1 pixel (∼4 microns), which was also lower compared to the reference algorithms.We believe that OCTRIMA 3D is a leap forward towards achieving reliable, real-time analysis of 3D OCT retinal data.
UR - http://www.scopus.com/inward/record.url?scp=84942436789&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84942436789&partnerID=8YFLogxK
U2 - 10.1371/journal.pone.0133908
DO - 10.1371/journal.pone.0133908
M3 - Article
C2 - 26258430
AN - SCOPUS:84942436789
VL - 10
JO - PLoS One
JF - PLoS One
SN - 1932-6203
IS - 8
M1 - e0133908
ER -