Automatic quantification of superficial foveal avascular zone in optical coherence tomography angiography implemented with deep learning
Tóm tắt
An accurate segmentation and quantification of the superficial foveal avascular zone (sFAZ) is important to facilitate the diagnosis and treatment of many retinal diseases, such as diabetic retinopathy and retinal vein occlusion. We proposed a method based on deep learning for the automatic segmentation and quantification of the sFAZ in optical coherence tomography angiography (OCTA) images with robustness to brightness and contrast (B/C) variations. A dataset of 405 OCTA images from 45 participants was acquired with Zeiss Cirrus HD-OCT 5000 and the ground truth (GT) was manually segmented subsequently. A deep learning network with an encoder–decoder architecture was created to classify each pixel into an sFAZ or non-sFAZ class. Subsequently, we applied largest-connected-region extraction and hole-filling to fine-tune the automatic segmentation results. A maximum mean dice similarity coefficient (DSC) of 0.976 ± 0.011 was obtained when the automatic segmentation results were compared against the GT. The correlation coefficient between the area calculated from the automatic segmentation results and that calculated from the GT was 0.997. In all nine parameter groups with various brightness/contrast, all the DSCs of the proposed method were higher than 0.96. The proposed method achieved better performance in the sFAZ segmentation and quantification compared to two previously reported methods. In conclusion, we proposed and successfully verified an automatic sFAZ segmentation and quantification method based on deep learning with robustness to B/C variations. For clinical applications, this is an important progress in creating an automated segmentation and quantification applicable to clinical analysis.
Tài liệu tham khảo
Spaide RF, Fujimoto JG, Waheed NK, Sadda SR, Staurenghi G (2018) Optical coherence tomography angiography. Prog Retin Eye Res 64:1–55. https://doi.org/10.1016/j.preteyeres.2017.11.003
Ishibazawa A, Nagaoka T, Takahashi A, Omae T, Tani T, Sogawa K et al (2015) Optical coherence tomography angiography in diabetic retinopathy: a prospective pilot study. Am J Ophthalmol 160(1):35–44.e1. https://doi.org/10.1016/j.ajo.2015.04.021
Coscas F, Glacet-Bernard A, Miere A, Caillaux V, Uzzan J, Lupidi M et al (2016) Optical coherence angiography in retinal vein occlusion: evaluation of superficial and deep capillary plexuses. Am J Ophthalmol 161:160–171.e2. https://doi.org/10.1016/j.ajo.2015.10.008
Choi W, Moult EM, Waheed NK, Adhi M, Lee B, Lu CD et al (2015) Ultrahigh-speed, swept-source optical coherence tomography angiography in nonexudative age-related macular degeneration with geographic atrophy. Ophthalmology 122(12):2532–2544. https://doi.org/10.1016/j.ophtha.2015.08.029
Spaide RF, Klancnik JM Jr, Cooney MJ (2015) Retinal vascular layers in macular telangiectasia type 2 imaged by optical coherence tomographic angiography. JAMA Ophthalmol 133(1):66–73. https://doi.org/10.1001/jamaophthalmol.2014.3950
Hogan MJ, Alvarado JA, Weddell JE (1971) Histology of the human eye: an atlas and textbook. W.B. Saunders, Philadelphia
Takase N, Nozaki M, Kato A, Ozeki H, Yoshida M, Ogura Y (2015) Enlargement of foveal avascular zone in diabetic eyes evaluated by en face optical coherence tomography angiography. Retina 35(11):2377–2383. https://doi.org/10.1097/IAE.0000000000000849
Kang JW, Yoo R, Jo YH, Kim HC (2017) Correlation of microvascular structures on optical coherence tomography angiography with visual acuity in retinal vein occlusion. Retina 37(9):1700–1709. https://doi.org/10.1097/IAE.0000000000001403
Casselholmde Salles M, Kvanta A, Amrén U, Epstein D (2016) Optical coherence tomography angiography in central retinal vein occlusion: correlation between the foveal avascular zone and visual acuity. Invest Ophthalmol Vis Sci 57(9):OCT242–OCT246. https://doi.org/10.1167/iovs.15-18819
Samara WA, Shahlaee A, Adam MK, Khan MA, Chiang A, Maguire JI et al (2017) Quantification of diabetic macular ischemia using optical coherence tomography angiography and its relationship with visual acuity. Ophthalmology 124(2):235–244. https://doi.org/10.1016/j.ophtha.2016.10.008
Mehta N, Liu KK, Alibhai AY, Gendelman I, Braun PX, Ishibazawa A et al (2019) Impact of binarization thresholding and brightness/contrast adjustment methodology on optical coherence tomography angiography image quantification. Am J Ophthalmol 205:54–65. https://doi.org/10.1016/j.ajo.2019.03.008
Lu YS, Simonett JM, Wang J, Zhang M, Hwang T, Hagag AM et al (2018) Evaluation of automatically quantified foveal avascular zone metrics for diagnosis of diabetic retinopathy using optical coherence tomography angiography. Invest Ophthalmol Vis Sci 59(6):2212–2221. https://doi.org/10.1167/iovs.17-23498
Díaz M, Novo J, Cutrín P, Gómez-Ulla F, Penedo MG, Ortega M (2019) Automatic segmentation of the foveal avascular zone in ophthalmological OCT-A images. PLoS One 14(2):e0212364. https://doi.org/10.1371/journal.pone.0212364
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Lu W, Tong Y, Yu Y, Xing YQ, Chen CZ, Shen Y (2018) Deep learning-based automated classification of multi-categorical abnormalities from optical coherence tomography images. Transl Vis Sci Technol 7(6):41. https://doi.org/10.1167/tvst.7.6.41
Ji ZX, Chen Q, Niu SJ, Leng T, Rubin DL (2018) Beyond retinal layers: a deep voting model for automated geographic atrophy segmentation in SD-OCT images. Transl Vis Sci Technol 7(1):1. https://doi.org/10.1167/tvst.7.1.1
Lore KG, Akintayo A, Sarkar S (2017) LLNet: a deep autoencoder approach to natural low-light image enhancement. Pattern Recogn 61:650–662. https://doi.org/10.1016/j.patcog.2016.06.008
Zhao C, Han JG, Jia Y, Fan LH, Gou F (2018) Versatile framework for medical image processing and analysis with application to automatic bone age assessment. J Electr Comput Eng 2018:2187247. https://doi.org/10.1155/2018/2187247
Dosovitskiy A, Springenberg JT, Riedmiller MA, Brox T (2014) Discriminative unsupervised feature learning with convolutional neural networks. In: Abstracts of the 27th international conference on neural information processing systems. MIT Press, Montreal 8-13 December 2014
Shalabi LA, Shaaban Z, Kasasbeh B (2006) Data mining: a preprocessing engine. J Comput Sci 2(9):735–739. https://doi.org/10.3844/jcssp.2006.735.739
Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640–651. https://doi.org/10.1109/TPAMI.2016.2572683
Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Abstracts of the 18th international conference on medical image computing and computer-assisted intervention. Springer, Munich, 5-9 October 2015. https://doi.org/10.1007/978-3-319-24574-4_28
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Abstracts of the 32nd international conference on machine learning. PMLR, Lille 5 December 2015
Hu J, Shen L, Sun G (2018) In: Calvin L (ed) Squeeze-and-excitation networks. Paper presented at the IEEE conference on computer vision and pattern recognition. Rampton Salt Palace Convention Center, Salt Lake City 18-22 June, 2018
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv, p 1412.6980
Chollet, F (2015). Keras. https://github.com/fchollet/keras. Accessed 27 Aug 2019
Taylor R (1990) Interpretation of the correlation coefficient: a basic review. J Diagn Med Sonography 6(1):35–39. https://doi.org/10.1177/875647939000600106
Cheng XN, Chen XJ, Ma YH, Zhu WF, Fan Y, Shi F (2019) Choroid segmentation in OCT images based on improved U-net. In: Abstracts of SPIE 10949, medical imaging 2019: image processing. SPIE, San Diego, 15 March 2019. https://doi.org/10.1117/12.2509407
Gharaibeh Y, Dong PF, Prabhu D, Kolluru C, Lee J, Zimin V et al (2019) Deep learning segmentation of coronary calcified plaque from intravascular optical coherence tomography (IVOCT) images with application to finite element modeling of stent deployment. In: Abstracts of SPIE 10951, medical imaging 2019: image-guided procedures, robotic interventions, and modeling. SPIE, San Diego, 8 March 2019. https://doi.org/10.1117/12.2515256
Shahlaee A, Pefkianaki M, Hsu J, Ho AC (2016) Measurement of foveal avascular zone dimensions and its reliability in healthy eyes using optical coherence tomography angiography. Am J Ophthalmol 161:50–55.e1. https://doi.org/10.1016/j.ajo.2015.09.026