Guangxu Li
ABSTRACT
Estimating dimensional measurements of the choroid provides diagnostic values which can be used to assess choroidal health. In this paper we describe a methodology of calculating measurements from choroid segmentations automatically generated using convolutional neural network (CNN). We use a three-dimensional (3D) U-Net architecture built from residual units to segment the choroid. A surface fitting phase is jointed to the main process to compensate segmented defects at the area of Optic Nerve Hypoplasia (ONH). Consequently, we process these segmentations to estimate the mean choroidal thickness(MCT). The model is evaluated on volumetric scans from 183 subjects, approximately half of which are thyroid eyes. In the choroidal layer segmentation experiment, the accuracy of the automatic segmentation algorithm proposed in this paper was 98.25% when comparing the manual segmentation results masked by doctors. It showed that the MCT in thyroid eyes were higher than those in normal eyes.
- [1] 2019. https://monai.io/Google Scholar
- Rupesh Agrawal, Preeti Gupta, Kara-Anne Tan, Chui Ming Gemmy Cheung, Tien-Yin Wong, and Ching-Yu Cheng. 2016. Choroidal vascularity index as a measure of vascular status of the choroid: measurements in healthy eyes from a population-based study. Scientific reports 6, 1 (2016), 1–9.Google Scholar
- Dheo AY Cahyo, Damon WK Wong, Ai Ping Yow, Seang-Mei Saw, and Leopold Schmetterer. 2020. Volumetric choroidal segmentation using sequential deep learning approach in high myopia subjects. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, 1286–1289.Google ScholarCross Ref
- Xuena Cheng, Xinjian Chen, Yuhui Ma, Weifang Zhu, Ying Fan, and Fei Shi. 2019. Choroid segmentation in OCT images based on improved U-net. In Medical Imaging 2019: Image Processing, Vol. 10949. SPIE, 521–527.Google Scholar
- Özgün Çiçek, Ahmed Abdulkadir, Soeren S Lienkamp, Thomas Brox, and Olaf Ronneberger. 2016. 3D U-Net: learning dense volumetric segmentation from sparse annotation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19. Springer, 424–432.Google ScholarDigital Library
- Chiara Del Noce, Aldo Vagge, Massimo Nicolò, and Carlo Enrico Traverso. 2020. Evaluation of choroidal thickness and choroidal vascular blood flow in patients with thyroid-associated orbitopathy (TAO) using SD-OCT and Angio-OCT. Graefe’s Archive for Clinical and Experimental Ophthalmology 258 (2020), 1103–1107.Google Scholar
- Qi Dou, Hao Chen, Yueming Jin, Lequan Yu, Jing Qin, and Pheng-Ann Heng. 2016. 3D deeply supervised network for automatic liver segmentation from CT volumes. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19. Springer, 149–157.Google ScholarDigital Library
- Wolfgang Drexler and James G Fujimoto. 2008. State-of-the-art retinal optical coherence tomography. Progress in retinal and eye research 27, 1 (2008), 45–88.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.Google ScholarCross Ref
- Jason Kugelman, David Alonso-Caneiro, Scott A Read, Jared Hamwood, Stephen J Vincent, Fred K Chen, and Michael J Collins. 2019. Automatic choroidal segmentation in OCT images using supervised deep learning methods. Scientific reports 9, 1 (2019), 1–13.Google Scholar
- Seungyong Lee, George Wolberg, and Sung Yong Shin. 1997. Scattered data interpolation with multilevel B-splines. IEEE transactions on visualization and computer graphics 3, 3 (1997), 228–244.Google ScholarDigital Library
- F. Milletari, N. Navab, and S. Ahmadi. 2016. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. In 2016 Fourth International Conference on 3D Vision (3DV). IEEE Computer Society, Los Alamitos, CA, USA, 565–571. https://doi.org/10.1109/3DV.2016.79Google ScholarCross Ref
- Nihar Ranjan Panda and Ajit Kumar Sahoo. 2022. A Detailed Systematic Review on Retinal Image Segmentation Methods. Journal of Digital Imaging 35, 5 (2022), 1250–1270.Google ScholarCross Ref
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 234–241.Google Scholar
- N. Shigeta, M. Kamata, and M. Kikuchi. 2019. Effectiveness of Pseudo 3D Feature Learning for Spinal Segmentation by CNN with U-Net Architecture. Journal of Image and Graphics3 (2019).Google Scholar
- RKK Wang. 2002. Signal degradation by coherence tomography multiple scattering in optical of dense tissue: a Monte Carlo study towards optical clearing of biotissues. Physics in Medicine and Biology 47, 13 (2002), 2281–2299.Google ScholarCross Ref
- Hao Zhou, Zhongdi Chu, Qinqin Zhang, Yining Dai, Giovanni Gregori, Philip J Rosenfeld, and Ruikang K Wang. 2018. Attenuation correction assisted automatic segmentation for assessing choroidal thickness and vasculature with swept-source OCT. Biomedical optics express 9, 12 (2018), 6067–6080.Google Scholar
Index Terms
- Volumetric choroidal segmentation using 3D residual U-Net
Recommendations
Automatic measurement of choroidal thickness and vasculature in optical coherence tomography images of eyes with retinitis pigmentosa
AbstractRetinitis pigmentosa (RP) is a group of genetic disorders, characterized by degeneration of photoreceptor cells which is the main cause of choroidal thinning. It is one of the leading causes of blindness worldwide. Thus, an investigation of ...
Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network
Glaucoma is the second leading cause of blindness all over the world, with approximately 60 million cases reported worldwide in 2010. If undiagnosed in time, glaucoma causes irreversible damage to the optic nerve leading to blindness. The optic nerve ...
Accurate Myocardial Pathology Segmentation with Residual U-Net
Myocardial Pathology Segmentation Combining Multi-Sequence Cardiac Magnetic Resonance ImagesAbstractAccurate assessment of myocardial viability in multi-sequence cardiac magnetic resonance (CMR) images is desired to automate disease diagnosis. To classify myocardial pathology automatic segmentation methods are necessary. In this paper we propose ...
Comments