Morphological characteristics of retinal vessels in eyes with high myopia: Ultra-wide field images analyzed by artificial intelligence using a transfer learning system

被引:4
|
作者
Mao, Jianbo [1 ,2 ]
Deng, Xinyi [1 ,2 ]
Ye, Yu [3 ]
Liu, Hui [3 ]
Fang, Yuyan [2 ]
Zhang, Zhengxi [2 ]
Chen, Nuo [2 ]
Sun, Mingzhai [3 ]
Shen, Lijun [1 ,2 ]
机构
[1] Hangzhou Med Coll, Zhejiang Prov Peoples Hosp, Affiliated Peoples Hosp, Ctr Rehabil Med,Dept Ophthalmol, Hangzhou, Zhejiang, Peoples R China
[2] Wenzhou Med Univ, Eye Hosp, Wenzhou, Zhejiang, Peoples R China
[3] Univ Sci & Technol China, Dept Precis Machinery & Instrumentat, Hefei, Peoples R China
关键词
high myopia; ultra-wide field imaging; deep learning; vascular morphology; choroidal neovascularization; RETINOPATHY; NETWORK; ANGLE;
D O I
10.3389/fmed.2022.956179
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
PurposeThe purpose of this study is to investigate the retinal vascular morphological characteristics in high myopia patients of different severity. Methods317 eyes of high myopia patients and 104 eyes of healthy control subjects were included in this study. The severity of high myopia patients is classified into C0-C4 according to the Meta Analysis of the Pathologic Myopia (META-PM) classification and their vascular morphological characteristics in ultra-wide field imaging were analyzed using transfer learning methods and RU-net. Correlation with axial length (AL), best corrected visual acuity (BCVA) and age was analyzed. In addition, the vascular morphological characteristics of myopic choroidal neovascularization (mCNV) patients and their matched high myopia patients were compared. ResultsThe RU-net and transfer learning system of blood vessel segmentation had an accuracy of 98.24%, a sensitivity of 71.42%, a specificity of 99.37%, a precision of 73.68% and a F1 score of 72.29. Compared with healthy control group, high myopia group had smaller vessel angle (31.12 +/- 2.27 vs. 32.33 +/- 2.14), smaller fractal dimension (Df) (1.383 +/- 0.060 vs. 1.424 +/- 0.038), smaller vessel density (2.57 +/- 0.96 vs. 3.92 +/- 0.93) and fewer vascular branches (201.87 +/- 75.92 vs. 271.31 +/- 67.37), all P < 0.001. With the increase of myopia maculopathy severity, vessel angle, Df, vessel density and vascular branches significantly decreased (all P < 0.001). There were significant correlations of these characteristics with AL, BCVA and age. Patients with mCNV tended to have larger vessel density (P < 0.001) and more vascular branches (P = 0.045). ConclusionThe RU-net and transfer learning technology used in this study has an accuracy of 98.24%, thus has good performance in quantitative analysis of vascular morphological characteristics in Ultra-wide field images. Along with the increase of myopic maculopathy severity and the elongation of eyeball, vessel angle, Df, vessel density and vascular branches decreased. Myopic CNV patients have larger vessel density and more vascular branches.
引用
收藏
页数:9
相关论文
共 15 条
  • [1] Retinal vascular morphological characteristics in diabetic retinopathy: an artificial intelligence study using a transfer learning system to analyze ultra-wide field images
    Deng, Xin-Yi
    Liu, Hui
    Zhang, Zheng-Xi
    Li, Han-Xiao
    Wang, Jun
    Chen, Yi-Qi
    Mao, Jian-Bo
    Sun, Ming-Zhai
    Shen, Li -Jun
    INTERNATIONAL JOURNAL OF OPHTHALMOLOGY, 2024, 17 (06) : 1001 - 1006
  • [2] Comparison of Heidelberg Composite Images with Optos Ultra-Wide Field Images by Overlay using Artificial Intelligence vs Mathematical Warping
    Kalaw, Fritz Gerald Paguiligan
    Cavichini, Melina
    Zhang, Junkang
    Bartsch, Dirk-Uwe G.
    Alex, Varsha
    Galang, Carlo B.
    Heinke, Anna
    Warter, Alexandra
    Nguyen, Truong Q.
    An, Cheolhong
    Freeman, William R.
    INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2022, 63 (07)
  • [3] Deep Learning for prediction of late recurrence of retinal detachment using preoperative and postoperative ultra-wide field imaging
    Catania, Fiammetta
    Chapron, Thibaut
    Crincoli, Emanuele
    Miere, Alexandra
    Abdelmassih, Youssef
    Beaumont, William
    Chehaibou, Ismael
    Metge, Florence
    Bruneau, Sebastien
    Bonnin, Sophie
    Souied, Eric H.
    Caputo, Georges
    ACTA OPHTHALMOLOGICA, 2024, 102 (07) : e984 - e993
  • [4] Retinal Disease Diagnosis Using Deep Learning on Ultra-Wide-Field Fundus Images
    Nguyen, Toan Duc
    Le, Duc-Tai
    Bum, Junghyun
    Kim, Seongho
    Song, Su Jeong
    Choo, Hyunseung
    DIAGNOSTICS, 2024, 14 (01)
  • [5] Artificial Intelligence Using Deep Learning in Classifying Side of the Eyes and Width of Field for Retinal Fundus Photographs
    Bellemo, Valentina
    Yip, Michelle Yuen Ting
    Xie, Yuchen
    Lee, Xin Qi
    Quang Duc Nguyen
    Hamzah, Haslina
    Ho, Jinyi
    Lim, Gilbert
    Xu, Dejiang
    Lee, Mong Li
    Hsu, Wynne
    Garcia-Franco, Renata
    Menon, Geeta
    Lamoureux, Ecosse
    Cheng, Ching-Yu
    Wong, Tien Yin
    Ting, Daniel Shu Wei
    COMPUTER VISION - ACCV 2018 WORKSHOPS, 2019, 11367 : 309 - 315
  • [6] Development of a deep-learning system for detection of lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field fundus images: a pilot study
    Chenxi Zhang
    Feng He
    Bing Li
    Hao Wang
    Xixi He
    Xirong Li
    Weihong Yu
    Youxin Chen
    Graefe's Archive for Clinical and Experimental Ophthalmology, 2021, 259 : 2225 - 2234
  • [7] Development of a deep-learning system for detection of lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field fundus images: a pilot study
    Zhang, Chenxi
    He, Feng
    Li, Bing
    Wang, Hao
    He, Xixi
    Li, Xirong
    Yu, Weihong
    Chen, Youxin
    GRAEFES ARCHIVE FOR CLINICAL AND EXPERIMENTAL OPHTHALMOLOGY, 2021, 259 (08) : 2225 - 2234
  • [8] Deep-Learning-Based Hemoglobin Concentration Prediction and Anemia Screening Using Ultra-Wide Field Fundus Images
    Zhao, Xinyu
    Meng, Lihui
    Su, Hao
    Lv, Bin
    Lv, Chuanfeng
    Xie, Guotong
    Chen, Youxin
    FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY, 2022, 10
  • [9] Innovative utilization of ultra-wide field fundus images and deep learning algorithms for screening high-risk posterior polar cataract
    Mai, Elsa L. C.
    Chen, Bing-Hong
    Su, Tai-Yuan
    JOURNAL OF CATARACT AND REFRACTIVE SURGERY, 2024, 50 (06): : 618 - 623
  • [10] Detection of Referable and Vision-threatening Diabetic Retinopathy Using Deep Learning on Ultra-wide Field Scanning Laser Ophthalmoscope Images
    Tang, Fangyao
    Luenam, Phoomraphee
    Quadeer, Ahmed Abdul
    Ran, Anran
    Sivaprasad, Sobha
    Sen, Piyali
    Raman, Rajiv
    Anantharaman, Giridhar
    Gopalakrishnan, Mahesh
    Haridas, Swathy
    Mckay, Matthew R.
    Cheung, Carol Yim-lui
    INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2020, 61 (07)