Intelligent diagnostic model for pterygium by combining attention mechanism and MobileNetV2
Author:
Corresponding Author:

Wen-Qun Xi and Zhe Zhang. Shenzhen Eye Institute, Shenzhen Eye Hospital, Jinan University, Shenzhen 518040, Guangdong Province, China. wtongxxiwq125@126.com; hypotato@126.com

Fund Project:

Supported by the National Natural Science Foundation of China (No.61906066); Scientific Research Fund of Zhejiang Provincial Education Department (No.Y202147191); Huzhou University Graduate Research Innovation Project (No.2020KYCX21); Sanming Project of Medicine in Shenzhen (SZSM202311012); Shenzhen Science and Technology Program (No.JCYJ20220530153604010).

  • Article
  • | |
  • Metrics
  • |
  • Reference [41]
  • |
  • Related
  • | | |
  • Comments
    Abstract:

    AIM: To evaluate the application of an intelligent diagnostic model for pterygium. METHODS: For intelligent diagnosis of pterygium, the attention mechanisms—SENet, ECANet, CBAM, and Self-Attention—were fused with the lightweight MobileNetV2 model structure to construct a tri-classification model. The study used 1220 images of three types of anterior ocular segments of the pterygium provided by the Eye Hospital of Nanjing Medical University. Conventional classification models—VGG16, ResNet50, MobileNetV2, and EfficientNetB7—were trained on the same dataset for comparison. To evaluate model performance in terms of accuracy, Kappa value, test time, sensitivity, specificity, the area under curve (AUC), and visual heat map, 470 test images of the anterior segment of the pterygium were used. RESULTS: The accuracy of the MobileNetV2+Self-Attention model with 281 MB in model size was 92.77%, and the Kappa value of the model was 88.92%. The testing time using the model was 9ms/image in the server and 138ms/image in the local computer. The sensitivity, specificity, and AUC for the diagnosis of pterygium using normal anterior segment images were 99.47%, 100%, and 100%, respectively; using anterior segment images in the observation period were 88.30%, 95.32%, and 96.70%, respectively; and using the anterior segment images in the surgery period were 88.18%, 94.44%, and 97.30%, respectively. CONCLUSION: The developed model is lightweight and can be used not only for detection but also for assessing the severity of pterygium.

    Reference
    1 Chu WK, Choi HL, Bhat AK, Jhanji V. Pterygium: new insights. Eye (Lond) 2020;34(6):1047-1050.
    2 Shao Y, Jie Y, Liu ZG, Expert Workgroup of Guidelines for the application of artificial intelligence in the diagnosis of anterior segment diseases (2023); Ophthalmic Imaging and Intelligent Medicine Branch of Chinese Medicine Education Association; Ophthalmology Committee of International Association of Translational Medicine; Chinese Ophthalmic Imaging Study Groups. Guidelines for the application of artificial intelligence in the diagnosis of anterior segment diseases (2023). Int J Ophthalmol 2023;16(9):1373-1385.
    3 Rezvan F, Khabazkhoob M, Hooshmand E, Yekta A, Saatchi M, Hashemi H. Prevalence and risk factors of pterygium: a systematic review and meta-analysis. Surv Ophthalmol 2018;63(5):719-735.
    4 Ke HQ, Zhang WJ, Liu H, et al. Prevalence and risk factors of pterygium in Zhuang and Miao nationality adults aged 40 and over in Wenshan prefecture, Yunnan Province. Guoji Yanke Zazhi(Int Eye Sci) 2022;22(2):347-351.
    5 Akbari M. Update on overview of pterygium and its surgical management. J Popul Ther Clin Pharmacol 2022;29(4):e30-e45.
    6 Yang M, Guan Y, Kang LH, et al. Meta-analysis of the prevalence of pterygium in people aged 40 years and above in China. Chinese Journal of Experimental Ophthalmology 2019;4(03):190-196.
    7 Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM 2017;60(6):84-90.
    8 Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014:arXiv:1409.1556. http://arxiv.org/abs/1409.1556
    9 He KM, Zhang XY, Ren SQ, Sun J. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. IEEE, 2016:770-778.
    10 Howard AG, Zhu ML, Chen B, Kalenichenko D, Wang WJ, Weyand T, Andreetto M, Adam H. MobileNets: efficient convolutional neural networks for mobile vision applications. 2017:arXiv:1704.04861. http://arxiv.org/abs/1704.04861
    11 Howard A, Zhmoginov A, Chen LC, et al. Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation. 2018:arXiv:1801.04381. https://arxiv.org/pdf/1801.04381
    12 Howard A, Sandler M, Chen B, et al. Searching for MobileNetV3.2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, Korea (South). IEEE, 2019:1314-1324.
    13 Ting DSW, Cheung CY, Lim G, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 2017;318(22):2211-2223.
    14 Yang WH, Zheng B, Wu MN, Zhu SJ, Fei FQ, Weng M, Zhang X, Lu PR. An evaluation system of fundus photograph-based intelligent diagnostic technology for diabetic retinopathy and applicability for research. Diabetes Ther 2019;10(5):1811-1822.
    15 Verbraak FD, Abramoff MD, Bausch GCF, et al. Diagnostic accuracy of a device for the automated detection of diabetic retinopathy in a primary care setting. Diabetes Care 2019;42(4):651-656.
    16 Sotoudeh-Paima S, Jodeiri A, Hajizadeh F, Soltanian-Zadeh H. Multi-scale convolutional neural network for automated AMD classification using retinal OCT images. Comput Biol Med 2022;144:105368.
    17 Peng YF, Dharssi S, Chen QY, Keenan TD, Agrón E, Wong WT, Chew EY, Lu ZY. DeepSeeNet: a deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs. Ophthalmology 2019;126(4):565-575.
    18 Greenwald MF, Danford ID, Shahrawat M, et al. Evaluation of artificial intelligence-based telemedicine screening for retinopathy of prematurity. J AAPOS 2020;24(3):160-162.
    19 Wang J, Ji J, Zhang MZ, et al. Automated explainable multidimensional deep learning platform of retinal images for retinopathy of prematurity screening. JAMA Netw Open 2021;4(5):e218758.
    20 Chang J, Lee J, Ha A, et al. Explaining the rationale of deep learning glaucoma decisions with adversarial examples. Ophthalmology 2021;128(1):78-88.
    21 Li F, Yan L, Wang YG, Shi JX, Chen H, Zhang XD, Jiang MS, Wu ZZ, Zhou KQ. Deep learning-based automated detection of glaucomatous optic neuropathy on color fundus photographs. Graefes Arch Clin Exp Ophthalmol 2020;258(4):851-867.
    22 Cen LP, Ji J, Lin JW, et al. Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks. Nat Commun 2021;12(1):4828.
    23 Zheng B, Jiang Q, Lu B, He K, Wu MN, Hao XL, Zhou HX, Zhu SJ, Yang WH. Five-category intelligent auxiliary diagnosis model of common fundus diseases based on fundus images. Transl Vis Sci Technol 2021;10(7):20.
    24 He K,Wu MN, Zheng B, et al. Research on the automatic classification system of pterygium based on deep learning. Guoji Yanke Zazhi(Int Eye Sci) 2022;22(5):711-715.
    25 Zhu SJ, Fang XW, Zheng B, et al. Research on segmentation of pterygium lesions based on convolutional neural networks. Guoji Yanke Zazhi(Int Eye Sci) 2022;22(6):1016-1019.
    26 López Y, Aguilera LR. Automatic classification of pterygium-non pterygium images using deep learning. In: Tavares J, Natal Jorge R. (eds) VipIMAGE 2019. Lecture Notes in Computational Vision and Biomechanics, vol 34. Springer, Cham.
    27 Wan Zaki WMD, Mat Daud M, Abdani SR, Hussain A, Mutalib HA. Automated pterygium detection method of anterior segment photographed images. Comput Methods Programs Biomed 2018;154: 71-78.
    28 Zulkifley MA, Abdani SR, Zulkifley NH. Pterygium-Net: a deep learning approach to pterygium detection and localization. Multimed Tools Appl 2019;78(24):34563-34584.
    29 Abdani SR, Zulkifley MA, Hussain A. Compact convolutional neural networks for pterygium classification using transfer learning. 2019 IEEE International Conference on Signal and Image Processing Applications (ICSIPA). Kuala Lumpur, Malaysia. IEEE, 2019:140-143.
    30 Zamani NSM, Zaki WMDW, Huddin AB, Hussain A, Mutalib HA, Ali A. Automated pterygium detection using deep neural network. IEEE Access 2062;8:191659-191672.
    31 Abdani SR, Zulkifley MA, Moubark AM. Pterygium tissues segmentation using densely connected deeplab. 2020 IEEE 10th Symposium on Computer Applications & Industrial Electronics (ISCAIE), Malaysia, 2020:229-232.
    32 Abdani SR, Zulkifley MA, Zulkifley NH. Group and shuffle convolutional neural networks with pyramid pooling module for automated pterygium segmentation. Diagnostics (Basel) 2021;11(6):1104.
    33 Deng J, Dong W, Socher R, Li LJ, Kai L, Li FF. ImageNet: a large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA. IEEE, 2009:248-255.
    34 Hung KH, Lin C, Roan J, et al. Application of a deep learning system in pterygium grading and further prediction of recurrence with slit lamp photographs. Diagnostics 2022;12(4):888.
    35 Gumus K, Erkilic K, Topaktas D, Colin J. Effect of pterygia on refractive indices, corneal topography, and ocular aberrations. Cornea 2011;30(1):24-29.
    36 Hu J, Shen L, Sun G. Squeeze-and-excitation networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018:7132-7141.
    37 Wang QL, Wu BG, Zhu PF, Li PH, Zuo WM, Hu QH. ECA-net: efficient channel attention for deep convolutional neural networks. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020:11531-11539,
    38 Woo S, Park J, Lee JY, et al. CBAM: convolutional block attention module. 2018:arXiv:1807.06521. https://arxiv.org/pdf/1807.06521
    39 Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. 2017:arXiv:1706.03762. https://arxiv.org/pdf/1706.03762
    40 Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017:618-626.
    41 Bikbov MM, Zainullin RM, Kazakbaeva GM, et al. Pterygium prevalence and its associations in a Russian population: the Ural eye and medical study. Am J Ophthalmol 2019;205:27-34.
    Related
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

Mao-Nian Wu, Kai He, Yi-Bei Yu,/et al.Intelligent diagnostic model for pterygium by combining attention mechanism and MobileNetV2. Int J Ophthalmol, 2024,17(7):1184-1192

Copy
Share
Article Metrics
  • Abstract:129
  • PDF: 377
  • HTML: 0
  • Cited by: 0
Publication History
  • Received:September 24,2023
  • Revised:April 01,2024
  • Online: June 25,2024