Skip to main content
SpringerLink
Log in

Multi-view deep learning for rigid gas permeable lens base curve fitting based on Pentacam images

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Many studies in the rigid gas permeable (RGP) lens fitting field have focused on providing the best fit for patients with irregular astigmatism, a challenging issue. Despite the ease and accuracy of fitting in the current fitting methods, no studies have provided a high-pace solution with the final best fit to assist experts. This work presents a deep learning solution for identifying features in Pentacam four refractive maps and RGP base curve identification. An authentic dataset of 247 samples of Pentacam four refractive maps was gathered, providing a multi-view image of the corneal structure. Scratch-based convolutional neural network (CNN) architectures and well-known CNN architectures such as AlexNet, GoogLeNet, and ResNet have been used to extract features and transfer learning. Features are aggregated through a fusion technique. Based on a comparison of means square error (MSE) of normalized labels, the multi-view scratch-based CNN provided R-squared of 0.849, 0.846, 0.835, and 0.834 followed by GoogLeNet, comparable with current methods. Transfer learning outperforms various scratch-based CNN models, through which proper specifications some scratch-based models were able to increase coefficient of determinations. CNNs on multi-view Pentacam images have enabled fast detection of the RGP lens base curve, higher patient satisfaction, and reduced chair time.

The Pentacam four refractive maps is learned by the proposed scratch-based and transfer learning–based CNN methodology. The deep network–based solutions enable identification of rigid gas permeable lens for patients with irregular astigmatism.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. http://www.noorvision.com/default.aspx

References

  1. Anderson D, Chang C, Kusy P, Olafsson HE, Roddy D, Ziémba SL (2013) Clinical white paper- case reports: the UltraHealth silicone hydrogel contact lens for keratoconus and irregular corneas, Carlsbad, CA

  2. Mathews SM, Bradley JC, George JG, Xu KT (2005) Predicting contact lens base curve using corneal topography in keratoconus. Invest Ophthalmol Vis Sci 46:18

    Google Scholar 

  3. Yildiz EH, Erdurmus M, Elibol ES, Acar B, Vural ET (2015) Contact lens impact on quality of life in keratoconus patients: rigid gas permeable versus soft silicone-hydrogel keratoconus lenses. Int J Ophthalmol 8(5):1074–1077

    PubMed  PubMed Central  Google Scholar 

  4. Alkhaldi W (2010) Statistical signal and image processing techniques in corneal modeling. TU Darmstadt

  5. Alió JL, Belda JI, Artola A, García-Lledó M, Osman A (2002) Contact lens fitting to correct irregular astigmatism after corneal refractive surgery. J Cataract Refract Surg 28(10):1750–1757

    Article  PubMed  Google Scholar 

  6. Jain R, Grewal S (2009) Pentacam: principle and clinical applications. J Curr Glaucoma Pract 3(2):20–32

    Article  Google Scholar 

  7. Miranda MA, Radhakrishnan H, O’Donnell C (2009) Repeatability of oculus pentacam metrics derived from corneal topography. Cornea 28(6):657–666

    Article  PubMed  Google Scholar 

  8. Hashemi H, Mehravaran S (2010) Day to day clinically relevant corneal elevation, thickness, and curvature parameters using the orbscan II scanning slit topographer and the pentacam scheimpflug imaging device. Middle East Afr J Ophthalmol 17(1):44

    PubMed  PubMed Central  Google Scholar 

  9. Nosch DS, Ong GL, Mavrikakis I, Morris J (2007) The application of a computerised videokeratography (CVK) based contact lens fitting software programme on irregularly shaped corneal surfaces. Cont Lens Anterior Eye 30(4):239–248

    Article  PubMed  Google Scholar 

  10. Siddireddy JS, Mahadevan R (2013) Comparison of conventional method of contact lens fitting and software based contact lens fitting with Medmont corneal topographer in eyes with corneal scar. Contact Lens Anterior Eye 36(4):176–181

    Article  PubMed  Google Scholar 

  11. Ortiz-Toquero S, Rodriguez G, de Juan V, Martin R (2016) Rigid gas permeable contact lens fitting using new software in keratoconic eyes. Optom Vis Sci 93(3):286–292

    Article  PubMed  Google Scholar 

  12. Ortiz-Toquero S, Rodriguez G, de Juan V, Martin R (2017) New web-based algorithm to improve rigid gas permeable contact lens fitting in keratoconus. Contact Lens Anterior Eye 40(3):143–150

    Article  PubMed  Google Scholar 

  13. Zhao F, Wang J, Wang L, Chen L (2018) An approach for simulating the fitting of rigid gas-permeable contact lenses using 3D printing technology. Contact Lens Anterior Eye

  14. Wang K, Zhou S, Fu CA, Yu JX (2003) Mining changes of classification by correspondence tracing, in Proceedings of the 2003 SIAM International Conference on Data Mining, pp 95–106

  15. Awadalla M, El-Far S (2012) Aggregate function based enhanced a priori algorithm for mining association rules. Int J Comput Sci Issues 9(3):277–287

    Google Scholar 

  16. Mohammed E (2013) A framework intelligent mobile for diagnosis contact lenses by applying case based reasoning. In: Innovations and advances in computer, information, systems sciences, and engineering. Springer, pp 1233–1238

  17. Dua D, Karra Taniskidou E UCI machine learning repository. University of California, School of Information and Computer Science, Irvine

  18. Cardona G, Isern R (2011) Topography-based RGP lens fitting in normal corneas: the relevance of eyelid and tear film attributes. Eye Contact Lens Sci Clin Pract 37(6):359–364

    Article  Google Scholar 

  19. Rajabi MT, Mohajernezhad-Fard Z, Naseri SK, Jafari F, Doostdar A, Zarrinbakhsh P, Rajabi MB, Kohansal S (2011) Rigid contact lens fitting based on keratometry readings in keratoconus patients: predicting formula. Int J Ophthalmol 4(5):525–528

    PubMed  PubMed Central  Google Scholar 

  20. Pang S, Du A, Orgun MA, Yu Z (2019) A novel fused convolutional neural network for biomedical image classification. Med Biol Eng Comput 57(1):107–121

    Article  PubMed  Google Scholar 

  21. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak J, van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88

    Article  PubMed  Google Scholar 

  22. Zu C, Zhu L, Zahng D (2017) Iterative sparsity score for feature selection and its entension for multimodal data. Neurocomputing 259:146–153

    Article  Google Scholar 

  23. Zhao Y et al (2019) A CNN-based prototype method of unstructured surgical state perception and navigation for an endovascular surgery robot. Med Biol Eng Comput:1–13

  24. Shin H-C, Roth HR, Gao M, Lu L, Xu Z, Nogues I, Yao J, Mollura D, Summers RM (2016) Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35(5):1285–1298

    Article  PubMed  Google Scholar 

  25. Zou J, Rui T, Zhou Y, Yang C, Zhang S (2018) Convolutional neural network simplification via feature map pruning. Comput Electr Eng 70:950–958

    Article  Google Scholar 

  26. Yoo TK, Choi JY, Seo JG, Ramasubramanian B, Selvaperumal S, Kim DW (2019) The possibility of the combination of OCT and fundus images for improving the diagnostic accuracy of deep learning for age-related macular degeneration: a preliminary experiment. Med Biol Eng Comput 57(3):677–687

    Article  PubMed  Google Scholar 

  27. Tajbakhsh N, Shin JY, Gurudu SR, Hurst RT, Kendall CB, Gotway MB, Jianming Liang (2016) Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging 35(5):1299–1312

    Article  PubMed  Google Scholar 

  28. Dao TT (2019) From deep learning to transfer learning for the prediction of skeletal muscle forces. Med Biol Eng Comput 57(5):1049–1058

    Article  PubMed  Google Scholar 

  29. Mazo C, Bernal J, Trujillo M, Alegre E (2018) Transfer learning for classification of cardiovascular tissues in histological images. Comput Methods Prog Biomed 165:69–76

    Article  Google Scholar 

  30. Pan SJ, Yang Q (Oct. 2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359

    Article  Google Scholar 

  31. Chen C-H et al (2019) Computer-aided diagnosis of endobronchial ultrasound images using convolutional neural network. Comput Methods Prog Biomed 177:175–182

    Article  Google Scholar 

  32. Shin HC, Lu L, Kim L, Seff A, Yao J, Summers RM (2015) Interleaved text/image deep mining on a very large-scale radiology database, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1090–1099

  33. Bar Y, Diamant I, Wolf L, Lieberman S, Konen E, Greenspan H (2015) Chest pathology detection using deep learning with non-medical training, in 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), pp 294–297

  34. Huynh BQ, Li H, Giger ML (2016) Digital mammographic tumor classification using transfer learning from deep convolutional neural networks. J Med Imaging (Bellingham, Wash.) 3(3):034501

    Article  Google Scholar 

  35. Chen H, Zheng Y, Park J-H, Heng P-A, Zhou SK (2016) Iterative multi-domain regularized deep learning for anatomical structure detection and segmentation from ultrasound images. Springer, Cham, pp 487–495

    Google Scholar 

  36. Margeta J, Criminisi A, Cabrera Lozoya R, Lee DC, Ayache N (2017) Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition. Comput Methods Biomech Biomed Eng Imaging Vis 5(5):339–349

    Article  Google Scholar 

  37. Karri SPK, Chakraborty D, Chatterjee J (2017) Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration. Biomed Opt Express 8(2):579–592

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  38. Yu Y et al (2017) Deep transfer learning for modality classification of medical images. Information 8(3):91

    Article  Google Scholar 

  39. Cheng PM, Malhi HS (2017) Transfer learning with convolutional neural networks for classification of abdominal ultrasound images. J Digit Imaging 30(2):234–243

    Article  PubMed  Google Scholar 

  40. Shahin AI, Guo Y, Amin KM, Sharawi AA (2019) White blood cells identification system based on convolutional deep neural learning networks. Comput Methods Prog Biomed 168:69–80

    Article  CAS  Google Scholar 

  41. Jie B, Zhang D, Cheng B, Shen D (2015) Manifold regularized multitask feature learning for multimodality disease classification. Hum Brain Mapp 36(2):489–507

    Article  PubMed  Google Scholar 

  42. Hasan SA, Singh M (2014) Automatic diagnosis of astigmatism for Pentacam sagittal maps, in International Conference on Advances in Computing, Communications and Informatics (ICACCI, 2014), pp. 472–478

  43. Faust O, Hagiwara Y, Hong TJ, Lih OS, Acharya UR (2018) Deep learning for healthcare applications based on physiological signals: a review. Comput Methods Prog Biomed 161:1–13

    Article  Google Scholar 

  44. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks, in Advances in neural information processing systems 25 (NIPS 2012), pp 1097–1105

  45. Szegedy C et al (2015) Going deeper with convolutions, in IEEE conference on computer vision and pattern recognition, pp 1–9

  46. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition, in Computer Vision and Pattern Recogn, pp 770–778

  47. Alom MZ et al (2018) The history began from AlexNet: a comprehensive survey on deep learning approaches

    Google Scholar 

  48. H. M. Ahmad, S. Ghuffar, and K. Khurshid (2019) Classification of breast cancer histology images using transfer learning, in 2019 16th International Bhurban Conference on Applied Sciences and Technology (IBCAST), pp 328–332

  49. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition

    Google Scholar 

  50. Shao L, Zhu F, Li X (2015) Transfer learning for visual categorization: a survey. IEEE Trans Neural Networks Learn Syst 26(5):1019–1034

    Article  Google Scholar 

  51. Jorge A, Jose B, Amr O, Ahmad S (2003) Topography-guided laser in situ keratomileusis (TOPOLINK) to correct irregular astigmatism after previous refractive surgery. J Refract Surg 19(5):516–527

    Google Scholar 

  52. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift, In 32nd International Conference on Machine Learning

  53. Bausch and Lomb, Boston gas permeable contact lens materials, 2016. [Online]. Available: http://www.bauschsvp.com/Portals/137/assets/boston-xo-eo-es-insert.pdf. Accessed May 2019

Download references

Author information

Authors and Affiliations

  1. Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran

    Sara Hashemi, Hadi Veisi & Zainabolhoda Heshmati

  2. Department of Optometry, School of Rehabilitation Science, Iran University of Medical Sciences, Tehran, Iran

    Ebrahim Jafarzadehpur

  3. Digikala Company, Tehran, Iran

    Rouhollah Rahmani

Authors
  1. Sara Hashemi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hadi Veisi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ebrahim Jafarzadehpur
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Rouhollah Rahmani
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zainabolhoda Heshmati
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hadi Veisi.

Ethics declarations

Conflict of interest

The authors declare that they do not have a conflict of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hashemi, S., Veisi, H., Jafarzadehpur, E. et al. Multi-view deep learning for rigid gas permeable lens base curve fitting based on Pentacam images. Med Biol Eng Comput 58, 1467–1482 (2020). https://doi.org/10.1007/s11517-020-02154-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-020-02154-4

Keywords

Search

Navigation