OCTAGON Research Group - Bringing AI to Ophthalmology

Aim

The OCTAGON Research Group was established in January 2017 by Dr. Michael J.A. Girard and Dr. Alexandre H. Thiery. It aims to make a significant impact in glaucoma diagnosis and prognosis using artificial intelligence (deep learning) and 3D medical imaging (optical coherence tomography or OCT).

Providing an accurate glaucoma diagnosis is a complex endeavor that is time consuming. It is subjective and heavily dependent on a clinician’s experience/expertise, often requiring multiple clinical tests. Such tests often need to be repeated at multiple patients’ visits to overcome their inherent subjectivity to confirm a diagnosis. Furthermore, in 2016, the World Glaucoma Association stated that: “as yet there is no widely-accepted method of combining the results of several tests [to provide an accurate diagnosis/prognosis]”. In fact, the use of multiple diagnostic tests has been found to increase the likelihood of false-positives yielding to over-treatment.


To simplify glaucoma management, our team is currently developing custom-written artificial intelligence algorithms that can be applied to 3D OCT images of the optic nerve head (ONH) - the main site of glaucoma damage. We aim to provide a glaucoma diagnosis/prognosis that is more accurate than that given by any other gold-standard glaucoma parameters (or their combinations).

Principal Investigators

Michaël J.A. Girard, PhD

Alexandre H. Thiery, PhD

Research Staffs

Sripad Devalla, PhD Candidate

Haris Cheong, PhD Candidate

Dr Satish Panda, Fellow

Atin Ghosh, PhD Candidate

Than Chuangsuwanich, PhD C


Collaborators

Through OCTAGON, we have established collaborations with more than 15 glaucoma research groups worldwide (in China, India, Korea, Phillipines, France, Denmark, USA, Russia, Australia, Dubai).

Note that we are continuously looking for more clinical collaborators to provide us with OCT scans of the ONH. If you are intersted in joining exciting research, please drop us a line!

Selected Publications and Abstracts

  • Devalla SK, Subramanian G, Pham TH, Wang X, Perera S, Tun TA, Aung T, Schmetterer L, Thiery AH, Girard MJA. A Deep Learning Approach to Denoise Optical Coherence Tomography Images of the Optic Nerve Head. 2018. arXiv preprint arXiv:1809.10589. Pdf. arXiv.
  • Girard MJA, Chin KS, Devalla S, Aung T, Jonas J, Wang YX, Thiery AH. Deep Learning can Exploit 3D Structural Information of the Optic Nerve Head to Provide a Glaucoma Diagnostic Power Superior to that of Retinal Nerve Fibre Layer Thickness. Association for Research in Vision and Ophthalmology (ARVO) Annual Meeting, Hawaii, USA, Apr 29 - May 3 2018.
  • Devalla SK, Mari JM, Tun TA, Chin KS, Strouthidis NG, Aung T, Thiery AH, Girard MJA. A Device- Independent Deep Learning Approach to Digitally Stain Optical Coherence Tomography Images of the Optic Nerve Head. Association for Research in Vision and Ophthalmology (ARVO) Annual Meeting, Hawaii, USA, Apr 29 - May 3 2018.
  • Devalla SK, Renukanand PK, Sreedhar BK, Perera SA, Mari JM, Chin KS, Tun TA, Strouthidis N, Aung T, Thiery A, Girard MJA. DRUNET: A Dilated-Residual U-Net Deep Learning Network to Digitally Stain Optic Nerve Head Tissues in Optical Coherence Tomography Images. Biomed Opt Express. 2018 Jun 25;9(7):3244-3265. Pdf. Pubmed.
  • Devalla SK, Renukanand PK, Sreedhar BK, Perera S, Mari JM, Chin KS, Tun TA, Strouthidis N, Aung T, Thiery A, Girard MJA. DRUNET: A Dilated-Residual U-Net Deep Learning Network to Digitally Stain Optic Nerve Head Tissues in Optical Coherence Tomography Images. 2018. arXiv preprint arXiv:1803.00232. Pdf. arXiv.
  • Devalla SK, Mari JM, Tun TA, Strouthidis N, Aung T, Thiery A, Girard MJA. A Deep Learning Approach to Digitally Stain Optical Coherence Tomography Images of the Optic Nerve Head. 2018. Invest Ophthalmol Vis Sci. 59(1):63-74 Pdf. Pubmed.
  • Devalla SK, Mari JM, Tun TA, Strouthidis N, Aung T, Thiery A, Girard MJA. A Deep Learning Approach to Digitally Stain Optical Coherence Tomography Images of the Optic Nerve Head. 2017. arXiv preprint arXiv:1707.07609. Pdf. arXiv.
  • Girard MJA, Tun TA, Husain R, Wei X, Mari JM, Perera SA, Baskaran M, Aung T, Strouthidis NG. Lamina Cribrosa Visibility using Optical Coherence Tomography: Comparison of Devices and Effects of Image Enhancement Techniques. Invest Ophthalmol Vis Sci. 2015 Jan 15;56(2):865-74. Pdf. Pubmed.
  • Mari JM, Park SC, Strouthids NG, Girard MJA. Enhancement of Lamina Cribrosa Visibility in Optical Coherence Tomography Images Using Adaptive Compensation. Invest Ophthalm and Vis Sci. 2013; 54(3):2238-47. Pdf. Pubmed. IOVS.
  • Girard MJA, Strouthidis NG, Ethier CR, Mari JM. Shadow Removal and Contrast Enhancement in Optical Coherence Tomography Images of the Human Optic Nerve Head. Invest Opthalmol and Vis Sci. 2011; 52(10):7738-48. Pdf. Pubmed. IOVS.

Press Releases

  • Devalla SK, Thiery A, Girard MJA. ARVO News: Image Interpretation: The Next Hurdle.
  • Devalla SK, Mari JM, Trau D, Girard MJA. Abyss Processing - Exploring the Deep in Medical Images. Asia-Pacific Biotech News. Vol 20, No 12, December 2016 - Medical Image Technology.

Interested in Joining our Group?

We are always looking for smart, dynamic, and highly motivated scientists to perfrom ground breaking research in AI and Ophthalmology. Please drop us a line in case positions are available.