June 2020
Volume 61, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2020
Deep Learning based diagnosis of Sjögren syndrome using In Vivo Confocal Microscopy
Author Affiliations & Notes
  • Melanie Lubrano di Scandalea
    KEEN EYE Technologies, Paris, France
  • Jade Luzu
    Quinze-vingts,Centre Hospitalier National d’Ophtalmologie, Paris, France
  • Damien Sène
    Hôpital Lariboisière, APHP, Paris, France
  • Antoine Labbé
    Quinze-vingts,Centre Hospitalier National d’Ophtalmologie, Paris, France
  • Christophe Baudouin
    Quinze-vingts,Centre Hospitalier National d’Ophtalmologie, Paris, France
  • Sylvain BERLEMONT
    KEEN EYE Technologies, Paris, France
  • Footnotes
    Commercial Relationships   Melanie Lubrano di Scandalea, KEEN EYE Technologies (E); Jade Luzu, None; Damien Sène, None; Antoine Labbé, Aerie (C), Alcon (C), Allergan (C), Bausch & Lomb (C), Horus Pharma (C), Novartis (C), Santen (C), Théa (C); Christophe Baudouin, Aerie (C), Alcon (C), Allergan (C), Horus Pharma (F), Horus Pharma (C), Santen (F), Santen (C), Théa (F), Théa (C); Sylvain BERLEMONT, KEEN EYE Technologies (I)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 1621. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Melanie Lubrano di Scandalea, Jade Luzu, Damien Sène, Antoine Labbé, Christophe Baudouin, Sylvain BERLEMONT; Deep Learning based diagnosis of Sjögren syndrome using In Vivo Confocal Microscopy. Invest. Ophthalmol. Vis. Sci. 2020;61(7):1621.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Sjögren syndrome (SS) can lead to severe ocular pain and discomfort. Patients with SS exhibit corneal inflammation and alterations of the sub-basal plexus nerves. Additionally, SS is hard to diagnose as it requires invasive exams (e.g. salivary glands biopsy). In Vivo Confocal Microscopy (IVCM) offers to assess corneal nerve fibers in non-invasive way. Analyzing such images with Deep Learning based method could help to identify patterns and redundancies so far invisible to ophthalmologists.
Our solution offers to use Convolutional Neural Networks (CNN) in a Multiple Instance Learning setting to help diagnose Sjögren syndrome from IVCM images.

Methods :
Material:
Cohort of 80 patients from 15-20 hospital (17 healthy volunteers, 63 patients with SS), splitted between the training set and the test set.
The dataset consists of a hundreds of IVCM images per patient, acquired and pre-selected by the ophthalmologist and clinical data. See figure 1.
Method:
The method relies on two steps:
1) Segmentation of nerves, inflammatory cells and neuromas was performed on 200 IVCM images using a U-Net network. Abstract features learned from the segmentation task were then transferred to a second network (transfer learning).
2) A second network was used to perform the diagnostic task. It takes advantage of the Multiple Instance Learning (MIL) framework to let the model benefit from the multiple images available for each patient. This network relies on two parts: the “tile predictor” attributing a score to each image, and the “aggregator” (attention mechanism was used) to aggregate the score of each images in the best way possible and perform a good diagnosis.

Results : Figure 2 presents the confusion matrix for the binary classification on control patients versus SS patients. The model demonstrated an accuracy of 81.1 % and an average ROC AUC of 0.69, as well as the ROC Curve for the SS class on the test set.

Conclusions : This model demonstrates promising results in the ability to diagnose and monitor Sjögren syndrome from IVCM images, using non-invasive exams. Future works will consist in validating and improving the current algorithm on a larger cohort of patients.

This is a 2020 ARVO Annual Meeting abstract.

 

Figure 1: Sample of In Vivo Confocal Microscopy Images (Sjögren syndrome)

Figure 1: Sample of In Vivo Confocal Microscopy Images (Sjögren syndrome)

 

Figure 2: Confusion matrix on the test set (left) and ROC Curve for the SS class (right)

Figure 2: Confusion matrix on the test set (left) and ROC Curve for the SS class (right)

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×