Name

Performance de la détection automatisée du liquide rétinien à partir d'images OCT dans le traitement de la dégénérescence maculaire liée à l'âge exsudative en pratique clinique courante

Outcomes in neovascular age-related macular degeneration (nAMD) are often inferior in real-world practice which is mostly due to a high variability in the assessment of OCT images lacking precision and repeatability. Automated clinical decision support systems (CDSS) based on artificial intelligence (AI) are able to objectively identify and quantify macular fluid compartments such as intraretinal fluid (IRF),subretinal fluid (SRF) and pigment epithelium detachment (PED) in nAMD. This study analyzes the performance of the first CDSS with regulatory approval on optical coherence tomography (OCT) data from a real-world outpatient clinic.

A multi-class deep learning-based method was developed to identify regions of SRF, IRF and PED in nAMD eyes. Dilated convolutions are used to detect fluid regions at multiple features and ensembling methods were used to increase confidence in the final pixel label. The dataset was comprised of 219 SD-OCT volumes (Spectralis, Heidelberg Engineering, Heidelberg, Germany), with 6210 b-scans from 155 different nAMD patients. The tool was used in a prospective manner in comparison with conventional therapy management.

Automated AI-based and human expert quantification of fluid volumes were compared in a comprehensive training set of 136 OCT volumes with 3620 annotated B-scans, the validation set contained 40 OCT volumes with 1314 annotated B-scans, and the test set contained 43 OCT volumes with 1276 annotated B-scans. The Pearson correlations in the central 1mm of the ETDRS-grid for each quantitative fluid volume showed strong correlations between automated and the human expert gradings with values for IRF: r=0.9998, p<0.001; SRF: r=0.9940, p<0.001, and PED: r=0.9848, p<0.001. Fluid detection was consistently well performed by the algorithm for each compartment on the B-scan level: IRF (dice: 0.9207, sensitivity: 0.8960, precision: 0.9468), SRF: (dice: 0.9660, sensitivity 0.9733, precision 0.9589), and PED (dice: 0.9153, sensitivity 0.9450, precision 0.8873).

The tool was then used in the routine management of neovascular AMD by anti-VEGF therapy with reliable performance allowing to identify the activity of all fluid types over long-term follow-up to objectively guide treatment decisions.

Disease activity and therapeutic response in nAMD can be measured in a precise and repeatable manner using AI-based CDSS such as the Fluid Monitor. Quantifications of macular fluids enable clinicians to base their re-treatment criteria on objective evaluation performed fast and in real-time in a busy clinic. With the use of accurate fluid quantification every clinician is empowered to high-quality and transparency in AMD management introducing precision medicine and personalized treatment by saving costs and reducing workload.