Automated Quantification of Photoreceptor alteration in macular disease using Optical Coherence Tomography and Deep Learning

Abstract

Diabetic macular edema (DME) and retina vein occlusion (RVO) are macular diseases in which central photoreceptors are affected due to pathological accumulation of fluid. Optical coherence tomography allows to visually assess and evaluate photoreceptor integrity, whose alteration has been observed as an important biomarker of both diseases. However, the manual quantification of this layered structure is challenging, tedious and time-consuming. In this paper we introduce a deep learning approach for automatically segmenting and characterising photoreceptor alteration. The photoreceptor layer is segmented using an ensemble of four different convolutional neural networks. En-face representations of the layer thickness are produced to characterize the photoreceptors. The pixel-wise standard deviation of the score maps produced by the individual models is also taken to indicate areas of photoreceptor abnormality or ambiguous results. Experimental results showed that our ensemble is able to produce results in pair with a human expert, outperforming each of its constitutive models. No statistically significant differences were observed between mean thickness estimates obtained from automated and manually generated annotations. Therefore, our model is able to reliable quantify photoreceptors, which can be used to improve prognosis and managment of macular diseases.

Automatic prediction of treatment outcomes in patients with diabetic macular edema using ensemble machine learning

“…According to a study, an ensemble scheme of four different CNNs was introduced to automatically segment and characterize photoreceptor alteration in macular disease. The results showed that the ensemble scheme outperformed each of its constitutive models with higher Dice coefficient, precision and sensitivity (39). Similarly, the accuracy of the prediction was performed by integrating the ensemble DL scheme and the ensemble CML scheme, which remained satisfactory according to the results of our study.…”

“…The model automatically processed vital information (also called "features") for predicting the prognosis and generated the output of CFT and BCVA predictions based on the integration of the above features. Recent studies have shown that the ensemble scheme outperformed each individual alternative, improving the performance obtained by each characterization model separately (39,40). According to a study, an ensemble scheme of four different CNNs was introduced to automatically segment and characterize photoreceptor alteration in macular disease.…”

Spatio-temporal alterations in retinal and choroidal layers in the progression of age-related macular degeneration (AMD) in optical coherence tomography

“…The reference frame may also be applied to other study cohorts such as healthy versus various stages of AMD (mild, moderate, severe) 31 , 41 to obtain a broader view on disease progression. Furthermore, with the rapid development in AI and particular deep learning, more accurate and fine-grained segmentations will become available 5 , such as precise RPE and photoreceptor segmentations 42 , 43 , which may lead to novel findings and highlight different aspects of disease progression when analysing these in the proposed reference frame. A spatio-temporal atlas may also incorporate other OCT modalities such as adaptive optics OCT (AO-OCT), OCT angiography (OCT-A) or directional OCT (D-OCT) 35 that provide complementary information regarding the disease course.…”

Quantitative assessment of retinal fluid in neovascular age-related macular degeneration under anti-VEGF therapy

“…AI-algorithms for either the quantification of photoreceptor loss or preferably subclinical photoreceptor thinning might become important tools for the evaluation of treatment effects in various macular diseases. 62 , 65 , 66 …”