[Screening and management of retinal diseases using digital medicine]. / Screening und Management retinaler Erkrankungen mittels digitaler Medizin.

BACKGROUND: Modern retinal imaging creates gigantic amounts of data (big data) of anatomic information. At the same time patient numbers and interventions are increasing exponentially. OBJECTIVE: Introduction of artificial intelligence (AI) for optimization of personalized therapy and diagnosis. MATERIAL AND METHODS: Deep learning was introduced for automated segmentation and recognition of risk factors and activity levels in retinal diseases. RESULTS: Automated algorithms enable the precise identification and quantification of retinal fluid in all compartments. Early detection of retinopathy in diabetes or glaucoma or risk determination for the development of age-related macular degeneration (AMD) are possible as well as an individual visual prognosis and evaluation of the need for retreatment in intravitreal injection therapy. CONCLUSION: Methods using AI constitute a breakthrough perspective for the introduction of individualized medicine and optimization of diagnosis and therapy, screening and prognosis.

Supervised learning and dimension reduction techniques for quantification of retinal fluid in optical coherence tomography images.

PurposeThe purpose of the present study is to develop fast automated quantification of retinal fluid in optical coherence tomography (OCT) image sets.MethodsWe developed an image analysis pipeline tailored towards OCT images that consists of five steps for binary retinal fluid segmentation. The method is based on feature extraction, pre-segmention, dimension reduction procedures, and supervised learning tools.ResultsFluid identification using our pipeline was tested on two separate patient groups: one associated to neovascular age-related macular degeneration, the other showing diabetic macular edema. For training and evaluation purposes, retinal fluid was annotated manually in each cross-section by human expert graders of the Vienna Reading Center. Compared with the manual annotations, our pipeline yields good quantification, visually and in numbers.ConclusionsBy demonstrating good automated retinal fluid quantification, our pipeline appears useful to expert graders within their current grading processes. Owing to dimension reduction, the actual learning part is fast and requires only few training samples. Hence, it is well-suited for integration into actual manufacturer's devices, further improving segmentation by its use in daily clinical life.

Comparison of penetration depth in choroidal imaging using swept source vs spectral domain optical coherence tomography.

PURPOSE: To compare signal penetration depth and deep structure-visualization of swept source (SS) and spectral domain (SD)-optical coherence tomography (OCT) with and without enhanced depth imaging (EDI) and B-scan averaging modes. METHODS: Volume scans were obtained from 20 eyes of healthy volunteers by DRI OCT-1, Spectralis using EDI and B-scan averaging, and Cirrus HD-OCT. The signal penetration depth was measured as the distance between the retinal pigment epithelium and the deepest visible anatomical structure at the foveal center. Visibility and contrast of the choroidoscleral junction and of vascular details within the choroid were assessed across the entire volume using an ordinal scoring scale. Outcome measures were compared using paired t-test and rank-sum test. RESULTS: The mean signal penetration depth was 498±114 µm for Spectralis, 491±85 µm for DRI OCT-1, and 123±65 µm for Cirrus; P=0.9708 Spectralis vs DRI OCT-1, P<0.0001 Spectralis vs Cirrus, and P<0.0001 DRI OCT-1 vs Cirrus. Mean ranks for visibility and contrast of the choroidoscleral junction were 3.83 for Spectralis, 3.98 for DRI OCT-1, and 2.00 for Cirrus; and 3.45 for Spectralis, 2.93 for DRI OCT-1, and 1.58 for Cirrus. Mean ranks for visibility and contrast of vascular details were 3.73 (Spectralis), 3.70 (DRI OCT-1), and 2.23 (Cirrus); and 3.53 (Spectralis), 2.05 (DRI OCT-1), and 1.98 (Cirrus). CONCLUSION: Signal penetration depths are similar for SS-OCT and SD-OCT using EDI and frame averaging, and statistically significantly lower without EDI/averaging. Both SD-OCT using EDI/frame averaging and SS-OCT offer excellent visualization capabilities for volumetric imaging of the choroidoscleral interface.