Joint Multimodal Deep Learning-based Automatic Segmentation of Indocyanine Green Angiography and OCT Images for Assessment of Polypoidal Choroidal Vasculopathy Biomarkers.

Purpose: To develop a fully-automatic hybrid algorithm to jointly segment and quantify biomarkers of polypoidal choroidal vasculopathy (PCV) on indocyanine green angiography (ICGA) and spectral domain-OCT (SD-OCT) images. Design: Evaluation of diagnostic test or technology. Participants: Seventy-two participants with PCV enrolled in clinical studies at Singapore National Eye Center. Methods: The dataset consisted of 2-dimensional (2-D) ICGA and 3-dimensional (3-D) SD-OCT images which were spatially registered and manually segmented by clinicians. A deep learning-based hybrid algorithm called PCV-Net was developed for automatic joint segmentation of biomarkers. The PCV-Net consisted of a 2-D segmentation branch for ICGA and 3-D segmentation branch for SD-OCT. We developed fusion attention modules to connect the 2-D and 3-D branches for effective use of the spatial correspondence between the imaging modalities by sharing learned features. We also used self-supervised pretraining and ensembling to further enhance the performance of the algorithm without the need for additional datasets. We compared the proposed PCV-Net to several alternative model variants. Main Outcome Measures: The PCV-Net was evaluated based on the Dice similarity coefficient (DSC) of the segmentations and the Pearson's correlation and absolute difference of the clinical measurements obtained from the segmentations. Manual grading was used as the gold standard. Results: The PCV-Net showed good performance compared to manual grading and alternative model variants based on both quantitative and qualitative analyses. Compared to the baseline variant, PCV-Net improved the DSC by 0.04 to 0.43 across the different biomarkers, increased the correlations, and decreased the absolute differences of clinical measurements of interest. Specifically, the largest average (mean ± standard error) DSC improvement was for intraretinal fluid, from 0.02 ± 0.00 (baseline variant) to 0.45 ± 0.06 (PCV-Net). In general, improving trends were observed across the model variants as more technical specifications were added, demonstrating the importance of each aspect of the proposed method. Conclusion: The PCV-Net has the potential to aid clinicians in disease assessment and research to improve clinical understanding and management of PCV. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Comparison of photodynamic therapy, ranibizumab/bevacizumab or combination in the treatment of myopic choroidal neovascularisation: a 9-year-study from a single centre.

AIM: To compare treatment outcomes for myopic choroidal neovascularisation (CNV) managed with verteporfin photodynamic therapy (vPDT), intravitreal antivascular endothelial growth factor (anti-VEGF, bevacizumab/ranibizumab) agents or combination thereof. METHODS: Clinical data of 79 eyes with myopic CNV examined from March 2004 to July 2013 was retrospectively reviewed. Patients were managed with vPDT, intravitreal bevacizumab (1.25 mg/0.05 mL)/ranibizumab (0.5 mg/0.05 mL) or a combination of vPDT and anti-VEGF. Outcome measures included complete regression (scarring) of CNV and best-corrected visual acuity (BCVA). RESULTS: Treatments provided were vPDT (n=23), anti-VEGF (n=25) (ranibizumab, n=12; bevacizumab, n=13), vPDT+anti-VEGF (n=31). Mean logMAR BCVA changed from 0.59±0.44 to 0.49±0.40 at mean follow-up of 54.63±39.46 months. Mean logMAR vision changed from 0.68±0.57, 0.54±0.48 and 0.59±0.39 at presentation to 0.59±0.53, 0.38±0.44 and 0.37±0.37 at last follow-up in PDT (p=0.4), anti-VEGF (p=0.1) and vPDT+anti-VEGF groups (p=0.0002), respectively. CNV was scarred in 64 eyes (81%) at mean 11.03±13.56 months. Most common complication was macular scar (n=64), associated with reduced (n=17) or preserved (n=47) vision. Chorioretinal atrophy attributable to vPDT was seen in five eyes (vPDT, n=3; vPDT+anti-VEGF, n=2). CONCLUSION: Combination of vPDT and intravitreal anti-VEGF (ranibizumab/bevacizumab) was associated with better visual outcomes and higher rates of regression in eyes with myopic CNV as compared with monotherapy with PDT or anti-VEGF. Larger size of CNV, and high refractive error were independent risk factors for poor visual outcomes.