Correlation between AI-measured lacquer cracks extension and development of myopic choroidal neovascularization

Differential diagnosis of myopic choroidal neovascularization (mCNV): insights from multimodal imaging and treatment implications

PURPOSE

The aim of this article is to conduct a comprehensive systematic review about the current understandings and differential diagnosis of myopic choroidal neovascularization (mCNV) and other several similar diseases, describing their multimodal imaging analysis, prognostic implications, and current types of management.

METHODS

This systematic review was performed based on a search on the PubMed database of relevant papers regarding mCNV and other entities discussed in the paper, according to our current knowledge.

RESULTS

Through the integration of a multimodal imaging approach, especially optical coherence tomography (OCT), along with accurate demographic and clinical assessment, it becomes possible to effectively differentiate mCNV from similar yet heterogeneous entities. These conditions include macular hemorrhage due to new lacquer crack (LC) formation, inflammatory diseases such as punctate inner choroidopathy (PIC)/multifocal choroidits (MFC) and epiphenomenon multiple evanescent white dot syndrome (Epi-MEWDS), neovascular age-related macular degeneration (nAMD), idiopathic CNV (ICNV), dome-shaped macula (DSM) with subretinal fluid, retinal pigment epithelium (RPE) humps, angioid streaks (AS), choroidal rupture (CR), and choroidal osteoma (CO). Each one of these entities will be described and discussed in this article.

CONCLUSION

Myopic choroidal neovascularization is a common retinal condition, especially among young individuals. Accurate diagnosis and differentiation from similar conditions are crucial for effective treatment. Multimodal imaging, particularly OCT, plays a crucial role in precise assessment. Future research should focus on defining biomarkers and distinguishing features to facilitate prompt treatment.

Pathogenesis of myopic choroidal neovascularization: A systematic review and meta-analysis

Myopic choroidal neovascularization (CNV) is a vision-threatening complication of high myopia. Here, we systematically review cohort, case-control, and cross-sectional studies in PubMed, Embase, and Web of Science, and summarize the associated factors of myopic CNV using meta-analysis where applicable. Among 1,333 records assessed, 50 were found eligible, all having a low-to-moderate risk of bias. Highly myopic eyes with CNV had a higher risk of lacquer cracks (odds ratio = 2.88) and patchy chorioretinal atrophy (odds ratio = 3.43) than those without. The mean posterior staphyloma height (µm) was greater in myopic CNV eyes than in highly myopic eyes without CNV (mean difference = 82.03). The thinning of choroidal thickness (µm) between myopic eyes with and without CNV differed significantly (mean difference = -47.76). The level of vascular endothelial growth factor (pg/ml) in the aqueous humor of myopic CNV eyes was significantly higher than in highly myopic eyes without CNV (mean difference = 24.98), the same as interleukin-8 (IL-8) (pg/ml, mean difference = 7.73). Single-nucleotide polymorphisms in the vascular endothelial growth factor, complement factor I, and collagen type VIII alpha 1 genes were associated with myopic CNV. We found that myopic CNV eyes have a higher ratio of lacquer cracks and patchy chorioretinal atrophy, thinner choroid, greater posterior staphyloma height, and a higher level of vascular endothelial growth factor and IL-8 in aqueous. Structural predisposing lesions, hemodynamic, genetic, and systemic factors are also associated with myopic CNV.

ARTIFICIAL INTELLIGENCE'S ROLE IN DIFFERENTIATING THE ORIGIN FOR SUBRETINAL BLEEDING IN PATHOLOGIC MYOPIA

PURPOSE

To identify salient imaging features to support human-based differential diagnosis between subretinal hemorrhage (SH) due to choroidal neovascularization (CNV) onset and SH without CNV (simple bleeding [SB]) in pathologic myopia eyes using a machine learning (ML)-based step-wise approach.

METHODS

Four different methods for feature extraction were applied: GradCAM visualization, reverse engineering, image processing, and human graders' measurements. GradCAM was performed on a deep learning model derived from Inception-ResNet-v2 trained with OCT B-scan images. Reverse engineering consisted of merging U-Net architecture with a deconvolutional network. Image processing consisted of the application of a local adaptive threshold. Available OCT B-scan images were divided in two groups: the first group was classified by graders before knowing the results of feature extraction and the second (different images) was classified after familiarization with the results of feature extraction.

RESULTS

Forty-seven and 37 eyes were included in the CNV group and the simple bleeding group, respectively. Choroidal neovascularization eyes showed higher baseline central macular thickness ( P = 0.036). Image processing evidenced in CNV eyes an inhomogeneity of the subretinal material and an interruption of the Bruch membrane at the margins of the SH area. Graders' classification performance improved from an accuracy of 76.9% without guidance to 83.3% with the guidance of the three methods ( P  = 0.02). Deep learning accuracy in the task was 86.0%.

CONCLUSION

Artificial intelligence helps identifying imaging biomarkers suggestive of CNV in the context of SH in myopia, improving human ability to perform differential diagnosis on unprocessed baseline OCT B-scan images. Deep learning can accurately distinguish between the two causes of SH.