The implementation of clinical-decision support algorithms for medical imaging faces challenges with reliability and interpretability. Here, we establish a diagnostic tool based on a deep-learning framework for the screening of patients with common treatable blinding retinal diseases. Our framework utilizes transfer learning, which trains a neural network with a fraction of the data of conventional approaches. Applying this approach to a dataset of optical coherence tomography images, we demonstrate performance comparable to that of human experts in classifying age-related macular degeneration and diabetic macular edema. We also provide a more transparent and interpretable diagnosis by highlighting the regions recognized by the neural network. We further demonstrate the general applicability of our AI system for diagnosis of pediatric pneumonia using chest X-ray images. This tool may ultimately aid in expediting the diagnosis and referral of these treatable conditions, thereby facilitating earlier treatment, resulting in improved clinical outcomes. VIDEO ABSTRACT.
The human lens is comprised largely of crystallin proteins assembled into a highly ordered, interactive macro-structure essential for lens transparency and refractive index. Any disruption of intra- or inter-protein interactions will alter this delicate structure, exposing hydrophobic surfaces, with consequent protein aggregation and cataract formation. Cataracts are the most common cause of blindness worldwide, affecting tens of millions of people, and currently the only treatment is surgical removal of cataractous lenses. The precise mechanisms by which lens proteins both prevent aggregation and maintain lens transparency are largely unknown. Lanosterol is an amphipathic molecule enriched in the lens. It is synthesized by lanosterol synthase (LSS) in a key cyclization reaction of a cholesterol synthesis pathway. Here we identify two distinct homozygous LSS missense mutations (W581R and G588S) in two families with extensive congenital cataracts. Both of these mutations affect highly conserved amino acid residues and impair key catalytic functions of LSS. Engineered expression of wild-type, but not mutant, LSS prevents intracellular protein aggregation of various cataract-causing mutant crystallins. Treatment by lanosterol, but not cholesterol, significantly decreased preformed protein aggregates both in vitro and in cell-transfection experiments. We further show that lanosterol treatment could reduce cataract severity and increase transparency in dissected rabbit cataractous lenses in vitro and cataract severity in vivo in dogs. Our study identifies lanosterol as a key molecule in the prevention of lens protein aggregation and points to a novel strategy for cataract prevention and treatment.
In 2009, it was postulated that endothelial cells (ECs) would only be able to execute the orders of growth factors if these cells would accordingly adapt their metabolism. Ten years later, it has become clear that ECs, often differently from other cell types, rely on distinct metabolic pathways to survive and form new blood vessels; that manipulation of EC metabolic pathways alone (even without changing angiogenic signaling) suffices to alter vessel sprouting; and that perturbations of these metabolic pathways can underlie excess formation of new blood vessels (angiogenesis) in cancer and ocular diseases. Initial proof of evidence has been provided that targeting (normalizing) these metabolic perturbations in diseased ECs and delivery of metabolites deserve increasing attention as novel therapeutic approaches for inhibiting or stimulating vessel growth in multiple disorders.
Endothelial Metabolic Pathways Securing BioenergeticsCellular metabolism serves at least three main purposes, i.e., energy production, biomass synthesis, and redox homeostasis, in
SUMMARY
Glaucoma, a blinding neurodegenerative disease, whose risk factors include elevated intraocular pressure (IOP), age and genetics, is characterized by accelerated and progressive retinal ganglion cell (RGC) death. Despite decades of research, the mechanism of RGC death in glaucoma is still unknown. Here, we demonstrate that the genetic effect of the SIX6 risk-variant (rs33912345, His141Asn) is enhanced by another major POAG risk gene P16/INK4A (cyclin-dependent kinase inhibitor 2A). We further show that the upregulation of homozygous SIX6 risk alleles (CC) leads to an increase in P16/INK4A expression with a subsequent cellular senescence, as evidenced in a mouse model of elevated IOP and in human POAG eyes. Our data indicate that SIX6 and/or IOP promotes POAG by directly increasing P16/INK4A expression, leading to RGC senescence in adult human retinas. Our study provides important insights linking genetic susceptibility to the underlying mechanism of RGC death and provides a unified theory of glaucoma pathogenesis.
As a progressive chronic disease, age-related macular degeneration (AMD) is the leading cause of irreversible vision impairment worldwide. Experimental and clinical evidence has demonstrated that vascular endothelial growth factor (VEGF) plays a vital role in the formation of choroidal neovascularization. Intravitreal injections of anti-VEGF agents have been recommended as a first-line treatment for neovascular AMD. However, persistent fluid or recurrent exudation still occurs despite standardized anti-VEGF therapy. Patients suffering from refractory or recurrent neovascular AMD may develop mechanisms of resistance to anti-VEGF therapy, which results in a diminished therapeutic effect. Until now, there has been no consensus on the definitions of refractory neovascular AMD and recurrent neovascular AMD. This article aims at clarifying these concepts to evaluate the efficacy of switching drugs, which contributes to making clinical decision more scientifically. Furthermore, insight into the causes of resistance to anti-VEGF therapy would be helpful for developing possible therapeutic approaches, such as combination therapy and multi-target treatment that can overcome this resistance.
Purpose. To describe the morphological characteristics and efficacy of OCTA in detecting CNV in nAMD. We retrospectively reviewed 53 patients (86 eyes) with suspected CNV secondary to wet AMD. All the patients underwent a multimodal assessment for CNV. Two independent readers calculated the sensitivity and specificity of OCTA in detecting CNV compared with FA. A qualitative analysis of OCTA was also performed to describe the morphological appearance of CNV. Among 86 eyes of 53 patients, 52 eyes were diagnosed as having CNV based on the FA imaging analysis. According to FA, CNV was classified as classic in 28 eyes, predominantly classic in 6 eyes, minimally classic in 9 eyes, and occult in 9 eyes. In 56 eyes, CNV was visualized on OCTA and corresponding OCT B-scans. In total, 46.4% (26/56) had well-circumscribed vessels, and 53.6% (30/56) showed poorly circumscribed vessels. There were 11 false positives and 7 false negatives using OCTA. The specificity of OCTA for the detection of CNV was 67.6%, with sensitivity of 86.5%. OCTA may help in the noninvasive diagnosis of CNV and may provide a method for monitoring the evolution of CNV.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.