No abstract

IMPORTANCE A deep learning system (DLS) that could automatically detect glaucomatous optic neuropathy (GON) with high sensitivity and specificity could expedite screening for GON.OBJECTIVE To establish a DLS for detection of GON using retinal fundus images and glaucoma diagnosis with convoluted neural networks (GD-CNN) that has the ability to be generalized across populations. DESIGN, SETTING, AND PARTICIPANTSIn this cross-sectional study, a DLS for the classification of GON was developed for automated classification of GON using retinal fundus images obtained from the Chinese Glaucoma Study Alliance, the Handan Eye Study, and online databases. The researchers selected 241 032 images were selected as the training data set. The images were entered into the databases on June 9, 2009, obtained on July 11, 2018, and analyses were performed on December 15, 2018. The generalization of the DLS was tested in several validation data sets, which allowed assessment of the DLS in a clinical setting without exclusions, testing against variable image quality based on fundus photographs obtained from websites, evaluation in a population-based study that reflects a natural distribution of patients with glaucoma within the cohort and an additive data set that has a diverse ethnic distribution. An online learning system was established to transfer the trained and validated DLS to generalize the results with fundus images from new sources. To better understand the DLS decision-making process, a prediction visualization test was performed that identified regions of the fundus images utilized by the DLS for diagnosis. EXPOSURES Use of a deep learning system. MAIN OUTCOMES AND MEASURES Area under the receiver operating characteristics curve (AUC), sensitivity and specificity for DLS with reference to professional graders. RESULTS From a total of 274 413 fundus images initially obtained from CGSA, 269 601 images passed initial image quality review and were graded for GON. A total of 241 032 images (definite GON 29 865 [12.4%], probable GON 11 046 [4.6%], unlikely GON 200 121 [83%]) from 68 013 patients were selected using random sampling to train the GD-CNN model. Validation and evaluation of the GD-CNN model was assessed using the remaining 28 569 images from CGSA. The AUC of the GD-CNN model in primary local validation data sets was 0.996 (95% CI, 0.995-0.998), with sensitivity of 96.2% and specificity of 97.7%. The most common reason for both false-negative and false-positive grading by GD-CNN (51 of 119 [46.3%] and 191 of 588 [32.3%]) and manual grading (50 of 113 [44.2%] and 183 of 538 [34.0%]) was pathologic or high myopia.CONCLUSIONS AND RELEVANCE Application of GD-CNN to fundus images from different settings and varying image quality demonstrated a high sensitivity, specificity, and generalizability for detecting GON. These findings suggest that automated DLS could enhance current screening programs in a cost-effective and time-efficient manner.

Millions of people worldwide are blinded due to cataract formation. At present the only means of treating a cataract is through surgical intervention. A modern cataract operation involves the creation of an opening in the anterior lens capsule to allow access to the fibre cells, which are then removed. This leaves in place a capsular bag that comprises the remaining anterior capsule and the entire posterior capsule. In most cases, an intraocular lens is implanted into the capsular bag during surgery. This procedure initially generates good visual restoration, but unfortunately, residual lens epithelial cells undergo a wound-healing response invoked by surgery, which in time commonly results in a secondary loss of vision. This condition is known as posterior capsule opacification (PCO) and exhibits classical features of fibrosis, including hyperproliferation, migration, matrix deposition, matrix contraction and transdifferentiation into myofibroblasts. These changes alone can cause visual deterioration, but in a significant number of cases, fibre differentiation is also observed, which gives rise to Soemmering's ring and Elschnig's pearl formation. Elucidating the regulatory factors that govern these events is fundamental in the drive to develop future strategies to prevent or delay visual deterioration resulting from PCO. A range of experimental platforms are available for the study of PCO that range from in vivo animal models to in vitro human cell and tissue culture models. In the current review, we will highlight some of the experimental models used in PCO research and provide examples of key findings that have resulted from these approaches.

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Fibrosis affects multiple organs and is associated with hyperproliferation, cell transdifferentiation, matrix modification and contraction. It is therefore essential to discover the key drivers of fibrotic events, which in turn will facilitate the development of appropriate therapeutic strategies. The lens is an elegant experimental model to study the processes that give rise to fibrosis. The molecular and cellular organization of the lens is well defined and consequently modifications associated with fibrosis can be clearly assessed. Moreover, the avascular and non-innervated properties of the lens allow effective in vitro studies to be employed that complement in vivo systems and relate to clinical data. Using the lens as a model for fibrosis has direct relevance to millions affected by lens disorders, but also serves as a valuable experimental tool to understand fibrosis per se.