Smartphone-based diabetic macula edema screening with an offline artificial intelligence

BACKGROUND

Diabetic macular edema (DME) is a sight-threatening condition that needs regular examinations and remedies. Optical coherence tomography (OCT) is the most common used examination to evaluate the structure and thickness of the macula, but the software in the OCT machine does not tell the clinicians whether DME exists directly. Recently, artificial intelligence (AI) is expected to aid in diagnosis generation and therapy selection. We thus develop a smartphone-based offline AI system that provides diagnostic suggestions and medical strategies through analyzing OCT images from diabetic patients at the risk of developing DME.

METHODS

DME patients receiving treatments in 2017 at Taipei Veterans General Hospital were included in this study. We retrospectively collected the OCT images of these patients from January 2008 to July 2018. We established the AI model based on MobileNet architecture to classify the OCT images conditions. The confusion matrix has been applied to present the performance of the trained AI model.

RESULTS

Based on the convolutional neural network with the MobileNet model, our AI system achieved a high DME diagnostic accuracy of 90.02%, which is comparable to other AI systems such as InceptionV3 and VGG16. We further developed a mobile-application based on this AI model available at https://aicl.ddns.net/DME.apk.

CONCLUSION

We successful integrated an AI model into the mobile device to provide an offline method to provide the diagnosis for quickly screening the risk of developing DME. With the offline property, our model could help those nonophthalmological healthcare providers in offshore islands or underdeveloped countries.

Human Arm protein lost in epithelial cancers, on chromosome X 1 (ALEX1) gene is transcriptionally regulated by CREB and Wnt/beta-catenin signaling

The aberrant activation of Wnt signaling is a key process in colorectal tumorigenesis. Canonical Wnt signaling controls transcription of target genes via beta-catenin and T-cell factor/lymphoid enhancer factor family transcription factor complex. Arm protein lost in epithelial cancers, on chromosome X 1 (ALEX1) is a novel member of the Armadillo family which has two Armadillo repeats as opposed to more than six repeats in the classical Armadillo family members. Here we examine cis-regulatory elements and trans-acting factors involved in the transcriptional regulation of the ALEX1 gene. Site-directed mutations of a cyclic AMP response element (CRE) and an E-box impaired the basal activity of human ALEX1 promoter in colorectal and pancreatic cancer cell lines. Moreover, overexpression of CRE-binding protein (CREB) increased the ALEX1 promoter activity in these cell lines, whereas knockdown of CREB expression decreased the expression level of ALEX1 mRNA. Interestingly, luciferase reporter analysis and quantitative real-time RT-PCR demonstrated that the ALEX1 promoter was up-regulated in a CRE-dependent manner by continuous activation of Wnt/beta-catenin signaling induced by a glycogen synthase kinase-3 inhibitor and overexpression of beta-catenin. These results indicate that the CRE and E-box sites are essential cis-regulatory elements for ALEX1 promoter activity, and ALEX1 expression is regulated by CREB and Wntk/beta-catenin signaling.