Ultrasensitive and on-site eDNA detection for the monitoring of crown-of-thorns starfish densities at the pre-outbreak stage using an electrochemical biosensor.

The coral reef crisis has significantly intensified over the last decades, mainly due to severe outbreaks of crown-of-thorns starfish (COTS). Current ecological monitoring has failed to detect COTS densities at the pre-outbreak stage, thus preventing early intervention. In this work, we developed an effective electrochemical biosensor modified by a MoO2/C nanomaterial, as well as a specific DNA probe that could detect trace COTS environmental DNA (eDNA) at a lower detection limit (LOD = 0.147 ng/µL) with excellent specificity. The reliability and accuracy of the biosensor were validated against the standard methods by an ultramicro spectrophotometer and droplet digital PCR (p > 0.05). The biosensor was then utilized for the on-site analysis of seawater samples from SYM-LD and SY sites in the South China Sea. For the SYM-LD site suffering an outbreak, the COTS eDNA concentrations were 0.33 ng/µL (1 m, depth) and 0.26 ng/µL (10 m, depth), respectively. According to the ecological survey, the COTS density was 500 ind/hm2 at the SYM-LD site, verifying the accuracy of our measurements. At the SY site, COTS eDNA was also detected at 0.19 ng/µL, but COTS was not found by the traditional survey. Hence, larvae were possibly present in this region. Therefore, this electrochemical biosensor could be used to monitor COTS populations at the pre-outbreak stages, and potentially serve as a revolutionary early warning method. We will continue to improve this method for picomolar or even femtomolar detection of COTS eDNA.

High Accuracy of Convolutional Neural Network for Evaluation of Helicobacter pylori Infection Based on Endoscopic Images: Preliminary Experience.

OBJECTIVES: Application of artificial intelligence in gastrointestinal endoscopy is increasing. The aim of the study was to examine the accuracy of convolutional neural network (CNN) using endoscopic images for evaluating Helicobacter pylori (H. pylori) infection. METHODS: Patients who received upper endoscopy and gastric biopsies at Sir Run Run Shaw Hospital (January 2015-June 2015) were retrospectively searched. A novel Computer-Aided Decision Support System that incorporates CNN model (ResNet-50) based on endoscopic gastric images was developed to evaluate for H. pylori infection. Diagnostic accuracy was evaluated in an independent validation cohort. H. pylori infection was defined by the presence of H. pylori on immunohistochemistry testing on gastric biopsies and/or a positive 13C-urea breath test. RESULTS: Of 1,959 patients, 1,507 (77%) including 847 (56%) with H. pylori infection (11,729 gastric images) were assigned to the derivation cohort, and 452 (23%) including 310 (69%) with H. pylori infection (3,755 images) were assigned to the validation cohort. The area under the curve for a single gastric image was 0.93 (95% confidence interval [CI] 0.92-0.94) with sensitivity, specificity, and accuracy of 81.4% (95% CI 79.8%-82.9%), 90.1% (95% CI 88.4%-91.7%), and 84.5% (95% CI 83.3%-85.7%), respectively, using an optimal cutoff value of 0.3. Area under the curve for multiple gastric images (8.3 ± 3.3) per patient was 0.97 (95% CI 0.96-0.99) with sensitivity, specificity, and accuracy of 91.6% (95% CI 88.0%-94.4%), 98.6% (95% CI 95.0%-99.8%), and 93.8% (95% CI 91.2%-95.8%), respectively, using an optimal cutoff value of 0.4. DISCUSSION: In this pilot study, CNN using multiple archived gastric images achieved high diagnostic accuracy for the evaluation of H. pylori infection.