Deep Learning Solution for Quantification of Fluorescence Particles on a Membrane.

The detection and quantification of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) virus particles in ambient waters using a membrane-based in-gel loop-mediated isothermal amplification (mgLAMP) method can play an important role in large-scale environmental surveillance for early warning of potential outbreaks. However, counting particles or cells in fluorescence microscopy is an expensive, time-consuming, and tedious task that only highly trained technicians and researchers can perform. Although such objects are generally easy to identify, manually annotating cells is occasionally prone to fatigue errors and arbitrariness due to the operator's interpretation of borderline cases. In this research, we proposed a method to detect and quantify multiscale and shape variant SARS-CoV-2 fluorescent cells generated using a portable (mgLAMP) system and captured using a smartphone camera. The proposed method is based on the YOLOv5 algorithm, which uses CSPnet as its backbone. CSPnet is a recently proposed convolutional neural network (CNN) that duplicates gradient information within the network using a combination of Dense nets and ResNet blocks, and bottleneck convolution layers to reduce computation while at the same time maintaining high accuracy. In addition, we apply the test time augmentation (TTA) algorithm in conjunction with YOLO's one-stage multihead detection heads to detect all cells of varying sizes and shapes. We evaluated the model using a private dataset provided by the Linde + Robinson Laboratory, California Institute of Technology, United States. The model achieved a mAP@0.5 score of 90.3 in the YOLOv5-s6.

Membrane-Based In-Gel Loop-Mediated Isothermal Amplification (mgLAMP) System for SARS-CoV-2 Quantification in Environmental Waters.

Since the COVID-19 pandemic is expected to become endemic, quantification of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) in ambient waters is critical for environmental surveillance and for early detection of outbreaks. Herein, we report the development of a membrane-based in-gel loop-mediated isothermal amplification (mgLAMP) system that is designed for the rapid point-of-use quantification of SARS-CoV-2 particles in environmental waters. The mgLAMP system integrates the viral concentration, in-assay viral lysis, and on-membrane hydrogel-based RT-LAMP quantification using enhanced fluorescence detection with a target-specific probe. With a sample-to-result time of less than 1 h, mgLAMP successfully detected SARS-CoV-2 below 0.96 copies/mL in Milli-Q water. In surface water, the lowest detected SARS-CoV-2 concentration was 93 copies/mL for mgLAMP, while the reverse transcription quantitative polymerase chain reaction (RT-qPCR) with optimal pretreatment was inhibited at 930 copies/mL. A 3D-printed portable device is designed to integrate heated incubation and fluorescence illumination for the simultaneous analysis of nine mgLAMP assays. Smartphone-based imaging and machine learning-based image processing are used for the interpretation of results. In this report, we demonstrate that mgLAMP is a promising method for large-scale environmental surveillance of SARS-CoV-2 without the need for specialized equipment, highly trained personnel, and labor-intensive procedures.

Onsite Graywater Treatment in a Two-Stage Electro-Peroxone Reactor with a Partial Recycle of Treated Effluent.

The efficacy of an uncoupled electro-peroxone (E-peroxone) prototype reactor system for the treatment of synthetic graywater is determined. The two-stage E-peroxone process integrates ozonation with the in situ production of hydrogen peroxide (H2O2) in a first stage reactor before ozone (O3) is converted via the peroxone reaction to a hydroxyl radical (•OH). The two-stage prototype reactor system allows for the generation of H2O2 via cathodic oxygen reduction in the first-stage reactor before mixing with O3 in the second-stage reactor. This approach prevents the degradation of polytetrafluoroethylene (PTFE) coated carbon cathodes by •OH that takes place in a single well-mixed reactor that combines electrochemical peroxide generation with O3. The dosage of H2O2 into the second-stage reactor is optimized to enhance graywater treatment. Under these conditions, the uncoupled E-peroxone system is capable of treating synthetic graywater with an initial chemical oxygen demand (COD0) of 358 mg O2/L, a total organic carbon (TOC0) of 96.9 mg/L, a biochemical oxygen demand (BOD0) of 162 mg O2/L, and a turbidity of 11.2 NTU. The two-stage electro-peroxone system can reduce the initial COD0 by 89%, the TOC0 by 91%, BOD0 by 86%, and the turbidity by 95% after 90 min of treatment. At this performance level, the reactor effluent is acceptable for discharge and for use in nonpotable applications such as toilet-water flushing. A portion of the effluent is recycled back into the first-stage reactor to minimize water consumption. Recycling can be repeated consecutively for four or more cycles, although the time required to achieve the desired H2O2 concentration increased slightly from one cycle to another. The two-stage E-peroxone system is shown to be potentially useful for onsite or decentralized graywater treatment suitable for arid water-sensitive areas.