Background: Infection with Trichomonas vaginalis can lead to cervicitis, urethritis, pelvic inflammatory disease, prostatitis and perinatal complications and increased risk of HIV transmission. Here, we used an RPA-based CRISPR-Cas12a assay system in combination with a lateral flow strip (LFS) (referred to as RPA-CRISPR-Cas12a) to establish a highly sensitive and field-ready assay and evaluated its ability to detect clinical samples. Methods: We developed a one-pot CRISPR-Cas12a combined with RPA-based field detection technology for T. vaginalis, chose actin as the target gene to design crRNA and designed RPA primers based on the crRNA binding site. The specificity of the method was demonstrated by detecting genomes from nine pathogens. To improve the usability and visualize the RPA-CRISPR-Cas12a assay results, both fluorescence detection and LFS readouts were devised. Results: The RPA-CRISPR-Cas12a assay platform was completed within 60 min and had a maximum detection limit of 1 copy/µl and no cross-reactivity with Candida albicans, Mycoplasma hominis, Neisseria gonorrhoeae, Escherichia coli, Cryptosporidium parvum, G. duodenalis or Toxoplasma gondii after specificity validation. Thirty human vaginal secretions were tested by RPA-CRISPR-Cas12a assays, and the results were read by a fluorescent reporter and LFS biosensors and then compared to the results from nested PCR detection of these samples. Both RPA-CRISPR-Cas12a assays showed 26.7% (8/30) T. vaginalis-positive samples and a consistency of 100% (8/8). The RPA-CRISPR-Cas12a assays had a higher sensitivity than nested PCR (only seven T. vaginalis-positive samples were detected). Conclusions: The T. vaginalis RPA-CRISPR-Cas12a assay platform in this study can be used for large-scale field testing and on-site tests without the need for trained technicians or costly ancillary equipment. Graphical

Compared to magnetic resonance imaging (MRI) and X-ray computed tomography (CT), ultrasound imaging is safer, faster, and more widely applicable. However, the use of conventional ultrasound in transcranial brain imaging for adults is predominantly hindered by the high acoustic impedance contrast between the skull and soft tissue. This study introduces a 3D AI algorithm, Brain Imaging Full Convolution Network (BIFCN), combining waveform modeling and deep learning for precise brain ultrasound reconstruction. We constructed a network comprising one input layer, four convolution layers, and one pooling layer to train our algorithm. In the simulation experiment, the Pearson correlation coefficient between the reconstructed and true images was exceptionally high. In the laboratory, the results showed a slightly lower but still impressive coincidence degree for 3D reconstruction, with pure water serving as the initial model and no prior information required. The 3D network can be trained in 8 h, and 10 samples can be reconstructed in just 12.67 s. The proposed 3D BIFCN algorithm provides a highly accurate and efficient solution for mapping wavefield frequency domain data to 3D brain models, enabling fast and precise brain tissue imaging. Moreover, the frequency shift phenomenon of blood may become a hallmark of BIFCN learning, offering valuable quantitative information for whole-brain blood imaging.

Well integrity evaluation is of great significance to the production life and productivity of oil and gas wells as well as the protection of reservoir layers. However, traditional sonic logging technology has been unable to meet the current requirement for evaluating unconventional oil and gas resources. For instance, it falls short when it comes to detecting cementing quality between the cement and formation as well as achieving a quantitative assessment of annulus. In addition, factors such as mud invasion and wellbore damage have the potential to compromise the integrity of the cement sheath and lead to radial alteration in the medium in the wellbore, which can affect cementing quality. To address these issues, a novel approach based on deep learning is proposed to reconstruct slowness models from wellbore data using a fully connected neural network (FCNN) to evaluate the cementing quality. This interpretation workflow requires forward modeling with the 3D dyadic Green’s function to explore borehole acoustic signals and thus generate training and test data sets. Afterward, the spatial feature maps are learned to reconstruct the slowness models by using all the wellbore data. In addition, the Real-enhanced super-resolution generative adversarial networks (ESRGAN) method is applied to borehole imaging to further improve the preceding inversion. The inversion results regarding the slowness value, wellbore structure, and interface are more consistent with the true model. Finally, the image pixels are optimized using the thresholding method, leading to an image of superior quality in terms of sharpness and detail compared with previous results. This research reveals that the FCNN-based method can effectively invert the radial profile of slowness around the wellbore from monopole sonic logging data, and the Real-ESRGAN method can further enhance the imaging results to better approximate the true models. This method also has been applied to realistic borehole scenario models, demonstrating its feasibility.