Development and evaluation of two rapid lateral flow assays for on-site detection of African swine fever virus.

Introduction: African swine fever (ASF) is a lethal and highly contagious transboundary animal disease with the potential for rapid international spread. In the absence of a widely available and definitively proven vaccine, rapid and early detection is critical for ASF control. The quick and user-friendly lateral flow assay (LFA) can easily be performed by following simple instructions and is ideal for on-site use. This study describes the development and validation of two LFAs for the rapid detection of ASF virus (ASFV) in pig serum. Methods: The highly immunogenic antigens (p30 and p72) of ASFV Georgia 2007/1 (genotype II) were expressed in plants (Nicotiana benthamiana) and were used to immunize BALB/c mice to generate specific monoclonal antibodies (mAbs) against the p30 and p72 proteins. mAbs with the strongest binding ability to each protein were used to develop p30_LFA and p72_LFA for detecting the respective ASFV antigens. The assays were first evaluated using a spike-in test by adding the purified p30 or p72 protein to a serum sample from a healthy donor pig. Further validation of the tests was carried out using serum samples derived from experimentally infected domestic pigs, field domestic pigs, and feral pigs, and the results were compared with those of ASFV real-time PCR. Results: p30_LFA and p72_LFA showed no cross-reaction with common swine viruses and delivered visual results in 15 min. When testing with serially diluted proteins in swine serum samples, analytical sensitivity reached 10 ng/test for p30_LFA and 20 ng/test for p72_LFA. Using real-time PCR as a reference, both assays demonstrated high sensitivity (84.21% for p30_LFA and 100% for p72_LFA) with experimentally ASFV-infected pig sera. Specificity was 100% for both LFAs using a panel of PBS-inoculated domestic pig sera. Excellent specificity was also shown for field domestic pig sera (100% for p30_LFA and 93% for p72_LFA) and feral pig sera (100% for both LFAs). Conclusion: The results obtained in this study suggest that p30_LFA and p72_LFA hold promise as rapid, sensitive, user-friendly, and field-deployable tools for ASF control, particularly in settings with limited laboratory resources.

Differentiating malignant and benign eyelid lesions using deep learning.

Artificial intelligence as a screening tool for eyelid lesions will be helpful for early diagnosis of eyelid malignancies and proper decision-making. This study aimed to evaluate the performance of a deep learning model in differentiating eyelid lesions using clinical eyelid photographs in comparison with human ophthalmologists. We included 4954 photographs from 928 patients in this retrospective cross-sectional study. Images were classified into three categories: malignant lesion, benign lesion, and no lesion. Two pre-trained convolutional neural network (CNN) models, DenseNet-161 and EfficientNetV2-M architectures, were fine-tuned to classify images into three or two (malignant versus benign) categories. For a ternary classification, the mean diagnostic accuracies of the CNNs were 82.1% and 83.0% using DenseNet-161 and EfficientNetV2-M, respectively, which were inferior to those of the nine clinicians (87.0-89.5%). For the binary classification, the mean accuracies were 87.5% and 92.5% using DenseNet-161 and EfficientNetV2-M models, which was similar to that of the clinicians (85.8-90.0%). The mean AUC of the two CNN models was 0.908 and 0.950, respectively. Gradient-weighted class activation map successfully highlighted the eyelid tumors on clinical photographs. Deep learning models showed a promising performance in discriminating malignant versus benign eyelid lesions on clinical photographs, reaching the level of human observers.

Prediction of Submucosal Invasion for Gastric Neoplasms in Endoscopic Images Using Deep-Learning.

Endoscopic resection is recommended for gastric neoplasms confined to mucosa or superficial submucosa. The determination of invasion depth is based on gross morphology assessed in endoscopic images, or on endoscopic ultrasound. These methods have limited accuracy and pose an inter-observer variability. Several studies developed deep-learning (DL) algorithms classifying invasion depth of gastric cancers. Nevertheless, these algorithms are intended to be used after definite diagnosis of gastric cancers, which is not always feasible in various gastric neoplasms. This study aimed to establish a DL algorithm for accurately predicting submucosal invasion in endoscopic images of gastric neoplasms. Pre-trained convolutional neural network models were fine-tuned with 2899 white-light endoscopic images. The prediction models were subsequently validated with an external dataset of 206 images. In the internal test, the mean area under the curve discriminating submucosal invasion was 0.887 (95% confidence interval: 0.849-0.924) by DenseNet-161 network. In the external test, the mean area under the curve reached 0.887 (0.863-0.910). Clinical simulation showed that 6.7% of patients who underwent gastrectomy in the external test were accurately qualified by the established algorithm for potential endoscopic resection, avoiding unnecessary operation. The established DL algorithm proves useful for the prediction of submucosal invasion in endoscopic images of gastric neoplasms.

Characterization of human monoclonal autoantibody Fab fragments against oxidized LDL.

Oxidized low-density lipoprotein (oxLDL) is a key autoantigen in atherosclerosis. The genetic structures and pathogenic roles of autoantibodies against this protein remain to be established. In this study, we cloned several monoclonal IgG autoantibody Fab fragments specific for oxLDL from peripheral blood lymphocytes of atherosclerosis patients, using phage display technology. The sequences of their variable regions were determined at the cDNA level. The closest germline counterparts for the heavy chains belonged to the V(H)3 or V(H)1 family. The sequences and lengths of complementarity-determining regions (CDR)3-V(H) were diverse, and frequent mutations of positively charged amino acids (particularly arginine) over entire V(H) and V(L) sequences were observed. It is proposed that anti-oxLDL autoantibody formation is driven by antigens. Among the Fabs, P2-8 and P3-175 bound to both MDA-LDL and Cu-oxLDL, and inhibited the uptake of oxLDL by macrophages, suggesting the epitope(s) recognized by the Fabs is a part of ligands on oxLDL that is involved in uptake by macrophage scavenger receptor. These human autoantibody Fabs require detailed investigation to ascertain their potential as agents for clinical applications.