PurposeTo evaluate the clinical utility of dual energy spectral CT (DEsCT) in staging and characterizing gastric cancers.Materials and Methods96 patients suspected of gastric cancers underwent dual-phasic scans (arterial phase (AP) and portal venous phase (PP)) with DEsCT mode. Three types of images were reconstructed for analysis: conventional polychromatic images, material-decomposition images, and monochromatic image sets with photon energies from 40 to 140 keV. The polychromatic and monochromatic images were compared in TNM staging. The iodine concentrations in the lesions and lymph nodes were measured on the iodine-based material-decomposition images. These values were further normalized against that in aorta and the normalized iodine concentration (nIC) values were statistically compared. Results were correlated with pathological findings.ResultsThe overall accuracies for T, N and M staging were (81.2%, 80.0%, and 98.9%) and (73.9%, 75.0%, and 98.9%) determined with the monochromatic images and the conventional kVp images, respectively. The improvement of the accuracy in N-staging using the keV images was statistically significant (p<0.05). The nIC values between the differentiated and undifferentiated carcinoma and between metastatic and non-metastatic lymph nodes were significantly different both in AP (p = 0.02, respectively) and PP (p = 0.01, respectively). Among metastatic lymph nodes, nIC of the signet-ring cell carcinoma were significantly different from the adenocarcinoma (p = 0.02) and mucinous adenocarcinoma (p = 0.01) in PP.ConclusionThe monochromatic images obtained with DEsCT may be used to improve the N-staging accuracy. Quantitative iodine concentration measurements may be helpful for differentiating between differentiated and undifferentiated gastric carcinoma, and between metastatic and non-metastatic lymph nodes.

The computational prediction of interactions between drugs and targets is a standing challenge in drug discovery. State-of-the-art methods for drug-target interaction prediction are primarily based on supervised machine learning with known label information. However, in biomedicine, obtaining labeled training data is an expensive and a laborious process. This paper proposes a semi-supervised generative adversarial networks (GANs)-based method to predict binding affinity. Our method comprises two parts, two GANs for feature extraction and a regression network for prediction. The semisupervised mechanism allows our model to learn proteins drugs features of both labeled and unlabeled data. We evaluate the performance of our method using multiple public datasets. Experimental results demonstrate that our method achieves competitive performance while utilizing freely available unlabeled data. Our results suggest that utilizing such unlabeled data can considerably help improve performance in various biomedical relation extraction processes, for example, Drug-Target interaction and protein-protein interaction, particularly when only limited labeled data are available in such tasks. To our best knowledge, this is the first semi-supervised GANs-based method to predict binding affinity.

Aims:  The aim of this study was to develop an effective method for the identification of Vibrio harveyi based on using the toxR gene as a taxonomic marker. Methods and Results:  Primers for the toxR gene were designed for specificity to V. harveyi, and incorporated in a polymerase chain reaction (PCR). The results of the PCR, which took <5 h from DNA extraction to amplification, revealed positive amplification of the toxR gene fragment in 20 V. harveyi isolates including type strains, whereas DNA from 23 other Vibrionaceae type strains and 13 Vibrio parahaemolyticus strains were negative. The detection limit of the PCR was 4.0 × 103 cells ml−1. In addition, the technique enabled the recognition of V. harveyi from diseased fish. Conclusions:  The PCR was specific and sensitive, enabling the identification of V. harveyi within 5 h. Significance and Impact of the Study:  The PCR allowed the rapid and sensitive detection of V. harveyi.

Accurate tumor, node, and metastasis (TNM) staging, especially N staging in gastric cancer or the metastasis on lymph node diagnosis, is a popular issue in clinical medical image analysis in which gemstone spectral imaging (GSI) can provide more information to doctors than conventional computed tomography (CT) does. In this paper, we apply machine learning methods on the GSI analysis of lymph node metastasis in gastric cancer. First, we use some feature selection or metric learning methods to reduce data dimension and feature space. We then employ the K-nearest neighbor classifier to distinguish lymph node metastasis from nonlymph node metastasis. The experiment involved 38 lymph node samples in gastric cancer, showing an overall accuracy of 96.33%. Compared with that of traditional diagnostic methods, such as helical CT (sensitivity 75.2% and specificity 41.8%) and multidetector computed tomography (82.09%), the diagnostic accuracy of lymph node metastasis is high. GSI-CT can then be the optimal choice for the preoperative diagnosis of patients with gastric cancer in the N staging.