BackgroundIn this study, images of 2450 benign thyroid nodules and 2557 malignant thyroid nodules were collected and labeled, and an automatic image recognition and diagnosis system was established by deep learning using the YOLOv2 neural network. The performance of the system in the diagnosis of thyroid nodules was evaluated, and the application value of artificial intelligence in clinical practice was investigated.MethodsThe ultrasound images of 276 patients were retrospectively selected. The diagnoses of the radiologists were determined according to the Thyroid Imaging Reporting and Data System; the images were automatically recognized and diagnosed by the established artificial intelligence system. Pathological diagnosis was the gold standard for the final diagnosis. The performances of the established system and the radiologists in diagnosing the benign and malignant thyroid nodules were compared.ResultsThe artificial intelligence diagnosis system correctly identified the lesion area, with an area under the receiver operating characteristic (ROC) curve of 0.902, which is higher than that of the radiologists (0.859). This finding indicates a higher diagnostic accuracy (p = 0.0434). The sensitivity, positive predictive value, negative predictive value, and accuracy of the artificial intelligence diagnosis system for the diagnosis of malignant thyroid nodules were 90.5%, 95.22%, 80.99%, and 90.31%, respectively, and the performance did not significantly differ from that of the radiologists (p > 0.05). The artificial intelligence diagnosis system had a higher specificity (89.91% vs 77.98%, p = 0.026).ConclusionsCompared with the performance of experienced radiologists, the artificial intelligence system has comparable sensitivity and accuracy for the diagnosis of malignant thyroid nodules and better diagnostic ability for benign thyroid nodules. As an auxiliary tool, this artificial intelligence diagnosis system can provide radiologists with sufficient assistance in the diagnosis of benign and malignant thyroid nodules.

It is highly demanding to design active nanomotors that can move in response to specific signals with controllable rate and direction. A catalysis-driven nanomotor was constructed by designing catalytically and plasmonically active Janus gold nanoparticles (Au NPs), which generate an asymmetric temperature gradient of local solvent surrounding NPs in catalytic reactions. The self-thermophoresis behavior of the Janus nanomotor is monitored from its inherent plasmonic response. The diffusion coefficient of the self-thermophoresis motion is linearly dependent on chemical reaction rate, as described by a stochastic model.

The dynamics of enzymes are directly associated with their functions in various biological processes. Nevertheless, the ability to image motions of single enzymes in a highly parallel fashion remains a challenge. Here, we develop a DNA origami raft-based platform for in-situ real-time imaging of enzyme cascade at the single-molecule level. The motions of enzymes are rationally controlled via different tethering modes on a two-dimensional (2D) supported lipid bilayer (SLB). We construct an enzyme cascade by anchoring catalase on cholesterol-labeled double-stranded (ds) DNA and glucose oxidase on cholesterol-labeled origami rafts. DNA functionalized with cholesterol can be readily incorporated in SLB via the cholesterol-lipid interaction. By using a total internal reflection fluorescence microscope (TIRFM), we record the moving trajectory of fluorophore-labeled single enzymes on the 2D surface: the downstream catalase diffuses freely in SLB, whereas the upstream glucose oxidase is relatively immobile. By analyzing the trajectories of individual enzymes, we find that the lateral motion of enzymes increases in a substrate concentration-dependent manner and that the enhanced diffusion of enzymes can be transmitted via the cascade reaction. We expect that this platform sheds new light on studying dynamic interactions of proteins and even cellular interactions.

A DNA-programmed membrane fusion strategy for directing intracellular delivery of proteins into live cells.