Search

Background: The field of artificial intelligence (AI)‐based patient‐specific quality assurance (PSQA) for volumetric modulated arc therapy (VMAT) faces challenges in terms of developing general models across institutions due to the prevalence of multi‐institution data collection and multivariate heterogeneity. Building a general model that is capable of handling diverse multi‐institution data is critical for enabling large‐scale integration and analysis. Purpose: This study aims to develop a star generative adversarial network (StarGAN) and transformer‐based hybrid classification‐regression PSQA framework to address unification of heterogeneous data from different institutions. Methods: A StarGAN and transformer‐based hybrid classification‐regression model was developed as a general PSQA framework to predict gamma passing rates (GPRs) and classify quality assurance (QA) results as "Pass" or "Fail" at multiple institutions. A total of 1815 VMAT plans were collected from eight institutions to develop the general PSQA framework and perform clinical commissioning and implementation. Among them, 20 independent clinical plans from each of eight institutions, for a total of 160 plans, were used for the clinical commissioning, and 205 new clinical plans from eight institutions were used for clinical implementation. Results: For the 3%/3, 3%/2, and 2%/2 mm gamma criteria, the sensitivity of the proposed PSQA framework with pretraining was 90.13%, 92.03%, and 95.84%, respectively, while the specificity was 76.01%, 76.12%, and 85.34%, respectively. The mean absolute errors (MAEs) of the proposed PSQA framework with pretraining were 1.36%, 2.37%, and 3.96%, respectively, while the root‐mean‐square errors (RMSEs) were 2.31%, 3.89%, and 5.17%, respectively. The results demonstrated visible improvement at multiple institutions. For clinical commissioning, the deviations between the predicted and measured results were all within 3% for 3%/3 and 3%/2 mm at eight institutions. For clinical implementation, all failure plans were correctly identified by the proposed PSQA framework. Conclusions: The general PSQA framework enables diverse clinical data sources to be handled to achieve enhanced model performance and generalizability, and provides a solution to the unification of heterogeneous data from different institutions to construct robust QA models. This approach can be clinically deployed for VMAT QA. [ABSTRACT FROM AUTHOR]

Mercury is the most toxic and harmful heavy metal pollutant, and it is essential to detect and remove mercury from beverages. Inducing the porphyrin molecules into the chitosan structure, a novel membrane sensor tetrakis(4-carboxyphenyl)porphyrin-grafted chitosan fiber membrane (TCPP-CS) was prepared by electrospinning method and applied to recognize Hg2+ contaminant selectively. Compared with other common metal ions (Pb2+, Cu2+, Fe3+, Cr3+, Mg2+, and Zn2+), the colorimetric sensor has specific color development and sensitivity to Hg2+ and the detection limit of the sensor reaches 1 × 10−5 mol·L−1. The response time of the membrane is 5 s, and it can be specifically colored in various pH environments convenient for practical application. Hg2+ resulted in a visual color change of the fiber membrane from brown to yellow-green, indicating a potential interaction between the porphyrin-functionalized chitosan fiber membrane and Hg2+ ions, and the wavelength shift of the UV–visible spectrum can be observed. It has the advantages of simplicity, rapidity, high selectivity, and high sensitivity, providing a new method for removing and detecting heavy metals in traditional Chinese medicine and drinks. [ABSTRACT FROM AUTHOR]

Polyethersulfone-sulfonated polyethersulfone (PES-SPES)/NaY zeolite/nylon sandwich structure membranes were prepared and used to adsorb Cu2+ from water. The adsorption kinetics, adsorption isotherm, dynamic adsorption experiment, and reusability were discussed. The experimental data showed that the Langmuir isotherm model, Dubinin–Radushkevich (D-R) isotherm model, and the pseudo-first-order kinetic model can well represent the adsorption of Cu2+ on the membrane, indicating an ion exchange mechanism, with the maximum adsorption capacity of 111.25 mg·g−1. Repeatability experiments show that the sandwich film still has good adsorption performance after five times of adsorption and desorption. The as-prepared membrane showed considerable separation performance in removing Cu2+ from aspirin solution, providing a feasible method to remove heavy metals from drugs. [ABSTRACT FROM AUTHOR]