A new deep learning model for predicting IMRT dose distributions for lung cancer with dose masks.

Purpose: 3D U-Net deep neural networks are widely used for predicting radiotherapy dose distributions. However, dose prediction for lung cancer IMRT is limited to conventional radiotherapy, with significant errors in predicting the intermediate and low-dose regions.

Methods: We included a mixed dataset of conventional radiotherapy and simultaneous integrated boost (SIB) radiotherapy with various prescription schemes.

Uncertainty quantification-guided patient-specific quality assurance using Bayesian neural networks based on field complexity features and fluence maps.

Recent advancements in artificial intelligence (AI)-driven prediction models for measurement-based patient-specific quality assurance (PSQA) necessitate uncertainty quantification (UQ) to ensure clinical safety.An uncertainty-guided framework was proposed for PSQA prediction. A classification model utilizing field complexity features and fluence maps was trained to categorize PSQA outcomes.

Bridging Copper-Oxygen-Titanium Bonds for Methanol Photoreforming to Hydrogen on Zero-Dimensional/Two-Dimensional CuO/TiO Heterojunctions.

Solar-driven hydrogen (H) evolution from liquid organic hydrogen carriers (LOHCs) by using rationally designed heterojunctions represents a transformative approach toward carbon neutrality. However, practical implementation is hindered by inefficient charge separation and transport, predominantly due to suboptimal interfacial engineering in conventional heterostructures. Here, dense Cu-O-Ti bonds are created between zero-dimensional (0D) CuO nanocrystals (2-3 nm) and two-dimensional (2D) TiO architectures via a mechanism mediated by unsaturated oxygen atoms, which serve as electron mobility highways to ease excited-state relaxation and recombination.

Observation of nanoparticle coalescence during core-shell metallic nanowire growth in colloids via nanoscale imaging.

The surface morphology and shape of crystalline nanowires significantly influence their functional properties, including phonon transport, electrocatalytic performance, to name but a few. However, the kinetic pathways driving these morphological changes remain underexplored due to challenges in real-space and real-time imaging at single-particle and atomic resolutions. This study investigates the dynamics of shell (Au, Pd, Pt, Fe, Cu, Ni) deposition on AuAg alloy seed nanowires during core-shell formation.

Combined contour error control method for five-axis machine tools based on digital twin.

Contour error is a critical factor influencing machining quality. This paper proposes a combined contour error control method for five-axis machine tools based on digital twin. The proposed method combines pre-compensation implemented in digital twin with feedback control in the real-time controller.

High-Loading Cu Single-Atom Engineering on g-C₃N₄ for Visible-Light CO₂ Photoreduction.

The incorporation of metal single atoms into carbon nitride (CN) has emerged as a promising strategy for photocatalytic CO₂ reduction under visible light. However, achieving high single-atom loading and unraveling the precise role of active metal centers in CO₂ conversion remain formidable challenges. Herein, an ultrasound-assisted coordination exchange strategy is reported that enables the high-loading of Cu single atoms on CN.

A mass-producible macaque model displays a durable Alzheimer-like cognitive deficit and hallmark amyloid-β/tau/neurofilament light chain pathologies.

BackgroundAlzheimer's disease (AD) is the most prevalent neurodegenerative disorder characterized by cognitive deficit and pathological accumulation of amyloid-β (Aβ) and tau proteins. The rodent models have contributed greatly to unravel AD pathogenesis, but these AD models have been shown a modest clinical translational effectiveness.ObjectiveTherefore, developing mass-producible primate AD models is promising for more effective drug development.

Geographical Variation of Diet Composition of in Jiangxi, China Based on DNA Metabarcoding.

Food resources are the fundamental basis for the survival and reproduction of animals. Diet research is the foundation for understanding their ecological habits and is of great significance for evaluating their survival status and carrying out effective protection and management. South China sika deer () is the most endangered subspecies of wild sika deer in China, with a small population and a shrinking distribution area.

Artificial intelligence assisted identification of newborn auricular deformities via smartphone application.

Background: Auricular deformities are common in newborns and require early diagnosis and timely intervention. Several factors highlight the necessity of a machine learning-based diagnostic solution: the high prevalence of these conditions, the narrow time window for effective non-surgical treatment, limited medical resources, and the importance of both physical and mental well-being. This study presents a novel artificial intelligence (AI) model to identify and classify common sub-types of auricle deformities, using photos taken with mobile devices.

Few-layer MoS co-assembly with GO to optimize defect channels and stability of GO membranes for high-performance organic-inorganic separation.

The selective separation of organic compounds and inorganic salts is essential for wastewater recycling in fine chemical industries such as pharmaceuticals and pesticides. Membrane separation technology offers a promising solution. However, conventional organic membranes often face challenges related to precise separation and solvent resistance.

Eye-tracking dataset of endoscopist-AI teaming during colonoscopy: Retrospective and real-time acquisition.

Recent studies have demonstrated that integrating AI into colonoscopy procedures significantly improves the adenoma detection rate (ADR) and reduces the adenoma miss rate (AMR). However, few studies address the critical issue of endoscopist-AI collaboration in real-world settings. Eye-tracking data collection is considered a promising approach to uncovering how endoscopists and AI interact and influence each other during colonoscopy procedures.

GITRL enhances cytotoxicity and persistence of CAR-T cells in cancer therapy.

Chimeric antigen receptor (CAR)-T cell therapy has achieved remarkable clinical success in treating hematological malignancies. However, its clinical efficacy in solid tumors is less satisfactory, partially due to poor in vivo expansion and the limited persistence of CAR-T cells. Here, we demonstrated that the overexpression of GITR ligand enhances the anti-tumor activity of CAR-T cells.

Metallic 1T Phase MoS Nanosheets Covalently Functionalized with BBD Molecules for Enhanced Supercapacitor Performances.

Metallic 1T phase molybdenum disulfide (MoS) is among the most promising electrode materials for supercapacitors, but its capacitance and cyclability remain to be improved to meet the constantly increasing energy storage needs in portable electronics. In this study, we present a strategy, covalent functionalization, which achieves the improvement of capacitance of metallic 1T phase MoS. Covalently functionalized by the modifier 4-bromobenzenediazonium tetrafluoroborate, the metallic MoS membrane exhibits increased interlayer spacing, slightly curled layered architecture, enhanced charge transfer, and improved adsorption capabilities toward electrolyte molecules and ions.

Correction method for ionization chamber dosimetry in flattening filter free radiotherapy based on Monte Carlo simulation.

Background: The clinical use of flattening filter free (FFF) radiotherapy has significantly increased in recent years due to its effective enhancement of dose rates and reduction of scatter dose. A proposal has been made to adjust the incident electron angle of the accelerator to expand the application of FFF beams in areas such as large planning target volumes (PTVs). However, the inherent softening characteristics and non-uniformity of lateral dose distribution in FFF beams inevitably lead to increased dosimetry errors, especially for ionization chambers widely used in clinical practice, which may result in serious accidents during FFF radiotherapy.

LGR4 Deficiency Aggravates Skin Inflammation and Epidermal Hyperplasia in Imiquimod-Induced Psoriasis.

Psoriasis is a chronic inflammatory skin disease characterised by inflammatory cell infiltration, keratinocyte hyperproliferation and increased neovascularization. Despite extensive research, the precise mechanisms underlying psoriasis pathology and treatment strategies remain unclear because of a complex aetiology and disease progression. Hence, in this study, we aimed to identify potential therapeutic targets for psoriasis and explore their effects on disease progression.

A StarGAN and transformer-based hybrid classification-regression model for multi-institution VMAT patient-specific quality assurance.

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.

Quantitative texture analysis using machine learning for predicting interpretable pulmonary perfusion from non-contrast computed tomography in pulmonary embolism patients.

Background: Pulmonary embolism (PE) is life-threatening and requires timely and accurate diagnosis, yet current imaging methods, like computed tomography pulmonary angiography, present limitations, particularly for patients with contraindications to iodinated contrast agents. We aimed to develop a quantitative texture analysis pipeline using machine learning (ML) based on non-contrast thoracic computed tomography (CT) scans to discover intensity and textural features correlated with regional lung perfusion (Q) physiology and pathology and synthesize voxel-wise Q surrogates to assist in PE diagnosis.

Methods: We retrospectively collected Tc-labeled macroaggregated albumin Q-SPECT/CT scans from patients suspected of PE, including an internal dataset of 76 patients (64 for training, 12 for testing) and an external testing dataset of 49 patients.

Exploring the impact of network depth on 3D U-Net-based dose prediction for cervical cancer radiotherapy.

Purpose: The 3D U-Net deep neural network structure is widely employed for dose prediction in radiotherapy. However, the attention to the network depth and its impact on the accuracy and robustness of dose prediction remains inadequate.

Methods: 92 cervical cancer patients who underwent Volumetric Modulated Arc Therapy (VMAT) are geometrically augmented to investigate the effects of network depth on dose prediction by training and testing three different 3D U-Net structures with depths of 3, 4, and 5.

Comparative Analysis of Repeatability in CT Radiomics and Dosiomics Features under Image Perturbation: A Study in Cervical Cancer Patients.

This study aims to evaluate the repeatability of radiomics and dosiomics features via image perturbation of patients with cervical cancer. A total of 304 cervical cancer patients with planning CT images and dose maps were retrospectively included. Random translation, rotation, and contour randomization were applied to CT images and dose maps before radiomics feature extraction.

Deep reinforcement learning in radiation therapy planning optimization: A comprehensive review.

Purpose: The formulation and optimization of radiation therapy plans are complex and time-consuming processes that heavily rely on the expertise of medical physicists. Consequently, there is an urgent need for automated optimization methods. Recent advancements in reinforcement learning, particularly deep reinforcement learning (DRL), show great promise for automating radiotherapy planning.

Dynamic look-ahead feedrate scheduling method based on sliding mode velocity control.

In the feedrate scheduling of complex curve direct interpolation, dynamic constraints such as axis acceleration and jerk are related to the actual state of the tool. Most existing methods convert dynamic constraints to velocity constraints at sampling points. However, it cannot guarantee the dynamic constraints are satisfied between sampling points.