Browse Articles

Observation of *N₂H₃ Intermediates by In Situ Electrochemical SERS: New Pathway of Ammonia Oxidation on High-Durability PtIr Catalysts

Eu isotope fractionation and hydrothermal alteration

Electron Donors in the Intertwined Interface Restore Oxy-Substituted Selenides

Ensemble-based sesame disease detection and classification using deep convolutional neural networks (CNN)

Heme-Like {CoNO}⁹, (STTP^•–2){CoNO}⁹, and {CoNO}¹⁰ Complexes Supported by 21-Thiaporphyrin Macrocycle

Depression mediates the association between lipid accumulation products and overactive bladder

Triptycene-Based 2.5-Dimensional Metal–Organic Frameworks: Atomically Accurate Structures and Anisotropic Physical Properties from Hydrogen-Bonding Bridged Protonated Building Units

Exploring associations between breast tumor inflammatory gene expression and mammographic calcifications and masses in a community-based population

Mechanical-Bond-Enabled Highly Efficient Charge Separation in a Light-Harvesting Hetero[2]Catenane

Correction: Risk assessment of Escherichia coli O157:H7 along the farm-to-fork fresh-cut romaine lettuce supply chain

Breaking a Lewis Acidity Trend for Rare Earths by Excited State Quenching

Invulnerability bias in perceptions of artificial intelligence’s future impact on employment

Topochemical Reaction Involving Double-to-Single Layer Conversion: Mo₃Ta₂O₁₀N with a Kagomé Lattice

Efficacy and safety of lateral approach laparoscopic spleen-preserving distal pancreatectomy: a multicenter retrospective cohort study

Entropy-Driven Structural Evolution in Ceramic Oxides

Development of a deep learning based approach for multi-material decomposition in spectral CT: a proof of principle in silico study

Abstract Conventional approaches to material decomposition in spectral CT face challenges related to precise algorithm calibration across imaged conditions and low signal quality caused by variable object size and reduced dose. In this proof-of-principle study, a deep learning approach to multi-material decomposition was developed to quantify iodine, gadolinium, and calcium in spectral CT. A dual-phase network architecture was trained using synthetic datasets containing computational models of cylindrical and virtual patient phantoms. Classification and quantification performance was evaluated across a range of patient size and dose parameters. The model was found to accurately classify (accuracy: cylinders – 98%, virtual patients – 97%) and quantify materials (mean absolute percentage difference: cylinders – 8–10%, virtual patients – 10–15%) in both datasets. Performance in virtual patient phantoms improved as the hybrid training dataset included a larger contingent of virtual patient phantoms (accuracy: 48% with 0 virtual patients to 97% with 8 virtual patients). For both datasets, the algorithm was able to maintain strong performance under challenging conditions of large patient size and reduced dose. This study shows the validity of a deep-learning based approach to multi-material decomposition trained with in-silico images that can overcome the limitations of conventional material decomposition approaches.

Fully Recyclable and Remarkably Robust Cross-Linked Polyethylene Networks via Direct Free-Radical Copolymerization with Disulfide Dynamic Covalent Bonds

The practical impact of indoor temperature on the productivity of prefabricated construction workers using electroencephalogram data

Interfacial Electric Fields Modulate Redox Reactions in Abiological Coacervates

Air quality prediction-based big data analytics using hebbian concordance and attention-based long short-term memory