Weakly Supervised Learning of 3D Deep Network for Neuron Reconstruction. [PDF]
Huang Q +10 more
europepmc +1 more source
Femtosecond‐Laser‐Induced Physical Unclonable Random Maze Structure for Storage‐Free Encryption
Femtosecond‐laser‐induced gold random maze structures serve as multimodal physical unclonable functions for storage‐free encryption. Their stochastic optical, electrical, and Raman responses are generated by plasmon‐assisted Marangoni formation and converted into AES‐compatible keys without permanent secret‐key storage, offering a portable route toward
Shiru Jiang +6 more
wiley +1 more source
Extracting interpretable features for pathologists using weakly supervised learning to predict p16 expression in oropharyngeal cancer. [PDF]
Adachi M +10 more
europepmc +1 more source
Weakly-supervised learning for lung carcinoma classification using deep learning. [PDF]
Kanavati F +9 more
europepmc +1 more source
This work presents a CRISPR‐based, ultrasensitive multiplex protein detection array capable of simultaneously analyzing six plasma biomarkers associated with Alzheimer's disease (AD). By integrating antibody‐mediated signal transduction, recombinase polymerase amplification, and spatially encoded CRISPR‐Cas12a, the system achieves detection sensitivity
Liding Zhang +9 more
wiley +1 more source
3D‐Printed Magnetoelectronics for Interactive Appliances and Self‐Aware 4D‐Printed Mechatronics
3D‐printed magnetoelectronics integrate high‐performance magnetic field sensing directly into complex structural components. Flexible spring and cross‐shaped sensors exhibit giant magnetoimpedance and 3D Hall sensing for vector field reconstruction. Applications include smart‐home switches, robotic joysticks, volumetric magnetometers, and self‐aware 4D‐
Eduardo Sergio Oliveros‐Mata +5 more
wiley +1 more source
Pressure‐Induced Drift Artifacts in Stretchable Liquid Metal ThinFilm Electrocardiogram Electrodes
A stretchable LM electrode integrated with a strain sensor enables in situ quantitative investigation of drift artifact and skin deformation. This reveals the significance of pressure‐induced drift artifact and its intimate relationship with the skin potential model.
Ding Li +13 more
wiley +1 more source
Weakly supervised learning for subcutaneous edema segmentation of abdominal CT using pseudo-labels and multi-stage nnU-Nets. [PDF]
Bhadra S, Liu J, Summers RM.
europepmc +1 more source
Robust Semi-Supervised Traffic Sign Recognition via Self-Training and Weakly-Supervised Learning. [PDF]
Nartey OT +4 more
europepmc +1 more source
Mechanistic Understanding of Protein–MOF Integration Through Surfactant‐Driven Interfacial Design
This study reveals how surfactant‐driven interfacial design governs the assembly and stability of protein@MOF composites. Using lipid‐based nonionic surfactants, we modulate protein–MOF interactions to improve encapsulation efficiency, MOF crystallization, and catalytic performance.
Ehsan Rashidniyaghi +4 more
wiley +1 more source

