Results 211 to 220 of about 1,721,209 (309)

XcepFusion for brain tumor detection using a hybrid transfer learning framework with layer pruning and freezing. [PDF]

Sci Rep
Rastogi D, Johri P, Kadry S, Kim S, Kumar L, Baghela VS, Khan AA.   +6 more
europepmc   +1 more source

Biomimetic Membrane Interface Technologies for Detection and Isolation of CTCs and EVs: Advances and Opportunities in Liquid Biopsy

Advanced Science, EarlyView.
Biomimetic membrane interface engineering constructs functionalized detection platforms by integrating natural cell membranes, synthetic lipids, or hybrid membranes. This strategy effectively reduces background interference and enables efficient target capture and analysis, showing broad applications in circulating tumor cell separation, extracellular ...
Duo Liu, Jie Yu, Jingxue Li, Yixue Chen, Mengle Peng, Yifan Xu, Yongjun Wu, Lihua Ding, Sitian He   +8 more
wiley   +1 more source

Graph-theoretical analysis of EEG-based functional connectivity during emotional experience in virtual reality for emotion recognition. [PDF]

Sci Rep
Jo HJ, Lee MJ, Lee WH.
europepmc   +1 more source

Cellular Identity Crisis: RD3 Loss Fuels Plasticity and Immune Silence in Progressive Neuroblastoma

Advanced Science, EarlyView.
Researchers discovered that therapy‐induced loss of RD3 protein in neuroblastoma triggers a dangerous shift: cancer cells become more stem‐like, invasive, and resistant to treatment while evading immune detection. RD3 loss suppresses antigen presentation and boosts immune checkpoints, creating an immune‐silent environment.
Poorvi Subramanian, Sreenidhi Mohanvelu, Sheeja Aravindan, Afsana Parveen Jahir Hussain, Sivasubramani Narayanan, Sabir Salim, Loganayaki Periyasamy, Natarajan Aravindan   +7 more
wiley   +1 more source

Exploring Quantum-Inspired Encoding Strategies in Neuromorphic Systems for Affective State Recognition. [PDF]

Sensors (Basel)
Wang F, Liang X, Du X.
europepmc   +1 more source

Multimodal Cross‐Attentive Graph‐Based Framework for Predicting In Vivo Endocrine Disruptors

Advanced Science, EarlyView.
A multimodal cross‐attentive graph neural network integrates molecular graphs with androgen and estrogen adverse outcome pathway (AOP)–anchored in vitro assay signals to predict in vivo endocrine disruption. By fusing information on Tier‐1 AOP logits with chemical structures, the framework achieves high accuracy and provides assay‐traceable ...
Eder Soares de Almeida Santos, Gustavo Felizardo Santos Sandes, Artur Christian Garcia da Silva, Holli‐Joi Martin, Eugene N. Muratov, Rodolpho de Campos Braga, Bruno Junior Neves   +6 more
wiley   +1 more source

An AI methodology to reduce training intensity, error rates, and size of neural networks. [PDF]

Front Comput Neurosci
Kobylarz TJA.
europepmc   +1 more source

Beyond Transconductance: Cell‐Polymer Coupling Determines Fidelity in Action Potential Recording via Electrolyte‐Gated Polymer Transistors

Advanced Science, EarlyView.
High electrical performance alone does not guarantee efficient bioelectronic signal transduction. Despite excellent mixed ionic‐electronic conduction, recordings from cardiomyocytes reveal that p(g2T‐TT)‐based OECTs predominantly transduce field potential FP‐like signals due to weak cell‐polymer coupling.
Giulia Zoe Zemignani, Elena Mancinelli, Gabriele Tullii, Aleksandr Khudiakov, Cristiano Bortolotti, Shubham Tanwar, Peter J. Schwartz, Luca Sala, Maria Rosa Antognazza, Mario Caironi, Adrica Kyndiah   +10 more
wiley   +1 more source

SAGE: Spatially Aware Gene Selection and Dual‐View Embedding Fusion for Domain Identification in Spatial Transcriptomics

Advanced Science, EarlyView.
SAGE is a unified framework for spatial domain identification in spatial transcriptomics that jointly models tissue architecture and gene programs. Topic‐driven gene selection (NMF plus classifier‐based scoring) highlights spatially informative genes, while dual‐view graph embedding fuses local expression and non‐local functional relations.
Yi He, Yunpei Xu, Liqing Ding, Hong‐Dong Li, Yaohang Li, Shaokai Wang   +5 more
wiley   +1 more source

A hybrid BiLSTM-CNN approach for intrusion detection for IoT applications. [PDF]

Sci Rep
Sadhwani S, Khan MAH, Muthalagu R, Pawar PM, Suresh K.   +4 more
europepmc   +1 more source