Results 191 to 200 of about 934,428 (242)

Foundation Model‐Enabled Multimodal Deep Learning for Prognostic Prediction in Colorectal Cancer with Incomplete Modalities: A Multi‐Institutional Retrospective Study

Advanced Science, EarlyView.
FLARE, a multimodal AI framework, combines pathology slides, radiology scans, and clinical reports to predict colorectal cancer outcomes, even when some tests are missing. Evaluated retrospectively in 1679 patients from four medical centers, it consistently achieved the best prognostic accuracy and clearly separated high‐ and low‐risk groups.
Linhao Qu, Chengsheng Zhang, Yingyong Hou, Feng Tang, Weiqi Sheng, Dan Huang, Zhijian Song   +6 more
wiley   +1 more source

Uncertainty-weighted semi-supervised learning with dynamic entropy masking and Bhattacharyya-regularized loss. [PDF]

Sci Rep
Ghazal MT, Tanha J, Shahi N, Roshan S.
europepmc   +1 more source

The Disordered Region of ASXL1 Acts as an Auto‐Regulator Through Condensation

Advanced Science, EarlyView.
ASXL1's long IDR encodes an electrostatic “basic platform + acidic brake” that autoregulates condensation. Truncation at a clinical hotspot lifts this brake, forming condensates that retarget BRD2, remodel local chromatin accessibility, and impair neutrophil maturation.
Xiao Fang, Qiwei Li, Wenqing Zhang
wiley   +1 more source

From pretraining to privacy: federated ultrasound foundation model with self-supervised learning. [PDF]

NPJ Digit Med
Jiang Y, Feng CM, Ren J, Wei J, Zhang Z, Hu Y, Liu Y, Sun R, Tang X, Du J, Wan X, Xu Y, Du B, Gao X, Wang G, Zhou S, Cui S, Li Z.   +17 more
europepmc   +1 more source

Spatial Profiling Reveals Distinct Molecular and Immune Evolution of Mouse Lung Adenocarcinoma Precancers with or Without Carcinogen Exposure

Advanced Science, EarlyView.
Tumor evolution in lung adenocarcinoma is shaped by genetic alterations and spatial immune dynamics. By integrating whole‐exome sequencing, imaging mass cytometry, and spatial transcriptomics across two mouse models, this study reveals how mutational burden, immune infiltration, and cell–state interactions evolve during early and late carcinogenesis ...
Bo Zhu, Muhammad Aminu, Pingjun Chen, Jian‐Rong Li, Chuanpeng Dong, Chenyang Li, Yanhua Tian, Shao‐Wei Lu, Hong Chen, Chenxi Ma, Xin Hu, Jie Ye, Andrew Y. Liu, Beibei Huang, Frank R. Rojas, Parra Cuentas. Edwin Roger, Ou Shi, Monique B. Nilsson, Alissa Poteete, Khaja B. Khan, Wei Lu, Luisa M. Solis Soto, Junya Fujimoto, Cara Haymaker, Ignacio I. Wistuba, Zhubo Wei, Linghua Wang, Don L. Gibbons, Ken Chen, Alexandre Reuben, Jason M. Schenkel, John V. Heymach, Chao Cheng, Jia Wu, Jianjun Zhang   +34 more
wiley   +1 more source

Single‐Cell Metabolic Imaging and Digital Scoring of Fat Tissue Remodeling by Label‐Free Metabolic Microscopy

Advanced Science, EarlyView.
Mid‐infrared optoacoustic microscopy (MiROM) acquires lipid‐ and protein‐ associated vibrational contrast in intact fat tissue without dyes, preserving native tissue architecture. Through lateral and axial segmentation, MiROM tracks intrinsic intracellular changes during postnatal remodeling. A quantitative spatial analysis tool (Q‐SAT) maps white‐ and
Myeongseop Kim, Constantin Berger, Alexander Wolf, Alina Peteranderl, Martin Klingenspor, Vasilis Ntziachristos, Yongguo Li, Miguel A. Pleitez   +7 more
wiley   +1 more source

Supervised-Learning-Driven Interrogation of Organ-on-a-Chip Quality from Microscopy Images. [PDF]

Chem Bio Eng
George RM, Kenry.
europepmc   +1 more source

MGM as a Large‐Scale Pretrained Foundation Model for Microbiome Analyses in Diverse Contexts

Advanced Science, EarlyView.
We present the Microbial General Model (MGM), a transformer‐based foundation model pretrained on over 260,000 microbiome samples. MGM learns contextualized microbial representations via self‐supervised language modeling, enabling robust transfer learning, cross‐regional generalization, keystone taxa discovery, and prompt‐guided generation of realistic,
Haohong Zhang, Yuli Zhang, Zixin Kang, Jiayun Xiong, Ronghua Yang, Kang Ning   +5 more
wiley   +1 more source

Feedback Recorrection Semantic-Based Image Inpainting Under Semi-Supervised Learning. [PDF]

Sensors (Basel)
Ye X, Tan R, Sui M, Chen H, Ying N.
europepmc   +1 more source

Learned Conformational Space and Pharmacophore Into Molecular Foundational Model

Advanced Science, EarlyView.
The Ouroboros model introduces two orthogonal modules within a unified framework that independently learn molecular representations and generate chemical structures. This design enables flexible optimization strategies for each module and faithful structure reconstruction without prompts or noise.
Lin Wang, Yifan Wu, Hao Luo, Minglong Liang, Yihang Zhou, Cheng Chen, Chris Liu, Jun Zhang, Yang Zhang   +8 more
wiley   +1 more source