.png){kind=icon}
返回
Interpretable deep learning enables reliable and label-efficient fluorescence imaging
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.113037.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• AEMS-Net predicts two subcellular structures simultaneously from single-channel imaging. • KAN Attention mechanisms and brightness adaptation layers optimize staining normalization. • Feature decomposition provides a transparent interpretation of subcellular morphology predictions. • Real-time dual-structure imaging achieves 30% quality improvement over conventional deep learning. • Halves the imaging time in mitochondria-microtubule interaction visualization while maintaining accuracy.
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
A first explainable-AI-based workflow integrating forward-forward and backpropagation-trained networks of label-free multiphoton microscopy images to assess human biopsies of rare neuromuscular disease一种基于可解释人工智能的首次工作流程，整合了标签自由多光子显微图像的正向传播和反向传播训练网络，以评估罕见神经肌肉疾病的人类活检样本。
OAAI
OAAI分享收藏Multiplexed and reproducible high content screening of live and fixed cells using Dye Drop.png)
NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏
分享收藏A Review of deep learning methods for denoising of medical low-dose CT images医学低剂量CT图像去噪的深度学习方法综述
PREAI
分享收藏TransGraphNet: A novel network for medical image segmentation based on transformer and graph convolutionTransGraphNet: 一种基于transformer和图卷积的新型医学图像分割网络
PREAI
分享收藏UM-CAM: Uncertainty-weighted multi-resolution class activation maps for weakly-supervised segmentationPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容