从数据分析和研究设计的角度读新论文：数据从哪来、流程怎么走、用了什么工具、哪里值得学。
High-resolution diffusion MRI of rectal cancer ex vivo surgical specimens reveals post-treatment microstructural characteristics of tissue components
直肠癌治疗后离体标本中，扩散MRI指标与组织成分差异相关，可提供常规对比之外的微结构信息。
Multiplexed intravascular molecular imaging using dual-channel near-infrared fluorescence integrated with optical coherence tomography
提出时间调制双通道NIRF/OCT导管系统，抑制通道串扰并同步获取斑块结构与双靶点分子信息。
Diagnostic accuracy of deep learning for microsatellite instability prediction in gastric cancer: A systematic review and meta-analysis
深度学习预测胃癌微卫星不稳定性具有良好诊断准确性，但临床效用仍需前瞻性外部验证。
Dendritic computation for abstract rule-based flexible decision-making.
在小鼠中，听觉皮层神经元树突与胞体分别偏重编码抽象规则和感觉刺激，树突抑制损害选择编码。
Calibration, Uncertainty, and Data Efficiency of Deep Learning Chest Radiograph Classifiers Under Cross-Dataset Distribution Shift: A Multi-Dataset Benchmark
开展胸部X线分类器跨数据集基准评测，显示源数据校准不能稳定迁移，判别能力提升不保证概率可靠。
Near-infrared photochromic miniprotein enables photoacoustic molecular imaging of acute inflammation and intracellular antigens.
开发了微型光开关探针rsmiRFPnano，用于急性炎症与细胞内抗原的活体光声分子成像。
Early detection of gastric cancer using DNA features in red blood cells, with multicenter validation.
红细胞DNA特征分类器在多中心验证中检测胃癌的敏感度为83%-90%，I期为82%-89%。
Invasive interval breast cancer rates after digital breast tomosynthesis plus synthesised mammography versus digital mammography screening (TOSYMA): 24-month follow-up of the multicentre, open-label, randomised, controlled, superiority trial.
断层合成联合合成乳腺摄影组24个月浸润性间期癌发生率数值较低，但主要终点未达统计学显著性。
Spatially tuned localization of interleukins and OX40 agonists enhances synergistic anti-tumor immunity.
在小鼠肿瘤模型中，水凝胶介导的细胞因子与 OX40 激动剂空间定位给药增强了协同抗肿瘤疗效。
Microglia-mediated extracellular matrix disruption drives neuronal dysfunction, motor impairments, and sedation following alcohol abuse.
在小鼠中，小胶质细胞介导的细胞外基质破坏驱动酒精相关神经损伤，敲除其Myd88具有保护作用。
SIMworks-an integrated software suite for quality-controlled augmented quantitative structured illumination microscopy.
开发了SIMworks，整合SIM数据的质量控制、处理与定量分析，降低分析门槛并提升数据可靠性。
Deep learning-enabled screening of chronic kidney disease from echocardiography.
超声心动图深度学习模型可识别慢性肾脏病，在两个独立外部队列中保持稳健表现。
Autonomous labeling of surgical resection margins using a foundation model.
提出虚拟染墨网络VIN，在全切片图像上自动定位手术切面，减少对实体染墨的依赖。