Deep learning models for medical data are typically trained using task specific objectives that encourage representations to collapse onto a small number of discriminative directions. While effective for individual prediction problems, this paradigm underutilizes the rich structure of clinical data and limits the transferability, stability, and interpretability of learned features. In this work, we propose dense feature learning, a representation centric framework that explicitly shapes the linear structure of medical embeddings. Our approach operates directly on embedding matrices, encouraging spectral balance, subspace consistency, and feature orthogonality through objectives defined entirely in terms of linear algebraic properties. Without relying on labels or generative reconstruction, dense feature learning produces representations with higher effective rank, improved conditioning, and greater stability across time. Empirical evaluations across longitudinal EHR data, clinical text, and multimodal patient representations demonstrate consistent improvements in downstream linear performance, robustness, and subspace alignment compared to supervised and self supervised baselines. These results suggest that learning to span clinical variation may be as important as learning to predict clinical outcomes, and position representation geometry as a first class objective in medical AI.
PCRLv2: A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image Analysis
The University of Hong Kong（香港大学）；ShanghaiTech University（上海科技大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）
Preserving clusters and correlations: a dimensionality reduction method for exceptionally high global structure preservation
University of Oslo (UiO)（奥斯陆大学）；Oslo University Hospital (OUS)（奥斯陆大学医院）；University of Lübeck (UzL)（吕贝克大学）；University Medical Center Schleswig-Holstein (UKSH)（石勒苏益格-荷尔斯泰因大学医学中心）；University of Latvia (LU)（拉脱维亚大学）；Tel Aviv University (TAU)（特拉维夫大学）
Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data
Department of Neurosurgery, Qilu Hospital of Shandong University and Institute of Brain and Brain-Inspired Science（齐鲁医院山东大学神经外科和脑科学与脑启发科学研究院）；Department of Neurosurgery, The Affiliated Hospital of Qingdao University（青岛大学附属医院神经外科）；Department of Neurosurgery, Peking Union Medical College Hospital（北京地坛医院神经外科）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；College of Artificial Intelligence, Dalian Maritime University（大连海事大学人工智能学院）；University of Colorado Boulder（科罗拉多大学波尔德分校）；Zhengzhou University（郑州大学）；The University of Hong Kong（香港大学）；Georgia Institute of Technology（佐治亚理工学院）
A Review on Generative AI Models for Synthetic Medical Text, Time Series, and Longitudinal Data
Mälardalen University（梅拉达伦大学）；Servicehälsan Familjeläkare i Västerås AB（韦斯特罗斯家庭医生服务公司）；Turku University of Applied Sciences（图尔库应用科技大学）；Linköping University（林雪平大学）
G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training
Imperial College London（帝国理工学院）；University of Oxford（牛津大学）；École des Ponts（巴黎桥路学校）；EDF R&D（法国电力公司研发中心）；Royal Brompton and Harefield Hospitals（皇家布朗普顿和 Harefield 医院）
CoM$^3$eT: A foundation model for medical image analysis through federated, multidimensional context integration
Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）；RWTH Aachen University（亚琛工业大学）；Medizinische Hochschule Hannover（汉诺威医学院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Charité – Universitätsmedizin Berlin（柏林夏里特医学院）；Freie Universität Berlin（柏林自由大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）
SDCNet: Smoothed Dense-Convolution Network for Restoring Low-Dose Cerebral CT Perfusion
University of Florida（佛罗里达大学）
随着公众对医学成像中累积的辐射暴露引起的潜在癌症风险和健康危害的大量关注，减少基于X射线的医学成像（诸如计算机断层扫描灌注（CTP））中的辐射剂量已经引起了重大的研究兴趣。在本文中，我们采用基于深度卷积神经网络（CNN）的方法，并引入平滑密集卷积神经网络（SDCNet）来从低剂量图像恢复高剂量质量CTP图像。SDCNet由通过跳跃连接级联的子网络块组成，以从成对的低/高剂量CT扫描中推断噪声（差异）。SDCNet可以有效地去除实际低剂量CT扫描中的噪声，提高医学图像的质量。我们评估了数千个CT灌注帧的重建图像去噪和灌注图量化，包括脑血流量（CBF）和脑血容量（CBV）的建议架构。SDCNet在视觉和定量结果方面都实现了高性能，具有良好的计算效率，与最先进的方法相比毫不逊色。\textit{The code is available at \url{https://github.com/cswin/RC-Nets}}。
MedFLIP: Medical Vision-and-Language Self-supervised Fast Pre-Training with Masked Autoencoder
University of Copenhagen（哥本哈根大学）；Tsinghua University（清华大学）；Shanghai Medical Image Insights（上海医学影像洞察）；Harvard University（哈佛大学）；University of Waterloo（滑铁卢大学）
Sparse cubical complexes for efficient topology-preservation in image data
Weill Cornell Medicine（威尔康奈尔医学院）；Technical University of Munich（慕尼黑工业大学）；Imperial College London（伦敦帝国理工学院）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Cornell Tech（康奈尔科技校区）；Munich Data Science Institute（慕尼黑数据科学研究所）
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
University of Science Technology of China（中国科学技术大学）；University of Maryland College Park（马里兰大学帕克分校）；JD Explore Academy（京东探索研究院）；The University of Sydney（悉尼大学）
