ROFI: a deep learning-based ophthalmic sign-preserving and reversible patient face anonymizer [0.03%]
基于深度学习的保护眼科符号且可逆的眼科患者面部匿名化方法（ROFI）
Yuan Tian,Min Zhou,Yitong Chen et al.
Yuan Tian et al.
Patient face images provide a convenient mean for evaluating eye diseases, while also raising privacy concerns. Here, we introduce ROFI, a deep learning-based privacy protection framework for ophthalmology. Using weakly supervised learning ...
Fetal gestational age estimation using artificial intelligence on non-targeted ultrasound images and video [0.03%]
基于非目标超声图像和视频的人工智能胎儿胎龄估算方法
Martin Benson,Sacha Walton,Tom Hartley et al.
Martin Benson et al.
We developed a deep learning model trained on over two million ultrasound images from 78,531 pregnancies from Australia, India, and the UK to estimate gestational age (GA) directly from any fetal ultrasound image, regardless of orientation....
PlaqueCap: lesion-centered captioning of atherosclerotic plaques in intravascular ultrasound using vision-language models and prompt injection [0.03%]
基于视觉语言模型和提示注入的血管内超声图像动脉粥样硬化斑块病变中心描述
Guoqiang Ren,Ming Hou,Xiaoping Yang et al.
Guoqiang Ren et al.
Accurate characterization of atherosclerotic plaques in intravascular ultrasound (IVUS) imaging is essential for evaluating coronary artery disease and guiding clinical interventions. Traditional methods rely on handcrafted features and rul...
The explainable AI dilemma under knowledge imbalance in specialist AI for glaucoma referrals in primary care [0.03%]
知识不平衡下的可解释人工智能困境：初级保健中青光眼转诊的专科人工智能问题
Catalina Gomez,Ruolin Wang,Katharina Breininger et al.
Catalina Gomez et al.
Primary eye care providers refer glaucoma patients using their clinical experience and context. Specialized Artificial Intelligence (AI) excels in referrals trained on clinical data but relies on assumptions that may not hold in practice. T...
Natural language processing techniques to detect delirium in hospitalized patients from clinical notes: a systematic review [0.03%]
用于从住院患者临床记录中检测谵妄的自然语言处理技术系统评价研究
Ravi Shankar,Janani Kannan,Yih Hng Tan et al.
Ravi Shankar et al.
Delirium affects 50% of hospitalized older adults and 80% of ICU patients, yet detection rates are as low as 20-30% with traditional methods. Natural language processing (NLP) offers potential for automated detection from clinical notes. We...
Diagnosis of cardiac conditions from 12-lead electrocardiogram through natural language supervision [0.03%]
基于自然语言监督的12导联心电图心脏疾病诊断
Xue Zhou,Tianhui Li,Hiromasa Hayama et al.
Xue Zhou et al.
Current AI approaches for cardiac diagnosis require condition-specific supervised learning with extensive labeled datasets, leading to fundamental scalability barriers. We developed an ECG-CLIP model, applying contrastive multimodal learnin...
Systematic review of dynamically tailored eHealth interventions targeting physical activity and healthy diet in chronic disease [0.03%]
针对慢性病人群的动态数字化健康干预措施系统性回顾：以促进身体活动和健康饮食为目标
E A G Hietbrink,C Lansink,G D Laverman et al.
E A G Hietbrink et al.
This systematic review synthesized 61 dynamically tailored eHealth interventions for chronic disease management from 117 papers. Tailoring strategies varied in scope and complexity, with most targeting physical activity (87%) and nutrition ...
Network meta analysis of contributions by different healthcare practitioners in digital self care for hypertension [0.03%]
系统评价和荟萃分析：不同医疗保健人员在高血压数字自我管理中的作用
Xiaoyan Ni,Hui Xue,Lijun Fan et al.
Xiaoyan Ni et al.
Digital health interventions (DHIs) targeting blood pressure (BP) control were more effective in patient self-care than usual care (UC). However, the relative contribution of DHIs involving different healthcare practitioners (HCPs) towards ...
Deep learning model for assessing survival benefits in hepatocellular carcinoma patients undergoing intra-arterial therapies based on proliferative subtype [0.03%]
基于增殖亚型的肝细胞癌患者经动脉治疗生存获益的深度学习模型评估
Fei Cao,Chao An,Shaolong Li et al.
Fei Cao et al.
The proliferative hepatocellular carcinoma (HCC) subtype is associated with aggressive disease and poor prognosis, yet it remains challenging to identify non-invasively. This retrospective multicenter study developed a multitask deep learni...
PathOrchestra: a comprehensive foundation model for computational pathology with over 100 diverse clinical-grade tasks [0.03%]
PathOrchestra：一种计算病理学基础模型，涵盖超过100种多样化的临床级任务
Fang Yan,Jianfeng Wu,Jiawen Li et al.
Fang Yan et al.
The complexity and variability of high-resolution pathological images present significant challenges in computational pathology. While AI-driven pathology foundation models have advanced the field, they require large-scale datasets, substan...