Interpretable integration of SEM and SVM for reliable thyroid nodule classification [0.03%]
可解释的SEM和SVM融合方法及其在甲状腺结节分类中的应用
Mustafa Arif,Yoshiyasu Takefuji
Mustafa Arif
Can one model fit all? Evaluating foundation models for time series forecasting across clinical medicine [0.03%]
万能模型真的存在吗？跨临床医学的时间序列预测通用基础模型评估
Gernot Pucher,Amin Dada,Aurel Agbodoyetin et al.
Gernot Pucher et al.
Artificial intelligence (AI) is increasingly integrated into clinical medicine, with foundation models emerging as an alternative to task-specific models for forecasting longitudinal healthcare data. These models, pre-trained on large datas...
Self-tuned healthy homogeneous core: Addressing heterogeneities in biomedical datasets [0.03%]
自我调节健康同质核心：解决生物医学数据集中的异质性问题
Abhidnya Patharkar,Yutong Wen,Jiajing Huang et al.
Abhidnya Patharkar et al.
Heterogeneity within healthy biomedical populations can degrade disease-classification performance by distorting the decision boundary between healthy and diseased cohorts. In this study, the healthy cohort is decomposed into two subtypes: ...
Deep learning for predicting cardiac procedure outcomes: A scoping review of recent advances [0.03%]
深度学习在预测心脏手术结果中的应用：近期进展综述
Susanne Jauhiainen,Ilkka Rautiainen,Tommi Vasankari et al.
Susanne Jauhiainen et al.
Accurate prediction of outcomes after cardiac procedures is critical for personalised decision-making and risk stratification. While machine learning (ML) has shown promise in this domain, most prior studies rely on traditional ML methods t...
Contrastive adapter training and consensus knowledge distillation for multi-source-free domain adaptation in skin cancer diagnosis [0.03%]
用于皮肤癌诊断的多源无监督领域适应的对比适配器训练和共识知识蒸馏方法
Ali Abedi,Q M Jonathan Wu,Ning Zhang et al.
Ali Abedi et al.
Skin cancer diagnosis, particularly the differentiation of melanoma from benign nevi, is a vital yet challenging task due to the visual similarity between lesions. Although deep learning models such as convolutional neural networks (CNNs) a...
Whitening black boxes: Interpretable and explainable DL-based systems for trustworthy healthcare [0.03%]
使黑盒变白：用于可信医疗的可解释深度学习系统
Antonio Lo Faro,Yves Grandvalet,Luca Ulrich et al.
Antonio Lo Faro et al.
Artificial intelligence (AI), and specifically deep learning (DL) models, are rapidly gaining traction in healthcare to analyze complex medical images and support clinical decision-making. However, DL models are often considered black boxes...
Artificial intelligence based techniques for brain tumor analysis: A systematic review [0.03%]
基于人工智能的脑肿瘤分析技术系统综述
Oluwabukola G Adegboro,Julia Dietlmeier,Noel E O&#x;Connor et al.
Oluwabukola G Adegboro et al.
Brain tumors are formed when abnormal cells grow within the brain or its surrounding tissues. Approximately 400 people in Ireland receive a primary brain tumor diagnosis each year. In the US, this number increases to almost 90,000 individua...
Uncertainty quantification framework for AI-based survival models: Application to lung cancer prognosis in older adults for informed decision-making [0.03%]
基于人工智能的生存模型不确定性量化框架：在老年人肺癌预后中的应用以辅助决策制定
Dahhay Lee,Thi-Ngoc Tran,Jonghyeok Jeong et al.
Dahhay Lee et al.
Reliable prediction is critical for prognosis communication and informed decision-making, yet remains challenging for cancer patients-especially older adults with non-small cell lung cancer (NSCLC)-due to the uncertainty inherent in model-b...
Annotator reliability and probabilistic consensus for semantic segmentation in digital pathology [0.03%]
数字病理学中语义分割的注释可靠性和概率共识
Laura Gálvez Jiménez,Christine Decaestecker
Laura Gálvez Jiménez
In medical image segmentation and its semantic variant, annotations from multiple experts, when available, are used to generate consensus labels for training machine learning models. However, the annotator consistency is generally not captu...
A critical perspective on finite sample conformal prediction theory in medical applications [0.03%]
医学应用中有限样本的符合性预测理论批判角度透视
Klaus-Rudolf Kladny,Bernhard Schölkopf,Lisa Koch et al.
Klaus-Rudolf Kladny et al.
Machine learning (ML) is transforming healthcare, but safe clinical decisions demand reliable uncertainty estimates that standard ML models fail to provide. Conformal prediction (CP) is a popular tool that allows users to turn heuristic unc...