检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Feola, Francesco Di Tronchin, Lorenzo Soda, Paolo Department of Radiation Sciences Umeå University Umeå Sweden Research Unit of Computer Systems and Bioinformatics Campus Bio-Medico University of Rome Rome Italy

The current deep learning approaches for low-dose CT denoising can be divided into paired and unpaired methods. The former involves the use of well-paired datasets, whilst the latter relaxes this constraint. The large availability of unpaired datasets has raised the interest in deepening unpaired denoising strategies that, in turn, need for robust evaluation techniques going beyond the qualitative evaluation. To this end, we can use quantitative image quality assessment scores that we divided into two categories, i.e., paired and unpaired measures. However, the interpretation of unpaired metrics is not straightforward, also because the consistency with paired metrics has not been fully investigated. To cope with this limitation, in this work we consider 15 paired and unpaired scores, which we applied to assess the performance of low-dose CT denoising. We perform an in-depth statistical analysis that not only studies the correlation between paired and unpaired metrics but also within each category. This brings out useful guidelines that can help researchers and practitioners select the right measure for their applications. © 2023, CC BY-NC-SA.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Not Another Imputation Method: A Transformer-Based Model for Missing Values in Tabular Datasets

SSRN

引用

SSRN 2025年

作者： Caruso, Camillo Maria Soda, Paolo Guarrasi, Valerio Research Unit of Computer Systems and Bioinformatics Department of Engineering Università Campus Bio-Medico di Roma Roma Italy Department of Diagnostics and Intervention Radiation Physics Biomedical Engineering Umeå University Umeå Sweden

Handling missing values in tabular datasets presents a significant challenge in training and testing artificial intelligence models, an issue usually addressed using imputation techniques. Here we introduce "Not Another Imputation Method" (NAIM), a novel transformer-based model specifically designed to address this issue without the need for traditional imputation techniques. NAIM employs feature-specific embeddings and a masked self-attention mechanism that effectively learns from available data, thus avoiding the necessity to impute missing values. Additionally, a novel regularization technique is introduced to enhance the model’s generalization capability from incomplete data. We extensively evaluated NAIM on 5 publicly available tabular datasets, demonstrating its superior performance over 6 state-of-the-art machine learning models and 4 deep learning models, each paired with 3 different imputation techniques when necessary. The results highlight the efficacy of NAIM in improving predictive performance and resilience in the presence of missing data. To facilitate further research and practical application in handling missing data without traditional imputation methods, we made the code for NAIM available at https://***/cosbidev/NAIM. © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Identification of Optimal Training for Prediction of Glucose Levels in Type-1-Diabetes Using Edge Computing

Identification of Optimal Training for Prediction of Glucose...

引用

2022 International Conference on Electrical, computer, Communications and Mechatronics Engineering, ICECCME 2022

作者： D'Antoni, Federico Petrosino, Lorenzo Velieri, Andrea Sasso, Daniele D'Angelis, Onorato Boscarino, Tamara Vollero, Luca Merone, Mario Piemonte, Vincenzo Università Campus Bio-Medico di Roma Research Unit of Computer Systems and Bioinformatics Department of Engineering Rome Italy Università Campus Bio-Medico di Roma Chemical-physics Fundamentals in Chemical Engineering Department of Engineering Rome Italy

ISBN: (数字)9781665470957

ISBN: (纸本)9781665470957

Type 1 Diabetes Mellitus (T1DM) is a chronic autoimmune disease involving high blood glucose levels. It is caused by the destruction of pancreatic β-cells, which are responsible for insulin production. Survival of subjects with T1DM is dependent on exogenous insulin administrations [1]. In order to calculate and then inject an appropriate insulin dose, subjects must frequently monitor their glucose values, taking into account not only the exact amount of carbohydrates ingested, but also physical activity [2], [3], disease states [4], and stress episodes [5]. The main goal of glycemic control is to avoid or at least mitigate events such as hypoglycemia and hyperglycemia [6]. Hypoglycemia, defined as a blood glucose level lower than 70 mg/dL, can result in serious immediate complications such as seizure or coma [7], whereas hyperglycemia, defined as a blood glucose level greater than 180 mg/dL, leads to several microvascular and macrovascular complications in the long term [7]. The advent of Continuous Glucose Monitoring (CGM) devices, i.e., sensors capable of measuring interstitial glucose concentration at 1-to 5-minute intervals, has improved the quality of life of individuals with T1DM, allowing a decrease in the occurrence of hypo/hyperglycemic events [8]. Despite the widespread use of these devices, adverse glycemic events still occur. Providing patients with a prediction of blood glucose levels can further improve their quality of life enabling proactive interventions and reducing their daily cognitive load [9]. Indeed, research is focusing on the development of data-driven models that can predict future glycemic levels as accurately as possible on both short-term [10] and long-term predictions [11], leveraging past CGM values alone [12] or in combination with other features such as insulin injections or carbohydrate intake [13]. © 2022 IEEE.

关键词： Insulin

来源：评论

学校读者我要写书评

暂无评论

Texture-Aware StarGAN for CT data harmonization

arXiv

引用

arXiv 2025年

作者： Di Feola, Francesco Pompilio, Ludovica Assolito, Cecilia Guarrasi, Valerio Soda, Paolo Research Unit of Computer Systems and Bioinformatics Campus Bio-Medico University of Rome Rome Italy Department of Diagnostics and Intervention Radiation Physics Biomedical Engineering Umeå University Sweden La Sapienza University of Rome Italy

Computed Tomography (CT) plays a pivotal role in medical diagnosis;however, variability across reconstruction kernels hinders data-driven approaches, such as deep learning models, from achieving reliable and generalized performance. To this end, CT data harmonization has emerged as a promising solution to minimize such non-biological variances by standardizing data across different sources or conditions. In this context, Generative Adversarial Networks (GANs) have proved to be a powerful framework for harmonization, framing it as a style-transfer problem. However, GAN-based approaches still face limitations in capturing complex relationships within the images, which are essential for effective harmonization. In this work, we propose a novel texture-aware StarGAN for CT data harmonization, enabling one-to-many translations across different reconstruction kernels. Although the StarGAN model has been successfully applied in other domains, its potential for CT data harmonization remains unexplored. Furthermore, our approach introduces a multi-scale texture loss function that embeds texture information across different spatial and angular scales into the harmonization process, effectively addressing kernel-induced texture variations. We conducted extensive experimentation on a publicly available dataset, utilizing a total of 48667 chest CT slices from 197 patients distributed over three different reconstruction kernels, demonstrating the superiority of our method over the baseline StarGAN. © 2025, CC BY-NC-SA.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition in Italian Lung Cancer Clinical Reports using Transformers

Named Entity Recognition in Italian Lung Cancer Clinical Rep...

引用

2023 IEEE International Conference on bioinformatics and Biomedicine, BIBM 2023

作者： Paolo, Domenico Bria, Alessandro Greco, Carlo Russano, Marco Ramella, Sara Soda, Paolo Sicilia, Rosa Università Campus Bio-Medico di Roma Unit of Computer Systems & Bioinformatics Department of Engineering Italy University of Cassino and Southern Latium Department of Electrical and Information Engineering Cassino Italy Università Campus Bio-Medico di Roma Research Unit of Radiation Oncology Department of Medicine and Surgery Italy Fondazione Policlinico Universitario Campus Bio-Medico Operative Research Unit of Radiation Oncology Italy Fondazione Policlinico Universitario Campus Bio-Medico Operative Research Unit of Medical Oncology Italy Umeå University Department of Radiation Sciences Radiation Physics Biomedical Engineering Sweden

ISBN: (纸本)9798350337488

The widespread adoption of electronic health records (EHRs) offers a valuable opportunity to support clinical research by containing crucial patient information, including diagnoses, symptoms, medications, lab tests, and more. Despite the success of deep learning for biomedical Named Entity Recognition (NER), the literature in this field still presents a gap regarding applications focused on lung cancer for the Italian language. Hence, this paper presents a transformer-based approach to extract named entities from Italian clinical notes related to Non-Small Cell Lung Cancer (NSCLC). We introduce a novel set of 25 clinical entities related to NSCLC building a corpus annotated for NER. We apply a state-of the-art model pre-trained on Italian biomedical texts to the manually annotated clinical reports of a cohort of 257 patients suffering from NSCLC, successfully dealing with class-imbalance problems and obtaining promising performance (average F1-score of 84.3%). We also compared our method with two other pre-trained state-of-the-art models showing that the domain specific knowledge offered by the proposed approach is necessary to achieve higher performance. These findings also showcase the feasibility of using transformers to extract biomedical information in the Italian language. © 2023 IEEE.

关键词： deep learning EHRs NER NSCLC trasformer

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Tensor Completion for Heart Failure Exacerbation Detection in Multivariate Time Series with Missing Data

Low-Rank Tensor Completion for Heart Failure Exacerbation De...

引用

Annual IEEE Symposium on computer-Based Medical systems

作者： Óscar Escudero-Arnanz Rosa Sicilia Cristina Soguero-Ruiz Inmaculada Mora-Jiménez Diana Lelli Claudio Pedone Antonio G. Marques Dept. Signal Theory & Communications Telematics & Computing Systems Rey Juan Carlos University Fuenlabrada Spain Department of Engineering Unit of Computer Systems & Bioinformatics Università Campus Bio-Medico di Roma Italy Operative Research Unit of Geriatrics Fondazione Policlinico Universitario Campus Bio-Medico Italy

ISBN: (数字)9798350384727

ISBN: (纸本)9798350384734

Heart failure exacerbations (HFE) represent a critical challenge in healthcare due to their significant role in global mortality. The rise of home and wearable devices capable of monitoring cardiac conditions provides valuable opportunities for data-driven analysis and HFE detection. However, these devices frequently generate low-quality measurements with irregular sampling frequencies and high rates of missing data. Our paper presents a methodology that processes these measurements as a three-dimensional tensor, applying a low-rank tensor completion scheme to manage missing data effectively, thus facilitating anomaly detection without necessitating data imputation. We validate our method on a dataset from 4 patients with chronic HF in the compensation phase, collected at the Hospital Fondazione Policlinico Universitario Campus Bio-Medico in Rome, Italy. Our results demonstrate the tensor-based method’s superiority over traditional techniques, highlighting its potential for detecting anomalies within complex multivariate time series data. This research emphasizes the critical role of advanced data analysis in enhancing HFE identification, which could lead to improved patient care and reduced hospitalization rates.

关键词： Tensors Data analysis Hospitals Time series analysis Imputation Data models Frequency measurement

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study Between Paired And Unpaired Image Quality Assessment In Low-Dose CT Denoising

A Comparative Study Between Paired And Unpaired Image Qualit...

引用

Annual IEEE Symposium on computer-Based Medical systems

作者： Francesco Di Feola Lorenzo Tronchin Paolo Soda Department of Radiation Sciences Radiation Physics Biomedical Engineering Umeå University Umeå Sweden Research Unit of Computer Systems and Bioinformatics Campus Bio-Medico University of Rome Rome Italy

关键词：

来源：评论

学校读者我要写书评

暂无评论

Photoplethysmographic Signal Quality Assessment: a Comparative Study of Unsupervised and Supervised Neural Networks 6

Photoplethysmographic Signal Quality Assessment: a Comparati...

引用

6th IEEE International Workshop on Metrology for Industry 4.0 and IoT, MetroInd4.0 and IoT 2023

作者： Sabatini, Anna Bacco, Luca Lotini, Leonardo Palombo, Giovanni Tomaso, Giulia Di Sabbadini, Riccardo Merone, Mario Vollero, Luca University Campus Bio-Medico of Rome Research Unit of Computer Systems and Bioinformatics Department of Engineering Via Alvaro del Portillo Rome21 - 00128 Italy Istituto di Analisi Dei Sistemi Ed Informatica 'A. Ruberti' Via dei Taurini Rome19 00185 Italy Heremos Srl Vicolo Mazzarino 14 Rome00184 Italy

ISBN: (纸本)9798350396577

We present algorithms to discriminate good quality PPG signals, i.e., free of artefacts and with suitable morphologies, which is fundamental for a correct medical diagnosis. We have investigated two different approaches of unsupervised and supervised learning. The first method is a Self Organizing Map (SOM), trained on entropic and morphological features extracted by BUT PPG signal windows. We then add three new features related to signal quality, namely the Kurtosis Index, Skewness Index and Signal to Noise Ratio (SNR), that we have shown to improve the performances. For the second approach, we have implemented a Multi Layer Perceptron (MLP) neural network. We have compared the results obtained with those in the literature showing superior performance, especially with the MLP approach, achieving an F_1 -score of 96.15%. © 2023 IEEE.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Symbolic Regression in Precision Livestock Farming 11

Exploring the Potential of Symbolic Regression in Precision ...

引用

11th European Conference on Precision Livestock Farming

作者： Mayrhuber, E. Oczak, M. Iwersen, M. Brunner, D. Dorfer, V. Winkler, S.M. Bioinformatics Research Group PLFDoc University of Applied Sciences Upper Austria Hagenberg Austria Computer Vision Lab TU Wien Vienna Austria Precision Livestock Farming Hub The University of Veterinary Medicine Vienna Vienna Austria Center for Animal Nutrition and Welfare The University of Veterinary Medicine Vienna Vienna Austria Center for Veterinary Systems Transformation and Sustainability Clinical Unit for Herd Health Management The University of Veterinary Medicine Vienna Vienna Austria

ISBN: (纸本)9791221067361

The ability to predict farrowing time in pigs is crucial for optimal farm management and ensuring piglet survival. This study investigates the potential of explainable artificial intelligence for precision livestock farming, focusing on acceleration sensor data from sows around the time of farrowing. Accurately predicting farrowing allows farmers to balance both, piglet safety by avoiding piglet crushing events and the mother sow's welfare, by avoiding early crating. Traditional machine learning models often lack interpretability ("closed-box" problem). Explainable artificial intelligence offers a solution by revealing the decision-making processes within the models. This work is split into two stages. First the detection of nest building behaviour and second the prediction of the remaining time to farrowing. The nest building detection was possible for 166 out of 180 sows and successful within 48 hours before farrowing for 149 sows. The nest building detection is purely based on the change of a sow's activity level and uses no machine learning techniques. Further, this study utilizes symbolic regression, an open-box modelling technique that generates interpretable mathematical formulas, to predict the remaining time until the onset of farrowing. The results are compared with closed-box models, like support vector regression and artificial neural networks, for both explainability and performance. Notably, symbolic regression achieved a mean absolute error of 9.28 hours for the time-to-farrowing prediction, outperforming the closed-box models in terms of performance and interpretability. This research demonstrates that explainable artificial intelligence, specifically symbolic regression, can offer both interpretable results and competitive performance in precision livestock farming. © 2024 11th European Conference on Precision Livestock Farming. All rights reserved.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

Whole-Body Image-to-Image Translation for a Virtual Scanner in a Healthcare Digital Twin

arXiv

引用

arXiv 2025年

作者： Guarrasi, Valerio Di Feola, Francesco Restivo, Rebecca Tronchin, Lorenzo Soda, Paolo Research Unit of Computer Systems and Bioinformatics Department of Engineering Università Campus Bio-Medico di Roma Rome Italy Department of Computing Science Umeå University Umeå Sweden Department of Diagnostics and Intervention Biomedical Engineering and Radiation Physics Umeå University Umeå Sweden

Generating positron emission tomography (PET) images from computed tomography (CT) scans via deep learning offers a promising pathway to reduce radiation exposure and costs associated with PET imaging, improving patient care and accessibility to functional imaging. Whole-body image translation presents challenges due to anatomical heterogeneity, often limiting generalized models. We propose a framework that segments whole-body CT images into four regions—head, trunk, arms, and legs—and uses district-specific Generative Adversarial Networks (GANs) for tailored CT-to-PET translation. Synthetic PET images from each region are stitched together to reconstruct the whole-body scan. Comparisons with a baseline non-segmented GAN and experiments with Pix2Pix and CycleGAN architectures tested paired and unpaired scenarios. Quantitative evaluations at district, whole-body, and lesion levels demonstrated significant improvements with our district-specific GANs. Pix2Pix yielded superior metrics, ensuring precise, high-quality image synthesis. By addressing anatomical heterogeneity, this approach achieves state-of-the-art results in whole-body CT-to-PET translation. This methodology supports healthcare Digital Twins by enabling accurate virtual PET scans from CT data, creating virtual imaging representations to monitor, predict, and optimize health outcomes. © 2025, CC BY-SA.

关键词： Positron emission tomography

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：