检索结果-内蒙古大学图书馆

Pathologic Complete Response Prediction with Machine Learning Using Hierarchical Attention Feature Extraction 27th

学校读者我要写书评

暂无评论

Pathologic Complete Response Prediction with Machine Learni...

27th International Conference on Pattern Recognition, ICPR 2024

作者： Paolo, Domenico Russo, Ciro Russo, Giulio Greco, Carlo Cortellini, Alessio Russano, Marco Ramella, Sara Soda, Paolo Marrocco, Claudio Bria, Alessandro Sicilia, Rosa Unit of Computer Systems and Bioinformatics Department of Engineering Universita‘ Campus Bio-Medico di Roma Selcetta Italy Department of Electrical and Information Engineering University of Cassino and Lazio Meridionale FR Cassino03043 Italy Research Unit of Radiation Oncology Department of Medicine and Surgery University Campus Bio-Medico di Roma Selcetta Italy Operative Research Unit of Medical Oncology Fondazione Policlinico Universitario Campus Bio-Medico Portillo Italy Department of Diagnostics and Intervention Umeå University Umeå Sweden

ISBN: (纸本)9783031876592

Predicting pathologic complete response in non-small cell lung cancer is crucial for tailoring effective treatment strategies and to improve patient outcomes. With the increasing application of artificial intelligence in cancer research, machine learning is poised to play a significant role in prognostication and decision-making. This paper presents a novel approach that utilizes named entity recognition and attention mechanisms applied to electronic health records to predict the pathologic complete response. We first employ named entity recognition to extract relevant biomedical entities from unstructured clinical notes within reports. These entities, combined with structured data, are then processed using a hierarchical attention mechanism to generate comprehensive patient representations. This approach captures complex relationships and contextual information within electronic health records compared to traditional methods. The results highlight the potential of advanced natural language processing techniques to enhance clinical decision-making and support personalized treatment planning in oncology. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Electronic health record

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

学校读者我要写书评

暂无评论

SSRN

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

Texture-Aware StarGAN for CT data harmonization

学校读者我要写书评

暂无评论

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

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

学校读者我要写书评

暂无评论

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

Doctor-in-the-Loop: An Explainable, Multi-View Deep Learning Framework for Predicting Pathological Response in Non-Small Cell Lung Cancer

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Caragliano, Alice Natalina Ruffini, Filippo Greco, Carlo Ippolito, Edy Fiore, Michele Tacconi, Claudia Nibid, Lorenzo Perrone, Giuseppe Ramella, Sara Soda, Paolo Guarrasi, Valerio Unit of Computer Systems and Bioinformatics Department of Engineering Università Campus Bio-Medico di Roma Rome Italy Research Unit of Radiation Oncology Department of Medicine and Surgery Università Campus Bio-Medico di Roma Rome Italy Operative Research Unit of Radiation Oncology Fondazione Policlinico Universitario Campus Bio-Medico Rome Italy Research Unit of Anatomical Pathology Department of Medicine and Surgery Università Campus Bio-Medico di Roma Rome Italy Anatomical Pathology Operative Research Unit Fondazione Policlinico Universitario Campus Bio-Medico Rome Italy Department of Diagnostics and Intervention Radiation Physics Biomedical Engineering Umeå University Umeå Sweden

Non-small cell lung cancer (NSCLC) remains a major global health challenge, with high post-surgical recurrence rates underscoring the need for accurate pathological response predictions to guide personalized treatments. Although artificial intelligence models show promise in this domain, their clinical adoption is limited by the lack of medically grounded guidance during training, often resulting in non-explainable intrinsic predictions. To address this, we propose Doctor-in-the-Loop, a novel framework that integrates expert-driven domain knowledge with explainable artificial intelligence techniques, directing the model toward clinically relevant anatomical regions and improving both interpretability and trustworthiness. Our approach employs a gradual multi-view strategy, progressively refining the model’s focus from broad contextual features to finer, lesion-specific details. By incorporating domain insights at every stage, we enhance predictive accuracy while ensuring that the model’s decision-making process aligns more closely with clinical reasoning. Evaluated on a dataset of NSCLC patients, Doctor-in-the-Loop delivers promising predictive performance and provides transparent, justifiable outputs, representing a significant step toward clinically explainable artificial intelligence in oncology. © 2025, CC BY-NC-ND.

关键词： Lung cancer

Efficient multi-task learning with instance selection for biomedical NLP

学校读者我要写书评

暂无评论

computers in Biology and Medicine 2025年 190卷 110050-110050页

作者： Bonfigli, Agnese Bacco, Luca Pecchia, Leandro Merone, Mario Dell'Orletta, Felice ItaliaNLP Lab Institute of Computational Linguistics "Antonio Zampolli" National Research Council Via Giuseppe Moruzzi 1 Pisa56124 Italy Research Unit of Intelligent Technology for Health and Wellbeing Department of Engineering Università Campus Bio-Medico di Roma Via Alvaro del Portillo 21 Rome00128 Italy Research Unit of Computer Systems and Bioinformatics Department of Engineering Università Campus Bio-Medico di Roma Via Alvaro del Portillo 21 Rome00128 Italy Fondazione Policlinico Universitario Campus Bio-Medico di Roma Via Alvaro del Portillo 200 Rome00128 Italy

Background: Biomedical natural language processing (NLP) increasingly relies on large language models and extensive datasets, presenting significant computational challenges. Methods: We propose Blue5, a multi-task model based on SciFive that incorporates instance selection (IS) to enable efficient, multi-task learning (MTL) on biomedical data. We adapt the E2SC-IS framework for the biomedical domain, integrating a calibrated SVM classifier to reduce computational costs. Results: Our approach achieves an average data reduction of 26.6% across the several tasks of the BLUE (Biomedical Language Understanding Evaluation) Benchmark, while maintaining performance comparable with state-of-the-art models. The multi-task SVM configuration emerges as the most effective, demonstrating the power of combining IS with MTL for biomedical NLP. As a result of the unified framework, Blue5 effectively selects the most informative instances across tasks, ensuring model generalization while efficiently handling multiple NLP tasks. Conclusion: Our work offers a practical solution to address growing computational demands, enabling more scalable and accessible applications of advanced NLP techniques in biomedical research and healthcare. © 2025 The Authors

关键词： Multi-task learning

MedCoDi-M: A Multi-Prompt Foundation Model for Multimodal Medical Data Generation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Molino, Daniele Feola, Francesco Di Faiella, Eliodoro Fazzini, Deborah Santucci, Domiziana Shen, Linlin Guarrasi, Valerio Soda, Paolo 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 Department of Diagnostic Imaging and Stereotactic Radiosurgey Centro Diagnostico Italiano S.p.A. Milano Italy Department of Radiology and Interventional Radiology Fondazione Policlinico Universitario Campus Bio-Medico Rome Italy Research Unit of Radiology and Interventional Radiology Department of Medicine and Surgery Università Campus Bio-Medico di Roma Rome Italy College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Artificial Intelligence is revolutionizing medical practice, enhancing diagnostic accuracy and healthcare delivery. However, its adaptation in medical settings still faces significant challenges, related to data availability and privacy constraints. Synthetic data has emerged as a promising solution to mitigate these issues, addressing data scarcity while preserving privacy. Recently, Latent Diffusion Models have emerged as a powerful tool for generating high-quality synthetic data. Meanwhile, the integration of different modalities has gained interest, emphasizing the need of models capable of handle multimodal medical data. Existing approaches struggle to integrate complementary information and lack the ability to generate modalities simultaneously. To address this challenge, we present MedCoDi-M, a 6.77-billion-parameter model, designed for multimodal medical data generation, that, following Foundation Model paradigm, exploits contrastive learning and large quantity of data to build a shared latent space which capture the relationships between different data modalities. Further, we introduce the Multi-Prompt training technique, which significantly boosts MedCoDi-M’s generation under different settings. We extensively validate MedCoDi-M: first we benchmark it against five competitors on the MIMIC-CXR dataset, a state-of-the-art dataset for Chest X-ray and radiological report generation. Secondly, we perform a Visual Turing Test with expert radiologists to assess the realism and clinical relevance of the generated data, ensuring alignment with real-world scenarios. Finally, we assess the utility of MedCoDi-M in addressing key challenges in the medical field, such as anonymization, data scarcity and imbalance learning. The results are promising, demonstrating the applicability of MedCoDi-M in medical contexts. Project page is at https://***/MedCoDi-M/. © 2025, CC BY-NC-ND.

关键词： Contrastive Learning

Deep Learning for Human Locomotion Analysis in Lower-Limb Exoskeletons: A Comparative Study

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Coser, Omar Tamantini, Christian Tortora, Matteo Furia, Leonardo Sicilia, Rosa Zollo, Loredana Soda, Paolo Unit of Computer Systems & Bioinformatics Università Campus Bio-Medico di Roma Via Álvaro del Portillo 21 Rome00128 Italy Unit of Advanced Robotics and Human-Centered Technologies Università Campus Bio-Medico di Roma Via Álvaro del Portillo 21 Rome00128 Italy Dipartimento di Ingegneria Navale Elettrica Elettronica e delle Telecomunicazioni Università degli Studi di Genova Via all’Opera Pia 11a Genova16145 Italy Department of Diagnostics and Intervention Radiation Physics Biomedical Engineering Umeå University Universitetstorget 4 Umeå40196 Sweden Institute of Cognitive Sciences and Technologies National Research Council of Italy Rome00196 Italy

Wearable robotics for lower-limb assistance have become a pivotal area of research, aiming to enhance mobility for individuals with physical impairments or augment the performance of able-bodied users. Accurate and adaptive control systems are essential to ensure seamless interaction between the wearer and the robotic device, particularly when navigating diverse and dynamic terrains. Despite the recent advances in neural networks for time series analysis, no attempts have been directed towards the classification of ground conditions, categorized into five classes and subsequently determining the ramp’s slope and stair’s height. In this respect, this paper presents an experimental comparison between eight deep neural network backbones to predict high-level locomotion parameters across diverse terrains. All the models are trained on the publicly available CAMARGO 2021 dataset. IMU-only data equally or outperformed IMU+EMG inputs, promoting a cost-effective and efficient design. Indeeds, using three IMU sensors, the LSTM achieved high terrain classification accuracy (0.94 ± 0.04) and precise ramp slope (1.95 ± 0.58°) and the CNN-LSTM a stair height (15.65 ± 7.40 mm) estimations. As a further contribution, SHAP analysis justified sensor reduction without performance loss, ensuring a lightweight setup. The system operates with 2 ms inference time, supporting real-time applications. The code is code available at https://***/cosbidev/Human-Locomotion-Identification. © 2025, CC BY.

关键词： Adaptive control systems

Hazelnut mapping detection system using optical and radar remote sensing:Benchmarking machine learning algorithms

学校读者我要写书评

暂无评论

Artificial Intelligence in Agriculture 2024年第2期12卷 97-108页

作者： Daniele Sasso Francesco Lodato Anna Sabatini Giorgio Pennazza Luca Vollero Marco Santonico Mario Merone Department of Engineering Research Unit of Computer Systems and BioinformaticsUniversitàCampus Bio-Medico di RomaviaÁlvaro del PortilloRome 00128Italy Department of Science and Technology for Sustainable Development and One Health Research Unit of Electronics for Sensor SystemsUniversitàCampus Bio-Medico di RomaviaÁlvaro del PortilloRome 00128Italy Department of Engineering Research Unit of Electronics for Sensor SystemsUniversitàCampus Bio-Medico di RomaviaÁlvaro del PortilloRome 00128Italy Department of Biology University of Naples FedericoⅡNaples 80138Italy

Mapping hazelnut orchards can facilitate land planning and utilization policies,supporting the development of cooperative precision farming *** present work faces the detection of hazelnut crops using optical and radar remote sensing data.A comparative study of Machine Learning techniques is *** system proposed utilizes multi-temporal data from the Sentinel-1 and Sentinel-2 datasets extracted over several years and processed with cloud *** provide a dataset of 62,982 labeled samples,with 16,561 samples belonging to the‘hazelnut’class and 46,421 samples belonging to the‘other’class,collected in 8 heterogeneous geograph-ical areas of the Viterbo *** different comparative tests are conducted:firstly,we use a Nested 5-Fold Cross-Validation methodology to train,optimize,and compare different Machine Learning algorithms on a single *** a second experiment,the algorithms were trained on one area and tested on the remaining seven geo-graphical *** developed study demonstrates how AI analysis applied to Sentinel-1 and Sentinel-2 data is a valid technology for hazelnut *** the results,it emerges that Random Forest is the classifier with the highest generalizability,achieving the best performance in the second test with an accuracy of 96%and an F1 score of 91%for the‘hazelnut’class.

关键词： Remote sensing Crop detection Hazelnut Machine learning Classification