Image Analysis and Processing - ICIAP 2023 Workshops [[electronic resource] ] : Udine, Italy, September 11–15, 2023, Proceedings, Part II / / edited by Gian Luca Foresti, Andrea Fusiello, Edwin Hancock

• Autore: Foresti Gian Luca
• Pubblicazione: Cham : , : Springer Nature Switzerland : , : Imprint : Springer, , 2024
• Edizione: 1st ed. 2024.
• Descrizione fisica: 1 online resource (514 pages)
• Disciplina: 006.37
• Soggetto topico: Computer vision; Computer engineering; Computer networks; Machine learning; Education - Data processing; Pattern recognition systems; Computer Vision; Computer Engineering and Networks; Machine Learning; Computers and Education; Automated Pattern Recognition
• Altri autori: FusielloAndrea HancockEdwin
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part II -- Contents - Part I -- Artificial Intelligence and Radiomics in Computer-Aided Diagnosis (AIRCAD) -- Leukocytes Classification Methods: Effectiveness and Robustness in a Real Application Scenario -- 1 Introduction -- 2 Materials and Methods -- 2.1 Data Sets -- 2.2 Data Pre-processing -- 2.3 Methods -- 3 Experimental Evaluation -- 3.1 Experimental Setup -- 3.2 Experimental Results -- 4 Conclusions -- References -- Vision Transformers for Breast Cancer Histology Image Classification -- 1 Introduction -- 2 Background and Related Work -- 2.1 Deep Learning in Histopathology Images of Breast Cancer -- 2.2 Vision Transformers -- 2.3 BACH: Grand Challenge on Breast Cancer Histology Images -- 3 Methodology -- 4 Experimental Evaluation -- 5 Discussion and Conclusion -- References -- Editable Stain Transformation of Histological Images Using Unpaired GANs -- 1 Introduction -- 2 Related Work -- 2.1 Overview of xAI-CycleGAN -- 2.2 SeFa Algorithm for Editable Outputs -- 2.3 cCGAN for Stain Transformation -- 3 Methods -- 3.1 Dataset -- 3.2 Separating Structure from Style -- 3.3 Editable Generation Results Using SeFa -- 4 Results -- 5 Discussion -- 6 Future Work -- References -- Assessing the Robustness and Reproducibility of CT Radiomics Features in Non-small-cell Lung Carcinoma -- 1 Introduction -- 2 Materials and Methods -- 2.1 Dataset -- 2.2 Segmentation -- 2.3 Image Pre-processing and Feature Extraction -- 2.4 Statistical Analysis -- 2.5 Feature Reduction, Selection, and Machine Learning -- 3 Results -- 3.1 Statistical Analysis -- 3.2 Feature Reduction, Selection, and Machine Learning -- 4 Discussion and Conclusions -- References -- Prediction of High Pathological Grade in Prostate Cancer Patients Undergoing [18F]-PSMA PET/CT: A Preliminary Radiomics Study -- 1 Introduction -- 2 Materials and Methods. ; 2.1 PET/CT Imaging -- 2.2 Inclusion Criteria -- 2.3 The Gleason Score -- 2.4 Radiomics Analysis -- 3 Results -- 4 Discussions and Conclusion -- References -- MTANet: Multi-Type Attention Ensemble for Malaria Parasite Detection -- 1 Introduction -- 2 Related Work -- 3 Materials and Methods -- 3.1 Dataset -- 3.2 YOLO Detectors and YOLOv5 -- 3.3 Convolutional Block Attention Module (CBAM) -- 3.4 Our Proposed Method: MTANet -- 3.5 Metrics -- 4 Experimental Results and Discussion -- 4.1 Experimental Setup -- 4.2 Experimental Results -- 5 Conclusions -- References -- Breast Mass Detection and Classification Using Transfer Learning on OPTIMAM Dataset Through RadImageNet Weights -- 1 Introduction -- 2 Methods -- 2.1 Dataset -- 2.2 Proposed Method -- 2.3 YOLO -- 3 Results -- 3.1 Breast Mass Detection -- 3.2 Breast Mass Classification -- 4 Discussion -- 5 Conclusion -- References -- Prostate Cancer Detection: Performance of Radiomics Analysis in Multiparametric MRI -- 1 Introduction -- 2 Materials and Methods -- 2.1 Population -- 2.2 MRI Technique -- 2.3 Manual Segmentation -- 2.4 Radiomics Features Extraction -- 2.5 Computational and Statistical Analyses -- 3 Results -- 3.1 Population -- 3.2 Performance of Radiomics -- 4 Discussion -- 5 Conclusion -- References -- Grading and Staging of Bladder Tumors Using Radiomics Analysis in Magnetic Resonance Imaging -- 1 Introduction -- 2 Materials and Methods -- 2.1 Population -- 2.2 MRI Technique -- 2.3 Qualitative Imaging Analysis -- 2.4 Segmentation and Radiomics Features Extraction -- 2.5 Computational and Statistical Analyses -- 3 Results -- 3.1 Population -- 3.2 Performance of Radiomics -- 4 Discussion -- 5 Conclusion -- References -- Combined Data Augmentation for HEp-2 Cells Image Classification -- 1 Introduction -- 2 Materials and Method -- 2.1 Dataset -- 2.2 Basic Image Manipulation -- 2.3 CVAE. ; 2.4 Experimental Protocol -- 3 Results -- 4 Conclusions -- References -- Multi-modal Medical Imaging Processing (M3IP) -- Harnessing Multi-modality and Expert Knowledge for Adverse Events Prediction in Clinical Notes -- 1 Introduction -- 2 Adverse Events Prediction: Task Formulation -- 3 Data and Information Extraction -- 3.1 Features of Interest -- 3.2 Features Extraction from Structured Data -- 3.3 Features Extraction from Unstructured Data -- 3.4 Multi-modality: Early and Late Fusion -- 4 Training -- 4.1 Datasets and Metrics -- 4.2 Classification Suite -- 4.3 Imbalance Learning -- 5 Results -- 6 Conclusion and Future Work -- References -- A Multimodal Deep Learning Based Approach for Alzheimer's Disease Diagnosis -- 1 Introduction -- 2 Materials and Methods -- 2.1 The Population -- 2.2 Data Preprocessing -- 2.3 The Neural Network -- 2.4 The Proposed Multimodal Approach -- 3 Experimental Set-Up -- 4 Results -- 5 Conclusion -- References -- A Systematic Review of Multimodal Deep Learning Approaches for COVID-19 Diagnosis -- 1 Introduction -- 2 Existing Literature Reviews -- 3 Materials and Methods -- 3.1 Data Sources -- 3.2 Search Strategy and Related Articles -- 4 Results and Discussion -- 5 Conclusions -- References -- A Multi-dimensional Joint ICA Model with Gaussian Copula -- 1 Introduction -- 2 Dataset -- 3 Methods -- 3.1 Conventional Joint ICA -- 3.2 Joint ICA with Different Variances -- 3.3 Proposed Copula Joint ICA -- 4 Implementation -- 4.1 Simulation -- 5 Results -- 6 Conclusion -- References -- Federated Learning in Medical Imaging and Vision (FEDMED) -- Federated Learning for Data and Model Heterogeneity in Medical Imaging -- 1 Introduction -- 2 Related Work -- 2.1 Federated Learning -- 2.2 Model and Data Heterogeneity -- 3 Federated Learning with Heterogeneous Data and Models -- 3.1 Model Heterogeneity. ; 3.2 Data and Labels Heterogeneity -- 4 Experimental Results -- 4.1 Datasets and Models -- 4.2 Comparison with State-of-the-Art Methods -- 5 Conclusion -- References -- Experience Sharing and Human-in-the-Loop Optimization for Federated Robot Navigation Recommendation -- 1 Introduction -- 2 Learning from Experience -- 3 Recommendation as the Silver Bullet -- 4 Human-in-the-Loop Optimization -- 5 Security-Related Considerations -- 6 Conclusion -- References -- FeDETR: A Federated Approach for Stenosis Detection in Coronary Angiography -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Problem Formulation -- 4 Experimental Evaluation -- 4.1 Dataset -- 4.2 Training Procedure -- 4.3 Results -- 5 Conclusion -- References -- FeDZIO: Decentralized Federated Knowledge Distillation on Edge Devices -- 1 Introduction -- 2 Related Work -- 3 Method -- 4 Performance Evaluation -- 4.1 Dataset -- 4.2 Training Procedure -- 4.3 Experimental Results -- 5 Conclusions -- References -- A Federated Learning Framework for Stenosis Detection -- 1 Introduction -- 2 Material and Methods -- 2.1 Datasets -- 2.2 Experimental Protocol -- 3 Results and Discussion -- 4 Conclusion -- References -- Benchmarking Federated Learning Frameworks for Medical Imaging Tasks -- 1 Introduction -- 2 Related Works -- 3 Experiments -- 4 Results -- 5 Conclusions -- 6 Future Works -- References -- Artificial Intelligence for Digital Humanities (AI4DH) -- Examining the Robustness of an Ensemble Learning Model for Credibility Based Fake News Detection -- 1 Introduction -- 2 Related Works -- 2.1 The Liar Dataset -- 2.2 The FakeNewsNet Dataset -- 2.3 The Fake and Real News Dataset -- 2.4 Spawned Dataset -- 3 Methods -- 3.1 Two-Class Boosted Decision Tree (BDT) -- 3.2 Two Class Neural Network -- 3.3 Mixture of Experts -- 3.4 Two Class Logistic Regression -- 4 Experimental Results. ; 4.1 Experiments Where the Train and Test Set are the Same -- 4.2 Experiments Where the Train and Test Set are Different -- 5 Conclusion -- References -- Prompt Me a Dataset: An Investigation of Text-Image Prompting for Historical Image Dataset Creation Using Foundation Models -- 1 Introduction -- 2 Current State of the Research -- 3 Pipeline -- 4 Text-Image Prompt Evaluation -- 4.1 A Note on the Environment -- 5 Conclusion -- References -- Artificial Intelligence in Art Generation: An Open Issue -- 1 Introduction -- 2 State of the Art -- 3 The Experts' Point of View -- 3.1 The Philosopher's Point of View -- 3.2 The Art Historian's Point of View -- 3.3 The Computer Scientist's Point of View -- 4 Experimental Results -- 4.1 The Art Exhibition -- 4.2 Users' Feedbacks -- 5 Conclusions -- References -- A Deep Learning Approach for Painting Retrieval Based on Genre Similarity -- 1 Introduction -- 2 Methodology and Experiments -- 2.1 Convolutional Neural Network -- 2.2 Dataset -- 2.3 Nearest Neighbour Algorithm and Similarity Measure -- 2.4 Experiments -- 3 Results -- 3.1 Classifier Performance -- 3.2 Comparison of CBIR Performance Before and After Fine-Tuning with Specific Domain Knowledge -- 3.3 Parameters Optimization of the Approximate Nearest Neighbour Algorithm -- 3.4 Introducing SimArt: A Web Application for Efficiently Searching Similar Artworks -- 4 Discussion and Conclusions -- References -- GeomEthics: Ethical Considerations About Using Artificial Intelligence in Geomatics -- 1 Introduction -- 2 The Use of Artificial Intelligence in Geomatics -- 3 Ethics of Artificial Intelligence in Geomatics -- 3.1 Geospatial Data Fairness -- 3.2 Local Identity -- 3.3 Geo-Privacy -- 4 Conclusions and Future Works -- References -- Fine Art Pattern Extraction and Recognition (FAPER). ; Enhancing Preservation and Restoration of Open Reel Audio Tapes Through Computer Vision.
• Sommario/riassunto: The two-volume set LNCS 14365 and 14366 constitutes the papers of workshops hosted by the 22nd International Conference on Image Analysis and Processing, ICIAP 2023, held in Udine, Italy, in September 2023. In total, 72 workshop papers and 10 industrial poster session papers have been accepted for publication. Part II of the set, volume 14366, contains 41 papers from the following workshops: – Medical Imaging Hub: • Artificial Intelligence and Radiomics in Computer-Aided Diagnosis (AIR- CAD) • Multi-Modal Medical Imaging Processing (M3IP) • Federated Learning in Medical Imaging and Vision (FedMed) – Digital Humanities Hub: • Artificial Intelligence for Digital Humanities (AI4DH) • Fine Art Pattern Extraction and Recognition (FAPER) • Pattern Recognition for Cultural Heritage (PatReCH) • Visual Processing of Digital Manuscripts: Workflows, Pipelines, Best Practices (ViDiScript).
• Titolo autorizzato: Image Analysis and Processing - ICIAP 2023 Workshops
• ISBN: 3-031-51026-7
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996587864003316
• Lo trovi qui: Univ. di Salerno
• Serie: Lecture Notes in Computer Science, . 1611-3349 ; ; 14366