Ophthalmic medical image analysis : 8th international workshop, OMIA 2021, held in conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, proceedings / / Huazhu Fu [and four others], editors

• Pubblicazione: Cham, Switzerland : , : Springer, , [2021]; ©2021
• Descrizione fisica: 1 online resource (211 pages)
• Disciplina: 621.367
• Soggetto topico: Optical data processing; Artificial intelligence
• Persona (resp. second.): FuHuazhu
• Nota di contenuto: Intro -- Preface -- Organization -- Contents -- Adjacent Scale Fusion and Corneal Position Embedding for Corneal Ulcer Segmentation -- 1 Introduction -- 2 Methodology -- 2.1 Adjacent Scale Fusion -- 2.2 Corneal Position Embedding -- 3 Experiment -- 3.1 Dataset -- 3.2 Implementation -- 3.3 Quantitative Results -- 3.4 Qualitative Results -- 4 Conclusion -- References -- Longitudinal Detection of Diabetic Retinopathy Early Severity Grade Changes Using Deep Learning -- 1 Introduction -- 2 Methods -- 2.1 Longitudinal Fusion Schemes -- 2.2 Pre-training -- 3 Dataset -- 4 Experiments and Results -- 5 Discussion -- References -- Intra-operative OCT (iOCT) Image Quality Enhancement: A Super-Resolution Approach Using High Quality iOCT 3D Scans -- 1 Introduction -- 2 Methods -- 2.1 Datasets -- 2.2 Image Quality Assessment -- 2.3 Registration -- 2.4 Data Augmentation -- 2.5 Super Resolution with Cycle Consistency -- 3 Results -- 3.1 Image Quality Assessment -- 3.2 Quantitative Analysis -- 3.3 Qualitative Analysis -- 4 Discussion and Conclusions -- References -- Diabetic Retinopathy Detection Based on Weakly Supervised Object Localization and Knowledge Driven Attribute Mining-10pt -- 1 Introduction -- 2 Method -- 2.1 Attention-Drop-Highlight Layer (ADHL) -- 2.2 NAS-ADHL -- 2.3 Attribute Mining (AM) -- 3 Experimental Results -- 3.1 Settings -- 3.2 Ablation Studies -- 3.3 Comparison with SOTA Methods on Disease Grading -- 3.4 User Study on Lesion Identification -- 4 Conclusion -- References -- FARGO: A Joint Framework for FAZ and RV Segmentation from OCTA Images -- 1 Introduction -- 2 Methodology -- 2.1 The Proposed Architecture -- 3 Experiments -- 3.1 Dataset and Image Preprocessing -- 3.2 Experimental Setting -- 3.3 Results -- 4 Conclusion -- References. ; CDLRS: Collaborative Deep Learning Model with Joint Regression and Segmentation for Automatic Fovea Localization -- 1 Introduction -- 2 Materials -- 3 Method -- 4 Experiments and Results -- 5 Conclusion -- References -- U-Net with Hierarchical Bottleneck Attention for Landmark Detection in Fundus Images of the Degenerated Retina -- 1 Introduction -- 2 Methods -- 2.1 Model Architecture -- 2.2 Datasets -- 2.3 Implementation Details -- 3 Experiments and Results -- 3.1 Joint Fovea and OD Detection in the Degenerated Retina -- 3.2 Ablation Study -- 4 Conclusions -- References -- Radial U-Net: Improving DMEK Graft Detachment Segmentation in Radial AS-OCT Scans -- 1 Introduction -- 1.1 Related Work -- 2 Methods and Materials -- 2.1 Data -- 2.2 Models and Experiments -- 2.3 Metrics -- 3 Results -- 4 Discussion -- References -- Guided Adversarial Adaptation Network for Retinal and Choroidal Layer Segmentation -- 1 Introduction -- 2 Proposed Method -- 2.1 Overview -- 2.2 Guided Dual-Encoding -- 2.3 Adversarial Adaptation -- 3 Experimental Results -- 3.1 Datasets -- 3.2 Implementation Details -- 3.3 Evaluation Metrics -- 3.4 Results -- 4 Conclusion -- References -- Juvenile Refractive Power Prediction Based on Corneal Curvature and Axial Length via a Domain Knowledge Embedding Network -- 1 Introduction -- 2 Methodology -- 2.1 Data Collection and Pre-processing -- 2.2 Domain Knowledge Embedding Network (DKE-Net) -- 3 Experimental Results -- 4 Discussion -- 4.1 Main Findings -- 4.2 Strengths and Limitations -- References -- Peripapillary Atrophy Segmentation with Boundary Guidance -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Boundary Guidance Block (BGB) -- 3.2 Loss Function -- 4 Experiment and Results -- 4.1 Dataset and Evaluation -- 4.2 Comparison with State-of-Arts -- 4.3 Ablation Study -- 5 Conclusion -- References. ; Are Cardiovascular Risk Scores from Genome and Retinal Image Complementary? A Deep Learning Investigation in a Diabetic Cohort -- 1 Introduction and Motivation -- 2 Related Work -- 3 Materials -- 3.1 Dataset -- 3.2 Outcome Variables: Risk Scores -- 4 Methods -- 4.1 Image Pre-processing -- 4.2 Deep Learning Architecture and Training -- 4.3 Evaluation Metrics -- 4.4 Statistical Significance -- 4.5 Activation Visualization -- 5 Results -- 6 Discussions and Conclusions -- References -- Dual-Branch Attention Network and Atrous Spatial Pyramid Pooling for Diabetic Retinopathy Classification Using Ultra-Widefield Images -- 1 Introduction -- 2 Methodology -- 2.1 Dual-Branch Network -- 2.2 Atrous Spatial Pyramid Pooling Module -- 2.3 Efficient Channel Attention Module and Spatial Attention Module -- 3 Experiments -- 3.1 Dataset and Implementation Details -- 3.2 Experimental Results -- 4 Conclusions -- References -- Self-adaptive Transfer Learning for Multicenter Glaucoma Classification in Fundus Retina Images -- 1 Introduction -- 2 Related Works -- 3 Method -- 4 Experiments and Results -- 4.1 Datasets -- 4.2 Implement Details and Evaluation Metrics -- 4.3 Results and Discussion -- 5 Conclusion -- References -- Multi-modality Images Analysis: A Baseline for Glaucoma Grading via Deep Learning -- 1 Introduction -- 2 Methodology -- 2.1 Baselines -- 2.2 Local Information of Optic Disc -- 2.3 Ordinal Regression Strategy -- 3 Experiments and Discussion -- 3.1 Overall Performances -- 4 Conclusion -- References -- Impact of Data Augmentation on Retinal OCT Image Segmentation for Diabetic Macular Edema Analysis -- 1 Introduction -- 2 Methods -- 2.1 Data Augmentation -- 2.2 Segmentation Network -- 2.3 Comparison of Shallow Network Versus Deep Network -- 3 Evaluation -- 3.1 Dataset and Training Process -- 3.2 Evaluation of Data Augmentation Impact on Segmentation. ; 4 Discussion -- References -- Representation and Reconstruction of Image-Based Structural Patterns of Glaucomatous Defects Using only Two Latent Variables from a Variational Autoencoder -- 1 Introduction -- 2 Methods -- 2.1 Overview -- 2.2 Macular Ganglion Cell - Inner Plexiform Layer Thickness Map -- 2.3 Variational Autoencoder -- 3 Experimental Methods -- 3.1 VAE Model - Training -- 3.2 VAE Model - Testing -- 4 Results -- 5 Discussion and Conclusion -- References -- Stacking Ensemble Learning in Deep Domain Adaptation for Ophthalmic Image Classification -- 1 Introduction -- 2 Proposed Model -- 2.1 Base Models -- 2.2 Meta-learner Model -- 3 Experimental Results -- 3.1 Implementation Details -- 3.2 Benchmark Dataset -- 3.3 Results and Discussions -- 4 Conclusions -- References -- Attention Guided Slit Lamp Image Quality Assessment -- 1 Introduction -- 2 Dataset -- 3 Method -- 3.1 Multi-task Two-Branch Architecture -- 3.2 Trainable Forward Grad-CAM -- 3.3 Attention Decision Module -- 4 Experiments -- 4.1 Implementation Details -- 4.2 Parameter Influence -- 4.3 Comparison with Other Methods -- 5 Conclusion -- References -- Robust Retinal Vessel Segmentation from a Data Augmentation Perspective -- 1 Introduction -- 2 Methodology -- 2.1 Channel-Wise Random Gamma Correction (CWRGC) -- 2.2 Channel-Wise Random Vessel Augmentation (CWRVA) -- 3 Experiments -- 3.1 Experiments Setup -- 3.2 Generalization Across Different Datasets -- 3.3 Robustness to Brightness, Contrast and Saturation -- 4 Conclusion -- References -- Correction to: Impact of Data Augmentation on Retinal OCT Image Segmentation for Diabetic Macular Edema Analysis. ; Correction to: Chapter "Impact of Data Augmentation on Retinal OCT Image Segmentation for Diabetic Macular Edema Analysis" in: H. Fu et al. (Eds.): Ophthalmic Medical Image Analysis, LNCS 12970, https://doi.org/10.1007/978-3-030-87000-3_16 -- Author Index.
• Titolo autorizzato: Ophthalmic Medical Image Analysis
• ISBN: 3-030-87000-6
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996464422703316
• Lo trovi qui: Univ. di Salerno
• Serie: Lecture notes in computer science ; ; 12970.