Bildverarbeitung für die Medizin 2024

Name: Bildverarbeitung für die Medizin 2024 | Proceedings, German Conference on Medical Image Computing, Erlangen, March 10-12, 2024
Brand: Springer Vieweg
Price: 86.99 EUR
Availability: OnlineOnly

Proceedings, German Conference on Medical Image Computing, Erlangen, March 10-12, 2024

Andreas Maier Thomas M. Deserno Heinz Handels Klaus Maier-Hein Christoph Palm Thomas Tolxdorff(Herausgeber*in)

Springer Vieweg (Verlag)

Erschienen am 19. Februar 2024

XXIV, 370 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-658-44037-4 (ISBN)

86,99 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Bildverarbeitung für die Medizin 2024
Preisträger der BVM 2022 in Heidelberg
Vorwort
Inhaltsverzeichnis
Keynote: Recent Advances in Surgical AI for Next Generation Interventions
References
Keynote: 4-D+ nanoSCOPE Project
References
Improving Hybrid Quantum Annealing Tomographic Image Reconstruction with Regularization Strategies
1 Introduction
2 Materials and methods
2.1 L2 regularization
2.2 Total variation regularization
3 Results
4 Discussion
References
Abstract: Deep Learning-based Detection of Vessel Occlusions on CT-Angiography in Patients with Suspected Acute Ischemic Stroke
References
Abstract: Cytologic Scoring of Equine Exercise-induced Pulmonary Hemorrhage. Performance of Human Experts and a Deep Learning
References
Abstract: Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation
References
Abstract: Flexible Unfolding of Circular Structures for Rendering Textbook-style Cerebrovascular Maps
References
Attention-guided Erasing. Novel Augmentation Method for Enhancing Downstream Breast Density Classification
1 Introduction
2 Materials and methods
2.1 Data
2.2 Methodology
3 Results and discussion
References
Appearance-based Debiasing of Deep Learning Models in Medical Imaging
1 Introduction
2 Materials and methods
2.1 CT-COPD dataset
2.2 MS-SCC dataset
2.3 Bias experiments
2.4 Appearance-based domain adversarial debiasing using control regions
2.5 Control region selection
3 Results
4 Discussion and outlook
References
Abstract: Interpretable Medical Image Classification Using Prototype Learning and Privileged Information
References
Abstract: Robust Multi-contrast MRI Denoising using Trainable Bilateral Filters without Noise-free Targets
References
Privacy-enhancing Image Sampling for the Synthesis of High-quality Anonymous Chest Radiographs
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Latent diffusion model
2.3 Privacy-enhancing image sampling strategy
2.4 Experiments
3 Results
4 Discussion
References
Segmentation-guided Medical Image Registration. Quality Awareness using Label Noise Correctionn
1 Introduction
2 Materials and methods
2.1 Method
2.1.1 Network overview.
2.1.2 Label correction.
2.1.3 Training strategy.
2.2 Experimental setup
2.2.1 Data.
2.2.2 Simulate low-quality labels.
2.2.3 Training.
2.2.4 Experiments.
3 Results
4 Discussion
References
Displacement Representation for Conditional Point Cloud Registration. HeatReg Applied to 2D/3D Freehand Ultrasound Reconstruction
1 Introduction
1.1 Related work
1.2 Contribution
2 Methods
3 Experiments
3.1 Data
3.2 Implementation details
3.3 Ablations and baseline methods
4 Results
5 Conclusion
References
Joint Learning of Image Registration and Change Detection for Lung CT Images
1 Introduction
2 Materials and methods
2.1 Creating change maps
2.2 Data and training
2.3 Experiments and evaluation
3 Results
4 Discussion
References
Abstract: Focused Unsupervised Image Registration for Structure-specific Population Analysis
References
Abstract: Combined 3D Dataset for CT- and Point Cloud-based Intra-patient Lung Registration. Lung250M-4B
References
Influence of Prompting Strategies on Segment Anything Model (SAM) for Short-axis Cardiac MRI Segmentation
1 Introduction
2 Methods
2.1 Datasets
2.2 Segment anything model (SAM):
3 Experiments and results
3.1 Baseline model
3.2 Fine-tuned model
4 Discussion and conclusion
References
Abstracting Volumetric Medical Images with Sparse Keypoints for Efficient Geometric Segmentation of Lung Fissures with a Graph CNN
1 Introduction
2 Material and methods
2.1 Pipeline for keypoint-based geometric segmentation
2.2 Data and experiments
3 Results
4 Discussion
References
Advanced Deep Learning for Skin Histoglyphics at Cellular Level
1 Introduction
2 Materials and methods
3 Results
4 Discussion
References
Combining Image- and Geometric-based Deep Learning for Shape Regression. Comparison to Pixel-level Methods for Segmentation in Chest X-ray
1 Introduction
2 Methods
2.1 Pipeline for shape regression
2.1.1 Formulation of shape regression.
2.2 Pixel-level baselines
3 Results
4 Discussion
References
Abstract: Multi-dataset Approach to Medical Image Segmentation. MultiTalent
References
Abstract: 3D Medical Image Segmentation with Transformer-based Scaling of ConvNets MedNeXt
References
Abstract: Baseline Pipeline for Automated Eye Redness Extraction with Relation to Clinical Grading
References
Abstract: Reducing Domain Shift in Deep Learning for OCT Segmentation using Image Manipulations
References
Neural Implicit k-space with Trainable Periodic Activation Functions for Cardiac MR Imaging
1 Introduction
2 Materials and methods
2.1 Neural implicit k-space representation
2.2 Trainable activation functions
2.3 Experimental setup
2.3.1 Dataset.
2.3.2 Training settings.
2.3.3 Evaluation.
3 Results
4 Discussion
References
Effect of Training Epoch Number on Patient Data Memorization in Unconditional Latent Diffusion Models
1 Introduction
2 Materials and methods
2.1 Generative modeling via latent diffusion models
2.2 Memorization assessment
2.2.1 Self-supervised training.
2.2.2 Copy detection.
2.3 Dataset and network training
3 Results
4 Discussion
References
Exploring GPT-4 as MR Sequence and Reconstruction Programming Assistant GPT4MR
1 Introduction
2 Materials and methods
2.1 PyPulseq
2.2 MR-zero
2.3 GPT4MR
3 Results
4 Discussion
References
Abstract: Understanding Silent Failures in Medical Image Classification
References
Abstract: Advancing Large-scale Deformable 3D Registration with Differentiable Volumetric Rasterisation of Point Clouds. Chasing Clouds
References
Harmonized Import of Clinical Research Data for the Open Source Image Analysis Platform Kaapana
1 Introduction
2 Materials and methods
2.1 Data integration and transformation scenarios
2.2 Score based selection of technologies
2.3 Kaapana
3 Results
3.1 Implementation
3.1.1 Evaluation.
4 Discussion
References
Interactive Exploration of Conditional Statistical Shape Models in the Web-browser. exploreCOSMOS
1 Introduction
2 Methods
3 Implementation
4 Results
5 Conclusion
References
Abstract: Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection
References
Abstract: Reformulating COPD Classification on Chest CT Scans as Anomaly Detection using Contrastive Representations cOOpD
References
Abstract: Handling Label Uncertainty on the Example of Automatic Detection of Shepherd's Crook RCA in Coronary CT Angiography
References
Segment-wise Evaluation in X-ray Angiography Stenosis Detection
1 Introduction
2 Materials and methods
2.1 Data
2.2 Stenosis detection model
2.3 Customized annotation tool
3 Results
4 Discussion
References
Automated Mitotic Index Calculation via Deep Learning and Immunohistochemistry
1 Introduction
2 Materials
3 Methods
3.1 Automatic tumor epithelium segmentation on H&E
3.2 Mitotic count estimation
3.3 Volume corrected mitotic index
3.4 Manual vs. automatic M/V-index
4 Results
5 Discussion
References
Abstract: Radiomics Processing Toolkit. Role of Feature Computation on Prediction Performance
References
Towards Unified Multi-modal Dataset Creation for Deep Learning Utilizing Structured Reports
1 Introduction
2 Material and methods
3 Results
4 Discussion
Acknowledgements
References
Abstract: Comprehensive Multi-domain Dataset for Mitotic Figure Detection
References
Assessment of Scanner Domain Shifts in Deep Multiple Instance Learning
1 Introduction
2 Methods
3 Materials
4 Results
5 Discussion
References
Few Shot Learning for the Classification of Confocal Laser Endomicroscopy Images of Head and Neck Tumors
1 Introduction
2 Materials
3 Methods
3.1 Preprocessing
3.2 Few shot learning methods
4 Results
5 Discussion
References
Computational Ontology and Visualization Framework for the Visual Comparison of Brain Atrophy Profiles
1 Introduction
2 Materials and methods
2.1 Semantic modeling
2.2 Summary plots
3 Results
3.1 Semantic modeling
3.2 Summary plots
4 Discussion
References
Abstract: Denoising of Home OCT Images using Noise-to-noise Trained on Artificial Eye Data
References
Abstract: Metal-conscious Embedding for CBCT Projection Inpainting
References
Abstract: Self-supervised Pre-training for Dealing with Small Datasets in Deep Learning for Medical Imaging. Evaluation of Contrastive and Masked Autoencoder Methods
References
Abstract: Enhanced Diagnostic Fidelity in Pathology Whole Slide Image Compression via Deep Learning
References
Abstract: Self-supervised CT Dual Domain Denoising using Low-parameter Models
References
Comparative Analysis of Radiomic Features and Gene Expression Profiles in Histopathology Data using Graph Neural Networks
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Graph structure
2.3 Dimensionality reduction
2.4 Graph random neural network
2.5 Experimental design
3 Results
4 Discussion
References
Magnetisation Reconstruction for Quantum Metrology
1 Introduction
1.1 Related work
2 Materials and methods
2.1 Dataset
2.2 Method
2.3 Loss function
2.4 Evaluation
3 Results
4 Discussion
References
Improving Segmentation Models for AR-guided Liver Surgery using Synthetic Images
1 Introduction
2 Materials and methods
2.1 Data recording, synthesis, depth stream mapping
2.2 Segmentation experiments
3 Results
4 Discussion
References
Application of Active Learning-based on Uncertainty Quantification to Breast Segmentation in MRI
1 Introduction
2 Materials and methods
2.1 Data
2.2 Active learning experiment setup
3 Results
3.1 Selecting an uncertainty measure for active learning
3.2 Active learning experiment
3.3 Correlation of uncertainty and segmentation quality over time
4 Discussion
References
Guidance to Noise Simulation in X-ray Imaging
1 Introduction
2 Noise simulation
2.1 Poisson distribution
2.2 Detector gain estimation
2.3 Reducing the number of arriving photons or enhancing the noise
2.4 Scintillator blurring
3 Results
4 Discussion and conclusion
References
Automated Lesion Detection in Endoscopic Imagery for Small Animal Models
1 Introduction
2 Materials and methods
2.1 Preparation protocol
2.2 Data
2.3 Detection algorithm
2.3.1 YOLOv7-tiny architecture.
2.3.2 Pre- and post-processing.
2.4 Evaluation parameters
3 Results
4 Discussion
References
Ultrasound to CT Image-to-image Translation for Personalized Thyroid Screening
1 Introduction
1.1 Related work
2 Materials and methods
2.1 Dataset and preprocessing
2.2 Method
2.3 Loss function
2.4 Evaluation
3 Results
4 Discussion
References
Abstract: Multistage Registration of CT and Biopsy CT Images of Lung Tumors
References
Abstract: Spatiotemporal Illumination Model for 3D Image Fusion in Optical Coherence Tomography
References
Abstract: Gradient-based Geometry Learning for Fan-beam CT Reconstruction
References
Segmentation-inspired Image Registration
1 Introduction
2 Material and methods
2.1 Variational formulation of the registration problem
2.2 Segmentation-based feature extraction
2.3 Registration Scheme
2.4 Application specific parametrization
2.5 Data set
2.6 Evaluation Measures and Computational Details
3 Results
4 Discussion
References
Exploring Epipolar Consistency Conditions
1 Introduction
2 Materials and methods
2.1 Epipolar consistency conditions
2.2 Motion simulation
2.3 Optimization details
3 Results
4 Discussion
References
Abstract: Enabling Geometry Aware Learning Through Differentiable Epipolar View Translation
References
Abstract: Realistic Collimated X-ray Image Simulation Pipeline
References
Abstract: RecycleNet. Latent Feature Recycling Leads to Iterative Decision Refinement
Abstract
References
Self-supervised Vessel Segmentation from X-ray Images using Digitally Reconstructed Radiographs
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Framework details
2.2.1 Framework overview.
2.2.2 Domain randomization.
2.2.3 Adversarial learning.
2.2.4 Self-supervised learning.
2.2.5 Implementation details.
3 Results
4 Conclusion
References
Influence of imperfect annotations on deep learning segmentation models
1 Introduction
2 Materials and Methods
2.1 Dataset
2.2 Annotation errors
2.3 Level of errors
2.4 Experiments
3 Results
4 Discussion and Conclusion
References
Addressing the Bias of the Dice Coefficient. Semantic Segmentation of Peripheral Airways in Lung CT
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Label generation
2.3 Dilation
2.4 Training details
3 Results
4 Discussion
References
Automated Tooth Instance Segmentation and Pathology Annotation Pipeline for Panoramic Radiographs. Mask-R-CNN Approach with Elastic Transformations
1 Introduction
2 Materials and methods
2.1 Augmentations
2.2 Patching and re-patching
2.3 Metrics
2.4 Data and annotations
3 Results
4 Discussion
References
Multi-task Learning to Improve Semantic Segmentation of CBCT Scans using Image Reconstruction
1 Introduction
2 Method
2.1 Dataset
2.2 Experimental setup
3 Results
4 Discussion
References
Non-specialist Versus Neural Network. An Example of Gender Classification from Abdominal CT Data
1 Introduction
2 Materials and methods
2.1 Materials
2.2 Methods
2.2.1 Manual analysis.
2.2.2 Automated analysis with neural network classification.
3 Results
4 Discussion
References
Automatic Segmentation of Lymphatic Perfusion in Patients with Congenital Single Ventricle Defects
1 Introduction
1.1 Contributions
2 Materials and methods
2.1 Dataset curation
2.2 Segmentation framework
3 Results
4 Discussion
References
Data Augmentation for Images of Chronic Foot Wounds
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Network architecture
2.3 Shape projection and blurring
2.4 Warping
2.5 Baseline
2.6 Training
2.7 Evaluation metric
3 Results
4 Discussion
References
Segmentation of Acute Ischemic Stroke in Native and Enhanced CT using Uncertainty-aware Labels
1 Introduction
2 Materials and methods
2.1 Data
2.2 Uncertainty-aware labels
2.3 Segmentation model training
2.4 Evaluation
2.4.1 Post-processing of predicted label maps.
2.4.2 Evaluation metrics.
3 Results
4 Discussion
References
Preprocessing Evaluation and Benchmark for Multi-structure Segmentation of the Male Pelvis in MRI on the Gold Atlas Dataset
1 Introduction
1.1 Related work
2 Materials and methods
2.1 Dataset
2.2 Preprocessing
2.3 Segmentation network set-up
2.4 Postprocessing
3 Results
4 Discussion
References
Evaluation of Semi-automatic Segmentation of Liver Tumors for Intra-procedural Planning
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 User input
2.3 Deepgrow
2.4 Experiment
3 Results
4 Discussion
References
Generalizable Kidney Segmentation for Total Volume Estimation
1 Introduction
2 Materials and methods
2.1 Patient data
2.2 Image annotation
2.3 Image pre-processing
2.4 Network architecture
2.5 Training
2.6 Evaluation
3 Results
4 Discussion
References
Multi-organ Segmentation in CT from Partially Annotated Datasets using Disentangled Learning
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Disentangled strategy
2.3 Experimental setup
3 Result
4 Discussion
References
Abstract: Generation of Synthetic 3D Data using Simulated MR Examinations in Augmented Reality
References
Smoke Classification in Laparoscopic Cholecystectomy Videos Incorporating Spatio-temporal Information
1 Introduction
2 Materials and methods
2.1 Dataset
2.2 Baseline architectures
2.3 Incorporation of spatio-temporal information
2.4 Experiments and evaluation
3 Results
4 Discussion
References
Learning High-resolution Delay-and-sum Beamforming
1 Introduction
2 Materials and methods
3 Results
4 Discussion
References
Neural Network-based Sinogram Upsampling in Real-measured CT Reconstruction
1 Introduction
2 Materials and methods
2.1 Dataset & data pre-processing
2.2 Network architecture
2.3 Training the networks
3 Results
4 Discussion
5 Conclusion
References
Data Consistent Variational Networks for Zero-shot Self-supervised MR Reconstruction
1 Introduction
2 Materials and methods
2.1 Zero-Shot SSDU
2.2 Variational network
2.3 Proposed data consistent variational network
2.4 Experiments
3 Results
4 Discussion
References
Deep Image Prior for Spatio-temporal Fluorescence Microscopy Images DECO-DIP
1 Introduction
2 Materials and methods
2.1 Imaging data
2.1.1 Synthetic data.
2.1.2 Genetically encoded Ca2+ indicator for optimal imaging (R-GECO) tagged to lysosomal TPC2 in Jurkat T cells.
2.1.3 Confocal Ca2+ imaging in astrocytes in situ.
2.2 Deep image prior and implemented variants
2.3 Experiments
3 Results
3.1 Synthetic data
3.2 Application to low exposure live cell data
4 Discussion
References
Unified Retrieval for Streamlining Biomedical Image Dataset Aggregation and Standardization
1 Introduction
1.1 Background
1.2 Problem
1.3 Relevance of the BIDS standard
2 Materials and methods
2.1 Architecture of URT
2.1.1 Sources and downloaders.
2.1.2 Conversion to BIDS structure.
2.2 Ensuring reproducibility
2.3 Application in high-performance-computing environments
3 Results
4 Discussion
References
Abstract: Object Detection for Breast Diffusion-weighted Imaging
References
Abstract: Semi-automatic White Matter Tract Segmentation using Active Learning atTRACTive
References
Abstract: Metal Inpainting in CBCT Projections using Score-based Generative Model
References
Abstract: Physics-informed Conditional Autoencoder Approach for Robust Metabolic CEST MRI at 7T
References
Comparing Image Segmentation Neural Networks for the Analysis of Precision Cut Lung Slices
1 Introduction
2 Materials and methods
2.1 Dataset and experimental setup
2.2 Proposed workflow
3 Results
4 Discussion
References
Comparison of Deep Learning Image-to-image Models for Medical Image Translation
1 Introduction
2 Materials and methods
2.1 Patient data
2.2 Image pre-processing
2.3 Network architecture
2.4 Network training
2.5 Evaluation
3 Results
3.1 Strategy for hyperparameter tuning
3.2 Validation phase results
4 Discussion
References
3D Deep Learning-based Boundary Regression of an Age-related Retinal Biomarker in High Resolution OCT
1 Introduction
2 Materials and methods
3 Results
4 Discussion
References
Accelerating Artificial Intelligence-based Whole Slide Image Analysis with an Optimized Preprocessing Pipeline
1 Introduction
2 Material and methods
2.1 Software requirements
2.2 Technical overview
2.3 Experimental setup
3 Results
3.1 Functionality
3.2 Runtime
4 Discussion
References
Abstract: Transient Hemodynamics Prediction using an Efficient Octree-based Deep Learning Model
References
Abstract: Utility-preserving Measure for Patient Privacy. Deep Learning-based Anonymization of Chest Radiographs
References
Autorenverzeichnis

Systemvoraussetzungen

Als PDF speichern Als Link merken