Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis

Name: Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis | 6th Joint International Workshops, CVII-STENT 2017 and Second International Workshop, LABELS 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 10-14, 2017, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

6th Joint International Workshops, CVII-STENT 2017 and Second International Workshop, LABELS 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 10-14, 2017, Proceedings

M. Jorge Cardoso Tal Arbel Su-Lin Lee Veronika Cheplygina Simone Balocco Diana Mateus Guillaume Zahnd Lena Maier-Hein Stefanie Demirci Eric Granger Luc Duong Marc-André Carbonneau Shadi Albarqouni Gustavo Carneiro(Editor)

Springer (Publisher)

Published on 6. September 2017

XVI, 166 pages

E-Book

PDF with digital watermarking

System requirements

978-3-319-67534-3 (ISBN)

€53.49incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Intro
Workshop Editors
Preface CVII-STENT 2017
Organization
Preface LABELS 2017
Organization
Contents
6th Joint International Workshops on Computing and Visualization for Intravascular Imaging and Computer Assisted Stenting, CVII-STENT 2017
Robust Detection of Circles in the Vessel Contours and Application to Local Probability Density Estimation
1 Introduction
2 Detection of Circles in the Vessel Contours
3 Application to the Local Analysis of the Histogram Around the Vessels
4 Experimental Results
5 Conclusions
References
Intra-coronary Stent Localization in Intravascular Ultrasound Sequences, A Preliminary Study
1 Introduction
2 Method
2.1 Gating
2.2 Struts Detection
2.3 Stent Presence Assessment
3 Validation
3.1 Material
3.2 Experiments on Stent Presence Assessment
4 Results and Discussion
5 Conclusion
References
Robust Automatic Graph-Based Skeletonization of Hepatic Vascular Trees
1 Introduction
2 Methods
2.1 Minimum-Cost Spanning Tree
2.2 Typical Artefacts of Graph-Based Skeletonization
2.3 Filtering of Spurious Branches
3 Results
3.1 Data
3.2 Evaluation of the Skeletonization
3.3 Method Parametrization
3.4 Original vs. Modified Skeletonization Method
4 Conclusions
References
DCNN-Based Automatic Segmentation and Quantification of Aortic Thrombus Volume: Influence of the Training Approach
1 Introduction
2 State-of-the-art
3 Methods
3.1 Abdominal Aortic Aneurysm Datasets
3.2 Experimental Setup: Thrombus Segmentation
3.3 Post-processing and Quantification
4 Results
5 Conclusions
References
Vascular Segmentation in TOF MRA Images of the Brain Using a Deep Convolutional Neural Network
1 Introduction
2 Vascular Segmentation of TOF MRA Images Using Deep CNN
2.1 CNN Architecture
2.2 CNN Training
3 Materials and Methods
3.1 Data Acquisition and Image Preprocessing
3.2 Classification
3.3 CNN Evaluation
3.4 Hardware Settings
4 Results
5 Discussion
6 Conclusion
References
VOIDD: Automatic Vessel-of-Intervention Dynamic Detection in PCI Procedures
1 Introduction
2 Vessel-of-Intervention Dynamic Detection (VOIDD) Algorithm
2.1 General Tracking Framework
2.2 Feature Pairs Extraction
2.3 Track Assignment Distance (TAD)
3 Results
4 Conclusion and Future Work
References
Second International Workshop on Large-Scale Annotation of Biomedical Data and Expert Label Synthesis, LABELS 2017
Exploring the Similarity of Medical Imaging Classification Problems
1 Introduction
2 Methods
3 Experiments
4 Results
5 Discussion and Conclusions
References
Real Data Augmentation for Medical Image Classification
Abstract
1 Introduction
2 Methods
2.1 Data Augmentation Based on Probabilities (CNN + Probability)
2.2 Data Augmentation Based on Distance Function Learning (CNN + Bilinear)
2.3 Data Augmentation Based on Feature Learning (Triplet + L2)
2.4 Unified Learning of Feature Representation and Similarity Matrix
3 Experiments
3.1 Model Parameters
3.2 Performance Metrics and Comparison
3.2.1 Classification Performance
3.2.2 Efforts of Domain Experts
3.3 Applicability to Other Types of Medical Images
4 Conclusion
References
Detecting and Classifying Nuclei on a Budget
1 Introduction
2 Methods
2.1 Detecting and Classifying Nuclei with CNNs
2.2 Transfer Learning with CNNs
2.3 Semi-supervised Learning with Ladder Networks
3 Results and Discussion
3.1 Experimental Setup
3.2 Nucleus Detection
3.3 Nucleus Classification
4 Conclusions and Future Work
References
Towards an Efficient Way of Building Annotated Medical Image Collections for Big Data Studies
1 Introduction
2 Semi-automatic Labeling
3 Web-Based Expert Sourcing of Image Annotations
4 Combining the Platform and Algorithm: Use Cases
4.1 Mode Labeling in Cardiac Echo
4.2 Disease/Healthy Labels for Cardiac Echo Images
5 Results
5.1 Ultrasound Mode Classification
5.2 Aortic Stenosis Detection
6 Conclusions
References
Crowdsourcing Labels for Pathological Patterns in CT Lung Scans: Can Non-experts Contribute Expert-Quality Ground Truth?
1 Introduction
2 Methodology
2.1 Ground Truth for Interstitial Lung Disease
2.2 Data
2.3 Recruitment of Participants
2.4 Annotation Task
3 Results
3.1 Evaluation of Non-expert Versus Expert Performance
3.2 Factors Predicting Performance
3.3 Crowdtruthing in the Real World: Assigning and Combining Multiple Observers
4 Discussion
References
Expected Exponential Loss for Gaze-Based Video and Volume Ground Truth Annotation
1 Introduction
2 Gaze-Based Pixel-Wise Annotation
3 Learning with an Expected Exponential Loss
4 Probability Estimation for Unknown Labels
5 Experiments
6 Conclusion
References
SwifTree: Interactive Extraction of 3D Trees Supporting Gaming and Crowdsourcing
1 Introduction
2 Method
3 Results
4 Conclusion
References
Crowdsourced Emphysema Assessment
1 Introduction
2 Materials and Methods
2.1 Data
2.2 Crowdsourced Triplets
2.3 Similarity Embedding
3 Experiments and Results
3.1 Simulated Similarity Triplets
3.2 Crowdsourced Similarity Triplets
4 Discussion and Conclusion
References
A Web-Based Platform for Distributed Annotation of Computerized Tomography Scans
1 Introduction
2 Related Work
3 The Interface
4 The Backend
5 Evaluation
5.1 Evaluating Interaction Design and Ease of Use
5.2 Evaluating Data Quality
6 Future Work
6.1 UI Improvements
6.2 Added Functionality
6.3 Further Evaluation of Annotation Quality
6.4 Utilizing 3D Information
References
Training Deep Convolutional Neural Networks with Active Learning for Exudate Classification in Eye Fundus Images
1 Introduction
2 Deep Learning Model
3 EGL for Patch and Image Selection in Convolutional Neural Networks
4 Experimental Setup
4.1 Ophtha Dataset
4.2 Evaluation
5 Results
6 Discussion
References
Uncertainty Driven Multi-loss Fully Convolutional Networks for Histopathology
1 Introduction
2 Method
3 Experiments and Discussion
4 Conclusion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis

Description

More details

Other editions

Additional editions

Content

System requirements