Applications of Medical Artificial Intelligence

Name: Applications of Medical Artificial Intelligence | Second International Workshop, AMAI 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023, Proceedings
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

Second International Workshop, AMAI 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023, Proceedings

Shandong Wu Behrouz Shabestari Lei Xing(Editor)

Springer (Publisher)

Published on 25. October 2023

XI, 178 pages

E-Book

PDF with digital watermarking

System requirements

978-3-031-47076-9 (ISBN)

€96.29incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Intro
Preface
Organization
Contents
Clinical Trial Histology Image Based End-to-End Biomarker Expression Levels Prediction and Visualization Using Constrained GANs
1 Introduction
2 Clinical Trial Data
3 Method
3.1 Whole Slide Image Registration
3.2 Image Tiling and Pre-processing
3.3 Activate Learning (AL) for Semantic Segmentation
3.4 Biomarker Expression Proportion Score (PS)
3.5 Constrained GAN for Virtual IHC Synthesis
4 Results and Discussion
4.1 Phase 1 Clinical Trial Dataset
4.2 Active Learning and PS Score Prediction
4.3 Constrained GAN Training and Testing
5 Conclusion and Future Work
References
More Than Meets the Eye: Physicians' Visual Attention in the Operating Room
1 Introduction
2 Related Work
2.1 Face Detection
2.2 Facial Landmarks
2.3 Spatiotemporal Gaze Architecture
2.4 Eye-Context Interaction Inferring Network
3 Materials
3.1 Benchmark Datasets
3.2 Our Datasets
4 Methods
4.1 Pipeline Construction
4.2 Implementation
5 Results
5.1 Ablation Study of the End-to-End Pipeline
5.2 Evaluation of the Proposed Framework on Our Datasets
6 Discussion
References
CNNs vs. Transformers: Performance and Robustness in Endoscopic Image Analysis
1 Introduction
2 Methods
2.1 Data: Setting, Datasets and Preprocessing
2.2 Network Architectures, Training and Evaluation
3 Experimental Results and Discussion
4 Conclusions
References
Investigating the Impact of Image Quality on Endoscopic AI Model Performance
1 Introduction
2 Methods and Materials
2.1 Network Training
2.2 Experiments
2.3 Image Corruptions
2.4 Evaluation
3 Results
4 Conclusions and Future Work
References
Ensembling Voxel-Based and Box-Based Model Predictions for Robust Lesion Detection
1 Introduction
2 Materials and Methods
2.1 Imaging Data
2.2 Ensembling Method
2.3 Evaluation
3 Results
4 Discussion and Conclusion
References
Advancing Abdominal Organ and PDAC Segmentation Accuracy with Task-Specific Interactive Models
1 Introduction
2 Related Work
3 Method
3.1 Dataset
3.2 Interaction Framework
3.3 Training Details and Evaluation Criteria
4 Results
5 Discussion
6 Future Work
7 Conclusion
References
Anatomical Location-Guided Deep Learning-Based Genetic Cluster Identification of Pheochromocytomas and Paragangliomas from CT Images
1 Introduction
2 Methods
2.1 Dataset
2.2 PPGL-Transformer
2.3 Supervised Contrastive Learning of PPGL-Transformer
2.4 Implementation and Evaluation Details
3 Results
4 Discussion and Conclusion
References
Video-Based Gait Analysis for Assessing Alzheimer's Disease and Dementia with Lewy Bodies
1 Introduction and Related Work
2 Method
2.1 Our Patient Data
2.2 MAX-GRNet for 3D Pose Estimation
2.3 Geometric Deep Learning for Severity Assessment
3 Experiments
3.1 Datasets
3.2 Implementation Details
3.3 Results
4 Conclusion
References
Enhancing Clinical Support for Breast Cancer with Deep Learning Models Using Synthetic Correlated Diffusion Imaging
1 Introduction
2 Related Works
2.1 Breast Cancer Grading
2.2 Pathologic Complete Response Prediction
3 Methodology
3.1 Patient Cohort and Imaging Protocol
3.2 Extracting Deep Radiomic Sequences from CDIs
3.3 pCR Prediction via Volumetric Deep Radiomic Features
4 Results
4.1 Breast Cancer Grading (SBR Grade)
4.2 pCR Prediction via Volumetric Deep Radiomic Features
5 Conclusion
References
Image-Based 3D Reconstruction of Cleft Lip and Palate Using a Learned Shape Prior
1 Introduction
2 Related Work
3 Methods
3.1 Data Pre-processing
3.2 Semi-dense Reconstruction
3.3 Data-Driven Shape Prior
3.4 Data Collection
4 Results
4.1 3D Reconstruction
4.2 Plate Evaluation
4.3 Learned Shape Prior
5 Conclusion
References
Breaking down the Hierarchy: A New Approach to Leukemia Classification
1 Introduction
2 Related Work
3 Dataset
3.1 Pre-processing
4 Methodology Overview
4.1 Flat/Leaf Classification (Baseline)
4.2 Hierarchical Multi-label Classification
5 Experimental Setup
5.1 Model Selection
5.2 Simulating Pathological Evaluation
5.3 Experimental Procedures
5.4 Evaluation Metrics
6 Results and Discussion
6.1 Flat/Leaf Classification
6.2 Base vs Proposed Hierarchical Classification
6.3 Flat vs Proposed Hierarchical Classification
6.4 Visual Experimental Results
7 Conclusion
References
Single-Cell Spatial Analysis of Histopathology Images for Survival Prediction via Graph Attention Network
1 Introduction
2 Method
2.1 Nuclei Classification
2.2 Cell Graph Construction
2.3 Graph Attention Network
2.4 Model Interpretability
3 Experimental and Results
3.1 Dataset
3.2 Implementation Details
3.3 Comparison with State-of-the-Art Methods
4 Conclusion
References
Ultrafast Labeling for Multiplexed Immunobiomarkers from Label-free Fluorescent Images
1 Introduction
2 Method
2.1 Framework Overview
2.2 Random MAE Feature Extractor
2.3 Dual-Modal Feature Combination With Self-Attention Mechanism
2.4 Multitasked Composite Loss Function
3 Experiments
3.1 Data Preparation
3.2 Assessment Scores
3.3 Software and Platform
4 Results
4.1 Comparison with Other Techniques
4.2 Clinical Observation Assessment
5 Conclusion
References
M U-Net: Intestine Segmentation Using Multi-dimensional Features for Ileus Diagnosis Assistance
1 Introduction
2 Method
2.1 Overview
2.2 Compound Loss Function with Deep Supervision
3 Experiments and Results
3.1 Experiment Detail
3.2 Results
4 Discussion and Conclusions
References
Enhancing Cardiac MRI Segmentation via Classifier-Guided Two-Stage Network and All-Slice Information Fusion Transformer
1 Introduction
2 Methods
2.1 Two-Stage Based Segmentation
2.2 All-Slice Fusion Transformer
2.3 Classifier-Guided Segmentation Refinement
2.4 Loss Functions
3 Experiments
3.1 Datasets and Settings
3.2 Results
3.3 Ablation Study
4 Discussion and Conclusion
References
Accessible Otitis Media Screening with a Deep Learning-Powered Mobile Otoscope
1 Introduction
2 Methodology
2.1 Mobile Otoscope
2.2 Deep Learning
2.3 Smartphone Application
3 Results
3.1 Algorithmic Testing
3.2 Validation Testing
4 Discussion and Conclusions
4.1 Prospect of Application
References
Feature Selection for Malapposition Detection in Intravascular Ultrasound - A Comparative Study
1 Introduction
2 Related Work
3 Methods
3.1 Masking Irrelevant Regions
3.2 Including Temporal Context
3.3 Including Blood Flow Information via Deformation Fields
3.4 Combining the Modules
4 Experiments and Results
4.1 Training Modules Needed for Defining M and V
4.2 Single-Frame Classification
4.3 Classification Using Temporal Context
5 Conclusion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Applications of Medical Artificial Intelligence

Description

More details

Other editions

Additional editions

Content

System requirements