Applications of Medical Artificial Intelligence : First International Workshop, AMAI 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Proceedings / edited by Shandong Wu, Behrouz Shabestari, Lei Xing.

Format:

Book

Contributor:

Shabestari, Behrouz, editor.

Xing, Lei, editor.

Wu, Shandong, editor.

Series:

Lecture Notes in Computer Science, 1611-3349 ; 13540

Language:

English

Subjects (All):

Computer vision.

Application software.

Artificial intelligence.

Education--Data processing.

Education.

Social sciences--Data processing.

Social sciences.

Computer Vision.

Computer and Information Systems Applications.

Artificial Intelligence.

Computers and Education.

Computer Application in Social and Behavioral Sciences.

Local Subjects:

Computer Vision.

Computer and Information Systems Applications.

Artificial Intelligence.

Computers and Education.

Computer Application in Social and Behavioral Sciences.

Physical Description:

1 online resource (171 pages)

Edition:

1st ed. 2022.

Place of Publication:

Cham : Springer Nature Switzerland : Imprint: Springer, 2022.

System Details:

Mode of access: World Wide Web.

Summary:

This book constitutes the refereed proceedings of the first International Workshop on Applications of Medical Artificial Intelligence, AMAI 2022, held in conjunction with MICCAI 2022, in Singapore, in September 2022. The book includes 17 papers which were carefully reviewed and selected from 26 full-length submissions. Practical applications of medical AI bring in new challenges and opportunities. The AMAI workshop aims to engage medical AI practitioners and bring more application flavor in clinical, evaluation, human-AI collaboration, new technical strategy, trustfulness, etc., to augment the research and development on the application aspects of medical AI, on top of pure technical research.

Contents:

Intro

Preface

Organization

Contents

Increasing the Accessibility of Peripheral Artery Disease Screening with Deep Learning

1 Problem

2 Related Work

3 Data Collection Study

4 System Development

5 Validation Study

6 Conclusion

References

Deep Learning Meets Computational Fluid Dynamics to Assess CAD in CCTA

1 Introduction

2 Automated Assessment of CAD in CCTA

2.1 Straightened Representation of the Coronary Vessels

2.2 Representing Ground-Truth Segmentation as a 3D Mesh

2.3 Segmentation of Vessels Using U-Nets in Upsampled CTTA

2.4 Blood Flow Simulation

3 Experimental Validation

4 Conclusions and Future Work

Machine Learning for Dynamically Predicting the Onset of Renal Replacement Therapy in Chronic Kidney Disease Patients Using Claims Data

2 Methods

2.1 Dataset Description

2.2 Task Definition

2.3 Data Representation and Processing

2.4 Model Description

2.5 Model Evaluation

3 Experiments and Results

3.1 Study Population and Dataset

3.2 Model Performance

4 Conclusions

Uncertainty-Aware Geographic Atrophy Progression Prediction from Fundus Autofluorescence

2 Method

2.1 Data

2.2 Model Development

2.3 Uncertainty Estimation Using Deep Ensemble

3 Results

Automated Assessment of Renal Calculi in Serial Computed Tomography Scans

1.1 Our Contributions

2 Materials and Methods

2.2 Calculi Detection and Segmentation

2.3 Registration and Stone Matching

2.4 Manual Review and Tracking

2.5 Evaluation of Performance

2.6 Statistical Analysis

3.1 Cohort Characteristics

3.2 Performance of the Stone Detection and Segmentation

3.3 Performance of Stone Tracking

4 Discussion

References.

Prediction of Mandibular ORN Incidence from 3D Radiation Dose Distribution Maps Using Deep Learning

2 Methods and Materials

2.2 Prediction Models

2.3 Model Evaluation

2.4 Statistical Analysis

4.1 ORN Prediction

4.2 Study Limitations and Future Work

5 Conclusion

Analysis of Potential Biases on Mammography Datasets for Deep Learning Model Development

2.1 Mammography Dataset

2.2 Bias Analysis

2.3 Bias Correction Techniques

2.4 Experimental Setup

3 Results and Discussion

ECG-ATK-GAN: Robustness Against Adversarial Attacks on ECGs Using Conditional Generative Adversarial Networks

2 Methodology

2.1 Generator and Discriminator

2.2 Objective Function and Individual Losses

2.3 Adversarial Attacks

3 Experiments

3.1 Data Set Preparation

3.2 Hyper-parameters

3.3 Quantitative Evaluation

3.4 Qualitative Evaluation

CADIA: A Success Story in Breast Cancer Diagnosis with Digital Pathology and AI Image Analysis

2.1 Starting Point Analysis and Functional Requirement Collection

2.2 Sample Selection and Collection

2.3 Digital Image Annotation

2.4 Model Development

2.5 Model Deployment and Integration

4 Conclusions and Future Perspectives

Was that so Hard? Estimating Human Classification Difficulty

2 Estimating Image Difficulty

3 Datasets

4 Experiments

5 Results

6 Discussion and Conclusion

A Deep Learning-Based Interactive Medical Image Segmentation Framework

3 Applicative Scope

4 Methodology

4.1 System.

4.2 Training with Dynamic Data Generation

5 Experimental Results

5.1 Setup

5.2 Automated Evaluation

5.3 User Evaluation

Deep Neural Network Pruning for Nuclei Instance Segmentation in Hematoxylin and Eosin-Stained Histological Images

2.1 Datasets

2.2 Segmentation and Regression Models

2.3 Pruning

2.4 Merging and Post-processing

2.5 Evaluation Metrics

4 Conclusion

Spatial Feature Conservation Networks (SFCNs) for Dilated Convolutions to Improve Breast Cancer Segmentation from DCE-MRI

2.1 Compensation Module

2.2 Network Architecture

2.3 Performance Evaluation

2.4 Image Dataset and Data Preparation

4 Discussion and Conclusion

The Impact of Using Voxel-Level Segmentation Metrics on Evaluating Multifocal Prostate Cancer Localisation

2.1 Prostate Lesion Segmentation for Procedure Planning

2.2 Voxel-Level Segmentation Metrics

2.3 Lesion-Level Object Detection Metrics

2.4 Lesion Detection Metrics for Multifocal Segmentation Output

2.5 Correlation, Pairwise Agreement and Impact on Evaluation

3.1 Comparison Between DSC and HD

3.2 Comparison Between Voxel- and Lesion-Level Metrics

OOOE: Only-One-Object-Exists Assumption to Find Very Small Objects in Chest Radiographs

2.1 Feature Extractor

2.2 Point Detection Head

3.1 Datasets

3.2 Evaluation Metrics

3.3 Implementation Details

3.4 Comparison to Other Methods

3.5 A Closer Look at ET-tube vs. T-tube Detection Performance

Wavelet Guided 3D Deep Model to Improve Dental Microfracture Detection.

1 Introduction

2 Materials

3 Methods

4 Results and Discussion

Author Index.

Notes:

Includes bibliographical references and index.

Other Format:

Print version: Wu, Shandong Applications of Medical Artificial Intelligence

ISBN:

9783031177217

3031177215