Advances in Deep Generative Models for Medical Artificial Intelligence (Studies in Computational Intelligence, 1124)

✍ Scribed by Hazrat Ali (editor), Mubashir Husain Rehmani (editor), Zubair Shah (editor)

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 259
• Edition: 1st ed. 2023
• Category: Library

✦ Synopsis

Generative Artificial Intelligence is rapidly advancing with many state-of-the-art performances on computer vision, speech processing, and natural language processing tasks. Generative adversarial networks and neural diffusion models can generate high-quality synthetic images of human faces, artworks, and coherent essays on different topics. Generative models are also transforming Medical Artificial Intelligence, given their potential to learn complex features from medical imaging and healthcare data. Hence, computer-aided diagnosis and healthcare are benefiting from Medical Artificial Intelligence and Generative Artificial Intelligence.

This book presents the recent advances in generative models for Medical Artificial Intelligence. It covers many applications of generative models for medical image data, including volumetric medical image segmentation, data augmentation, MRI reconstruction, and modeling of spatiotemporal medical data. This book highlights the recent advancements in Generative Artificial Intelligence for medical and healthcare applications, using medical imaging and clinical and electronic health records data. Furthermore, the book comprehensively presents the concepts and applications of deep learning-based artificial intelligence methods, such as generative adversarial networks, convolutional neural networks, and vision transformers. It also presents a quantitative and qualitative analysis of data augmentation and synthesis performances of Generative Artificial Intelligence models.

This book is the result of the collaborative efforts and hard work of many minds who contributed to it and illuminated the vast landscape of Medical Artificial Intelligence. The book is suitable for reading by computer science researchers, medical professionals, healthcare informatics, and medical imaging researchers interested in understanding the potential of artificial intelligence in healthcare. It serves as a compass for navigating the artificial intelligence-driven healthcare landscape.

✦ Table of Contents

Preface
Acknowledgements
Contents
About the Editors
Deep Learning Techniques for 3D-Volumetric Segmentation of Biomedical Images
1 Introduction
2 Deep Learning for 3D-Volumetric Segmentation of Biomedical Images
3 CNN-Based Algorithms for 3D-Volumetric Segmentation of Biomedical Images
3.1 Algorithms for 3D-Volumetric Semantic Segmentation of Biomedical Images
3.2 Algorithms for 3D-Volumetric Instance Segmentation of Biomedical Images
3.3 Algorithms for 3D-Volumetric Panoptic Segmentation of Biomedical Images
4 GAN-Based Algorithms for 3D-Volumetric Segmentation of Biomedical Images
4.1 Algorithms for 3D-Volumetric Semantic Segmentation of Biomedical Images
4.2 Algorithms for 3D-Volumetric Instance Segmentation of Biomedical Images
4.3 Algorithms for 3D-Volumetric Panoptic Segmentation of Biomedical Images
5 Challenges
5.1 Limited Data Annotation
5.2 High Computational Complexity
5.3 Overfitting
5.4 Training Time
6 Conclusion
References
Analysis of GAN-Based Data Augmentation for GI-Tract Disease Classification
1 Introduction
2 Related Work
2.1 Data Augmentation Approaches for Medical Imaging
3 Data Augmentation
4 Types of Image Data Augmentation Techniques
4.1 Geometric Transformations Based Augmentation
4.2 Data Augmentation with GANs
5 Methodology
6 Results and Discussion
7 Conclusion
References
Deep Generative Adversarial Network-Based MRI Slices Reconstruction and Enhancement for Alzheimer's Stages Classification
1 Introduction
2 Related Work
3 Dataset
4 Methodology
4.1 Deep Convolutional GAN (DCGAN)
4.2 Vanilla GAN (VGAN)
5 Results and Discussion
6 Conclusion
References
Evaluating the Quality and Diversity of DCGAN-Based Generatively Synthesized Diabetic Retinopathy Imagery
1 Introduction
2 Related Work
2.1 GAN-Based Approaches to Addressing Data Imbalance for DR
3 Methodology
3.1 DCGAN Architecture
3.2 Retinal Fundus Imagery
3.3 Evaluation of GAN-Based Synthetic Imagery
3.4 Normalization of Evaluation Metrics
3.5 Classification of PDR Images
3.6 Correlation of Quality, Diversity, and Classification Performances
4 Results and Discussion
4.1 Critical Analysis of Quantitative Evaluation Metrics
4.2 Evaluation of Synthetic PDR Imagery
4.3 Assessment of Synthetic Imagery Using Classification Scores
5 Conclusion
References
Deep Learning Approaches for End-to-End Modeling of Medical Spatiotemporal Data
1 Introduction
2 Spatial Temporal Deep Learning Background
2.1 Convolutional Neural Networks
2.2 Recurrent Neural Networks
2.3 Attention
3 Medical Imaging Applications
3.1 Biopotential Imaging
3.2 Cardiac Imaging
3.3 Angiography and Perfusion Imaging
3.4 Functional Magnetic Resonance Imaging
4 Learning from Small Samples
4.1 Network Pre-training
4.2 Regularization
5 Conclusion
References
Skin Cancer Classification with Convolutional Deep Neural Networks and Vision Transformers Using Transfer Learning
1 Introduction
2 Related Work
3 Methodology
3.1 Dataset
3.2 Preprocessing
3.3 Pre-trained Model Architectures
4 Results and Discussion
5 Conclusion
References
A New CNN-Based Deep Learning Model Approach for Skin Cancer Detection and Classification
1 Introduction
2 Related Works
3 Material and Method
3.1 Segmentation
3.2 Classification
4 Experimental Studies
4.1 Evaluation Metrics
4.2 Experimental Segmentation
4.3 Evaluation Results
5 Conclusion and Discussion
References
Machine Learning Based Miscellaneous Objects Detection with Application to Cancer Images
1 Introduction
2 The Adaptive Boosting Algorithm (ABA)
3 Experimental Setup and Results
3.1 Investigations on Melanoma
3.2 License Plate Detection (LPD)
3.3 Vehicle Detection
3.4 Pedestrian Detection
3.5 Players' Detection
3.6 Football Detection
3.7 Computational Complexity
3.8 Discussion
3.9 Future Research Direction
3.10 Final Remarks
4 Conclusions
References
Advanced Deep Learning for Heart Sounds Classification
1 Introduction
1.1 Heart Sounds and Auscultation
2 Datasets
2.1 PhysioNet 2016
2.2 PASCAL 2011
3 Pre-processing of Heart Sounds
4 Features Extraction
4.1 Heart Sounds Spectrograms
5 Classification
5.1 Convolutional Neural Network
5.2 Auto-encoders
5.3 Vision Transformers
5.4 Transfer-Learning Using Pre-trained Models
6 Performance Metrics
7 Results
8 Conclusions
References