Frontiers of Artificial Intelligence in Medical Imaging

follow Cover Title Copyright Contents Editor biographies List of contributors 1 Health informatics system 1.1 Introduction to health informatics 1.2 Traditional scheme 1.3 Recent advancements 1.4 Artificial intelligence schemes 1.5 Deep-learning schemes 1.6 The Internet of Medical Things in health informatics 1.7 Health-band-supported patient monitoring 1.8 Accurate disease diagnosis 1.9 Summary References 2 Medical-imaging-supported disease diagnosis 2.1 Introduction 2.2 Cancer prevention 2.3 Early detection 2.4 Internal organs and medical imaging 2.4.1 Lung abnormality examination 2.4.2 Colon/rectum abnormality examination 2.4.3 Liver abnormality examination 2.4.4 Breast abnormality examination 2.4.5 Skin cancer examination 2.4.6 Brain cancer examination 2.4.7 COVID-19 examination 2.5 Summary References 3 Traditional and AI-based data enhancement 3.1 Clinical image improvement practices 3.2 Significance of image enrichment 3.3 Common image improvement methods 3.3.1 Artifact elimination 3.3.2 Noise elimination 3.3.3 Contrast enhancement 3.3.4 Image edge detection 3.3.5 Restoration 3.3.6 Image smoothing 3.3.7 Saliency detection 3.3.8 Local binary pattern 3.3.9 Image thresholding 3.4 Summary References 4 Computer-aided-scheme for automatic classification of brain MRI slices into normal/Alzheimer’s disease 4.1 Introduction 4.2 Related work 4.3 Methodology 4.3.1 Proposed AD detection scheme 4.3.2 Machine-learning scheme 4.3.3 Deep-learning scheme 4.3.4 Scheme with integrated features 4.3.5 Data collection and pre-processing 4.3.6 Feature extraction and selection 4.3.7 Validation 4.4 Results and discussions 4.5 Conclusion Conflict of interest References 5 Design of a system for melanoma diagnosis using image processing and hybrid optimization techniques 5.1 Introduction 5.1.1 Conception 5.2 Literature review 5.3 Materials and methods 5.3.1 Artificial neural networks 5.3.2 Concept 5.3.3 Mathematical modeling of an ANN 5.4 Meta-heuristics 5.5 Electromagnetic field optimization algorithm 5.6 Developed electromagnetic field optimization algorithm 5.7 Simulation results 5.7.1 Image acquisition 5.7.2 Pre-processing stage 5.7.3 Processing stage 5.7.4 Classification 5.8 Final evaluation 5.9 Conclusions References 6 Evaluation of COVID-19 lesion from CT scan slices: a study using entropy-based thresholding and DRLS segmentation 6.1 Introduction 6.2 Context 6.3 Methodology 6.3.1 COVID-19 database 6.3.2 Image conversion and pre-processing 6.3.3 Image thresholding 6.3.4 Distance regularized level set segmentation 6.3.5 Performance computation and validation 6.4 Results and discussions 6.5 Conclusion References 7 Automated classification of brain tumors into LGG/HGG using concatenated deep and handcrafted features 7.1 Introduction 7.2 Context 7.3 Methodology 7.3.1 Image databases 7.3.2 Handcrafted feature extraction 7.3.3 Deep feature extraction 7.3.4 Feature concatenation 7.3.5 Performance measure computation and validation 7.4 Results and discussion 7.5 Conclusion References 8 Detection of brain tumors in MRI slices using traditional features with AI scheme: a study 8.1 Introduction 8.2 Context 8.3 Methodology 8.3.1 Image data sets 8.3.2 Pre-processing 8.3.3 Post-processing 8.3.4 Feature extraction 8.3.5 Classification 8.3.6 Performance evaluation 8.4 Results and discussion 8.5 Conclusion Acknowledgment References 9 Framework to classify EEG signals into normal/schizophrenic classes with machine-learning scheme 9.1 Introduction 9.2 Related work 9.3 Methodology 9.3.1 Electroencephalogram database 9.3.2 EEG pre-processing 9.3.3 Feature selection 9.3.4 Classification 9.3.5 Validation 9.4 Results and discussion 9.5 Conclusion References 10 Computerized classification of multichannel EEG signals into normal/autistic classes using image-to-signal transformation 10.1 Introduction 10.2 Context 10.3 Problem formulation 10.4 Methodology 10.4.1 Electroencephalogram database 10.4.2 Signal-to-image conversion with continuous wavelet transform 10.4.3 Nonlinear feature extraction 10.4.4 Locality-sensitive discriminant-analysis-based data reduction 10.4.5 Classifier implementation 10.4.6 Performance measure and validation 10.5 Results and discussion 10.6 Conclusion References