High Performance Computing for Intelligent Medical Systems

PRELIMS.pdf
Preface
Acknowledgements
Editors biographies
Varun Bajaj
Irshad Ahmad Ansari
Contributors biographies
Ms Athena Abrishamchi
Fatame Bafande
Hussain Ahmed Choudhury
Sengul Dogan
Vandana Dubey
Fatih Ertam
Jamal Esmaelpoor
Harsh Goud
Kapil Gupta
Lalita Gupta
Smith K Khare
Rajesh Kumar
Wahengbam Kanan Kumar
Gaurav Makwana
Miguel Ángel Mañanas
Hamid Reza Marateb
Arezoo Mirshamsi
Mohammad Reza Mohebbian
Mohammad Hassan Moradi
Kishorjit Nongmeikapam
Saurabh Pal
Antti Rissanen
Marjo Rissanen
Kalle Saastamoinen
Zahra Momayez Sanat
Prakash Chandra Sharma
Mehdi Shirzadi
Aheibam Dinamani Singh
Mithlesh Prasad Singh
Nidul Sinha
Abdulhamit Subasi
Turker Tuncer
Amit Kumar Verma
Dhyan Chandra Yadav
Ram Narayan Yadav
Shadi Zamani
CH001.pdf
Chapter 1 Automatic detection of hypertension by flexible analytic wavelet transform using electrocardiogram signals
1.1 Introduction
1.1.1 Various intervals of ECG
1.1.2 Related work
1.2 Methodology
1.2.1 Dataset
1.2.2 Flexible analytic wavelet transform
1.2.3 Feature extraction
1.2.4 Classification techniques
1.2.5 Performance parameters
1.3 Results
1.4 Conclusion
References
CH002.pdf
Chapter 2 Computational intelligence in surface electromyogram signal classification
2.1 Introduction
2.2 Computational intelligence in biomedical signal processing
2.3 Background
2.3.1 Discrete cosine transform
2.3.2 Fast Fourier transform
2.3.3 Singular value decomposition
2.3.4 Ternary pattern
2.3.5 Support vector machine
2.3.6 Linear discriminant analysis
2.3.7 KNN
2.3.8 Artificial neural network
2.4 Spider network
2.4.1 Pre-processing
2.4.2 Feature extraction
2.4.3 Feature reduction
2.4.4 Feature concatenation
2.4.5 Classification
2.5 Results and discussions
2.5.1 Dataset
2.5.2 Experimental results
2.5.3 Discussion
2.6 Conclusions and suggestions
References
CH003.pdf
Chapter 3 Analysis of IoT interventions to solve voice pathologies challenges
3.1 Introduction
3.1.1 Pathology assessment
3.1.2 Internet of things in voice pathology
3.2 Electroglottography
3.2.1 Quantitative analysis
3.3 Voice pathology datasets
3.3.1 Voice ICar fEDerico II (VOICED)
3.3.2 Massachusetts eye and ear infirmary
3.3.3 Saarbruecken Voice Database
3.3.4 Arabic voice pathology database
3.4 Acoustic speech features with machine learning for voice pathology classification
3.4.1 Feature extraction techniques
3.4.2 Voice pathology analysis and detection techniques
3.5 Discussion and conclusion
References
CH004.pdf
Chapter 4 Deep learning for cuffless blood pressure monitoring
4.1 Introduction
4.2 Physiological models
4.3 Data source
4.3.1 Preprocessing procedures
4.4 Deep learning models for blood pressure monitoring
4.4.1 LSTM model
4.4.2 PCA-LSTM model
4.4.3 Convolutional neural network model
4.4.4 CNN–LSTM model
4.5 Discussion
4.5.1 Comparison with other methods
4.6 Conclusion
References
CH005.pdf
Chapter 5 Reliability of machine learning methods for diagnosis and prognosis during the COVID-19 pandemic: a comprehensive critical review
5.1 Introduction
5.2 Methods
5.2.1 January–March
5.2.2 April–June
5.2.3 July–September
5.2.4 October 2020 to February 2021
5.2.5 Machine learning methods
5.2.6 Critical issues
5.3 Conclusion and future scope
References
CH006.pdf
Chapter 6 Forecasting confirmed cases of Corona patients in India using regression and Gaussian analysis
6.1 Introduction
6.2 Regression analysis in machine learning
6.3 Related work
6.4 Methodology
6.4.1 Data description
6.5 Results
6.6 Discussion
6.7 Conclusion
Acknowledgments
References
CH007.pdf
Chapter 7 A model for advanced patient feedback procedures in diagnostics
7.1 Introduction
7.2 Focus on diagnostics
7.2.1 Diagnostic error as a concept
7.2.2 Diagnostic errors in healthcare
7.2.3 Common reasons for diagnostic failures
7.2.4 Preventing diagnostic errors in cooperation with patients
7.3 Diagnostics and safety challenges in healthcare
7.3.1 Patient safety and equity challenges
7.3.2 Enhanced patient safety with rational cost control policy
7.4 Importance of patient feedback in the diagnostics phase
7.4.1 Need for timely feedback
7.4.2 The role of timely feedback
7.5 The challenges of diagnostics-centered clients’ feedback
7.6 Enhancing technology acceptance in system development
7.7 Phases of diagnostics and the requirements for doctors
7.7.1 Requirements for competence and compassion
7.7.2 Diagnostic process from the view of doctors
7.7.3 Diagnostic process from the view of patients
7.8 A model for instant patient feedback
7.8.1 General principles
7.8.2 Structure of the model
7.8.3 Patient management with the model
7.8.4 Meaning of the fixed format phase of the model—phase 1
7.8.5 Meaning and management of the free format phase—phase 2
7.8.6 Clients’ opinions of the feedback delivery system—phase 3
7.9 Client feedback as a translational development challenge
7.9.1 Enhancing process synergy in organizations
7.9.2 Maturing and validating patient-targeted feedback systems
7.10 Conclusion
References
CH008.pdf
Chapter 8 Soft computing techniques for efficient processing of large medical data
8.1 Introduction
8.2 Understanding the concept: video compression
8.3 Image compression standards
8.3.1 JPEG
8.3.2 JPEG2000
8.3.3 JPEG-LS
8.3.4 JPEG-XR
8.3.5 H.265
8.3.6 Types of coding and frames
8.4 Motion estimation and the necessity of it in video coding?
8.4.1 Forward and backward motion estimation
8.4.2 Block matching concept
8.5 What is soft computing: techniques and differences
8.6 Standard techniques for motion estimation
8.7 Soft computing techniques for motion estimation
8.8 Conceptual terms used in different SC techniques
8.8.1 Chromosomes and genes
8.8.2 Chromosome representation
8.8.3 Cross-over
8.8.4 Mutation
8.8.5 Weighting function and PBME
8.9 Some well-established soft computing based BMA
8.9.1 Genetic algorithm-BMA
8.9.2 Inter-block/inter-frame fuzzy search algorithm
8.9.3 Basic block-matching using particle swarm optimization
8.9.4 Harmony search block matching algorithm
8.9.5 Cat swarm optimization (CSO-BMA)
8.9.6 CUCKOO search based BMA (CS-BMA)
8.9.7 The ABC-BM algorithm
8.9.8 ABC-DE
8.9.9 HS-DE based BMA
8.9.10 ‘Deterministically starting-GA’ (GADet)
8.9.11 Enhanced Grey-wolf optimizer-BMA (EGWO-BMA)
8.9.12 Chessboard search pattern strategy
8.10 Results and discussion
Acknowledgment
References
CH009.pdf
Chapter 9 A comparison of Parkinson’s disease prediction using ensemble data mining techniques with features selection methods
9.1 Introduction
9.2 Related work
9.3 Methodology
9.3.1 Data description
9.3.2 Whisker plotting
9.3.3 Histogram plotting
9.4 Algorithms description
9.4.1 Decision tree
9.4.2 Naïve Bayes
9.4.3 Random forest
9.4.4 Extra tree
9.4.5 Bagging ensemble method
9.4.6 Features selection method in Parkinson’s disease
9.5 Results
9.5.1 Evaluation of result after prediction on Parkinson’s dataset
9.5.2 Result of features importance methods
9.5.3 Chi-square test
9.5.4 Extra tree
9.5.5 Heat map
9.5.6 Evaluation of results after features selection
9.6 Discussion
9.7 Conclusion
Acknowledgments
References
CH010.pdf
Chapter 10 A comparative analysis of image enhancement techniques for detection of microcalcification in screening mammogram
10.1 Introduction
10.2 Image enhancement in spatial domain
10.2.1 Histogram modeling
10.2.2 Histogram equalization
10.2.3 Histogram matching
10.2.4 Averaging filter
10.2.5 Gaussian filter
10.2.6 Median filter
10.3 Image enhancement in frequency domain
10.3.1 Butterworth filtering
10.3.2 Gaussian low-pass filter
10.3.3 Homomorphic filtering
10.3.4 Discrete wavelet transform
10.4 Convolutional neural network
10.5 Evaluation criteria
10.5.1 Mean square error
10.5.2 Peak signal-to-noise ratio
10.5.3 SNR
10.5.4 Mean
10.5.5 Variance
10.6 Results and discussion
10.7 Conclusion
References
CH011.pdf
Chapter 11 Computational intelligence for eye disease detection
11.1 Introduction
11.2 Anatomy of the eye
11.2.1 The cornea
11.2.2 The human retina
11.3 Retinal diseases
11.3.1 Retinal tear
11.3.2 Diabetic retinopathy
11.3.3 Macula hole
11.3.4 Degeneration of the macula
11.3.5 Disorders of the optic nerve
11.3.6 Glaucoma
11.3.7 Diabetic macular edema
11.3.8 Retinopathy of prematurity
11.4 History of retinal imaging
11.5 Current status of retinal analysis
11.5.1 Fundus imaging
11.5.2 Optical coherence tomography
11.6 Disease specific analysis of retinal images
11.6.1 Early detection of retinal disease from fundus photography
11.6.2 Early detection of systemic disease from fundus photography
11.6.3 3-Dimensional OCT and retinal diseases—image guided therapy
11.7 Fundus image analysis
11.7.1 Glaucoma detection using retinal imaging
11.7.2 Dementia detection using retinal imaging
11.7.3 Heart diseases detection using retinal imaging
11.7.4 Choroidal melanoma detection using retinal imaging
11.7.5 Advantages of retinal imaging
11.8 Comparative analysis between various retinal imaging methods
11.9 Conclusion
References
CH012.pdf
Chapter 12 Recent trends in medical image segmentation with special focus on brain tumours and retinal images
12.1 Introduction
12.1.1 Types of biomedical imaging
12.1.2 Biomedical image segmentation
12.1.3 Segmentation evaluation
12.2 Retinal images segmentation
12.2.1 Datasets
12.2.2 Fundus photography
12.2.3 Challenges in retinal vessel segmentation
12.2.4 Review of literature
12.3 Brain tumour segmentation
12.3.1 Brain tumour segmentation databases
12.3.2 Classification of brain tumour
12.3.3 Brain photography
12.3.4 Challenges
12.3.5 Image pre-processing
12.3.6 Image post-processing
12.3.7 Traditional machine learning in tumor segmentation
12.3.8 Deep learning
12.4 Discussion and conclusion
References
CH013.pdf
Chapter 13 Analysis of AI based PID controller for health care system
13.1 Introduction
13.2 Types of chronic disease
13.2.1 Cancer
13.2.2 Blood pressure
13.2.3 Diabetes
13.2.4 Arthritis
13.3 Analysis of the biomedical system
13.3.1 Classical controller in a biomedical system
13.4 Mathematical modeling of the biomedical system
13.4.1 MAP control
13.4.2 Intracranial tumor’s temperature control
13.4.3 Blood glucose
13.4.4 BP control after surgery in a diabetic patient
13.4.5 Heart modeling using PM
13.4.6 Tumor growth control
13.5 Conclusion
References