This book focuses on various aspects of computer vision applications in the field of healthcare. It covers new tools and technologies in some of the important areas of medical science like histopathological image analysis, cancer taxonomy, use of deep learning architecture dental care, and many more. Furthermore, this book reviews and discusses the use of intelligent learning-based algorithms for increasing the precision in medical domain. The book discusses different computer vision algorithms which are useful in various industries and day-to-day life. It also highlights many challenges faced by research community, like view point variations, scale variations, illumination variations, multi-modalities, and noise.
Author(s): Mukesh Saraswat, Harish Sharma, Karm Veer Arya
Series: Studies in Autonomic, Data-driven and Industrial Computing
Publisher: Springer
Year: 2022
Language: English
Pages: 164
City: Singapore
Preface
Contents
Editors and Contributors
1 Intelligent Vision in Healthcare
1 Introduction
2 Feature Representation
3 Conclusion and Future scope
References
2 Diagnosis of COVID-19 in X-Ray and CT Images Using Online Clustering Framework
1 Introduction
2 Related Works
3 Methodology
3.1 Phase 1: Mixture Model Approach for Offline Clustering
3.2 Phase 2: Real-Time Diagnosis Using Online Clustering Framework
4 Data and Feature Extraction
4.1 Dataset Description
4.2 Features Extraction Technique
5 Results and Discussion
5.1 Performance Measures
5.2 Experimental Results
6 Conclusion
References
3 Unsupervised Deep Learning Approach for the Identification of Intracranial Haemorrhage in CT Images Using PCA-Net and K-Means Algorithm
1 Introduction
2 Related Works
3 Proposed Method for Unsupervised ICH Identification
3.1 Filter Learning in PCA-Net
3.2 Feature Extraction Using PCA-Net
3.3 K-Means Classifier
3.4 Linear SVM Classifier
4 Experimental Set-up
5 Experimental Results and Discussions
6 Conclusion and Future Work
References
4 Automatic Segmentation of Optic Cup and Optic Disc Using MultiResUNet for Glaucoma Classification from Fundus Image
1 Introduction
2 Deep Learning Architectures
2.1 U-Net Architecture
2.2 MultiResUNet Architecture
3 Methodology
3.1 Experiments
3.2 Dataset
3.3 Training
3.4 Evaluation Metric
3.5 Segmentation Results
3.6 Classification Results
4 Conclusion
References
5 A Framework to Classify the Calcification Region from USG Images of Thyroid Nodules
1 Introduction
1.1 Related Work
1.2 Motivation
1.3 Contribution
2 Methods
2.1 Brief Description of the Work
2.2 De-Noising by Smoothing
2.3 Tentative Calcification Region Detection
2.4 Classification of Calcified Region
3 Experimental Results
3.1 Detection of Calcified Region
3.2 Classification of Calcified Region
4 Conclusion
References
6 Predicting Heart Disease with Multiple Classifiers
1 Introduction
2 Related Work
3 Proposed Method
3.1 Data Preprocessing
3.2 Feature Selection
3.3 Classification Modeling
3.4 Performance Modeling
3.5 Proposed Hybrid Method (HDRKL)
4 Experimental Environment
4.1 Evaluation Metrics
5 Results and Discussion
5.1 Results from the Two Datasets
5.2 Discussion
6 Conclusion
References
7 Detection of Cardiac Disease with Less Number of Electrocardiogram Sensor Samples Using Chebyshev
1 Introduction
2 Chebyshev Polynomial Interpolation
3 Dataset Description
3.1 Feature Extraction Technique Based on Chebfun
4 Methodology
5 Experiments and Results
6 Conclusion
References
8 Automatic True Vessel Identification by Efficient Removal of False Blood Vessels for Detection of Retinal Diseases
1 Introduction
1.1 False Vessel Significance
2 Proposed Methodology
2.1 Preprocessing
2.2 Image Enhancement Using Hybrid ICA
2.3 OD Segmentation Using DAF and Modified Bee Colony Algorithm
2.4 GLRM Feature Extraction
2.5 Feature Selection Using Mutual Information and Naive Bayesian Classifier
2.6 Enhanced Multiple Kernel Learning Classifier for Blood Vessel Classification
3 Results and Discussion
4 Conclusion
References
9 Neural Networks for Detecting Cardiac Arrhythmia from PCG Signals
1 Introduction
2 Literature Survey
3 Mathematical Model
4 Methodology
4.1 Dataset
4.2 Data Preprocessing
4.3 Model Architecture
4.4 Implemented Model
5 Results
5.1 Graph of ReLU Activation Function
5.2 Graph of ELU Activation Function
5.3 Graph of Tanh Activation Function
5.4 Graph of Transfer Learning Model
6 Conclusion
References
10 Data Labeling Impact on Deep Learning Models in Digital Pathology: a Breast Cancer Case Study
1 Introduction
2 Deep Learning for Ki-67 Scoring
3 Methodology
3.1 Data Annotation
3.2 Data Preprocessing
3.3 Data Segmentation
3.4 Data Classification
4 Experimental Setup
4.1 Segmentation and Classification Results
4.2 Ki67 LI Results
5 Discussion and Conclusion
References
11 Automatic Brain Tumor Classification in 2D MRI Images Using Integrated Deep Learning and Supervised Machine Learning Techniques
1 Introduction
1.1 Materials and Method
1.2 Brain MRI Image Dataset
1.3 Automatic High-Level Extraction of Features and Analysis Using CNN
1.4 Combining CNN and Supervised Machine Learning Techniques
1.5 Evaluation Metrics
1.6 Results and Discussion
1.7 Training and Testing of Brain Tumor Image Dataset
1.8 Performance Analysis of CNN with ADAM, SGDM, and RMSprop Optimizers
1.9 Performance Analysis of Integrated CNN and Machine Learning Techniques
2 Conclusion and Future Work
References
12 Deep Learning-Based Prediction of Alzheimer's Disease from Magnetic Resonance Images
1 Introduction
2 Prior Work
3 Proposed Method
3.1 Architecture
3.2 Dataset Used
4 Experimental Results
5 Summary
References
