Convolutional Neural Networks for Medical Applications

Description

Convolutional Neural Networks for Medical Applications consists of research investigated by the author, containing state-of-the-art knowledge, authored by Dr Teoh Teik Toe, in applying Convolutional Neural Networks (CNNs) to the medical imagery domain. This book will expose researchers to various applications and techniques applied with deep learning on medical images, as well as unique techniques to enhance the performance of these networks.Through the various chapters and topics covered, this book provides knowledge about the fundamentals of deep learning to a common reader while allowing a research scholar to identify some futuristic problem areas. The topics covered include brain tumor classification, pneumonia image classification, white blood cell classification, skin cancer classification and diabetic retinopathy detection. The first chapter will begin by introducing various topics used in training CNNs to help readers with common concepts covered across the book. Each chapter begins by providing information about the disease, its implications to the affected and how the use of CNNs can help to tackle issues faced in healthcare. Readers would be exposed to various performance enhancement techniques, which have been tried and tested successfully, such as specific data augmentations and image processing techniques utilized to improve the accuracy of the models. Preface Contents 1 Introduction 1.1 Medical Imaging 1.1.1 Example of An X-ray Image 1.1.2 Users of Medical Imaging 1.1.3 Importance of Medical Imaging 1.2 Convolutional Neural Networks 1.2.1 The Convolution Operation 1.2.2 Pooling 1.2.3 Flattening 1.2.4 CNN Architectures VGG16 InceptionNet ResNet 1.2.5 Finetuning 1.3 Data Augmentation 1.4 Regularization 1.4.1 Ridge Regression 1.4.2 Lasso Regression 1.4.3 Dropout References 2 CNN for Brain Tumor Classification 2.1 Introduction to Brain Tumors 2.1.1 Benign Tumors 2.1.2 Malignant Tumors 2.2 Brain Tumor Dataset 2.2.1 Glioma Tumor Who Does it Affect Survival Rates Complications 2.2.2 Meningioma Tumor Who Does it Affect Survival Rates Complications 2.2.3 Pituitary Tumor Who Does it Affect Survival Rates Symptoms Complications 2.3 Classifying Brain Tumors 2.3.1 Data Augmentation Method RandomColor Flip or Rotation Mixup 2.3.2 Convolution and Pooling Layers 2.3.3 Global Average Pooling (GAP) 2.3.4 Training 2.3.5 Result 2.3.6 Conclusion References 3 CNN for Pneumonia Image Classification 3.1 Introduction to Pneumonia 3.1.1 Causes of Pneumonia 3.1.2 Categories of Pneumonia 3.1.3 Risk Factors for Pneumonia 3.1.4 Complications of Pneumonia 3.2 Pneumonia Dataset 3.3 Classifying Pneumonia 3.3.1 Methodology Data Pre-processing Convolution and Pooling Layers 3.3.2 Model Compilation Optimizer Loss Compilation 3.3.3 Model Evaluation Accuracy LogLoss Precision and Recall F1 Score 3.3.4 Model Improvement 3.3.5 Conclusion References 4 CNN for White Blood Cell Classification 4.1 Introduction to White Blood Cells 4.2 White Blood Cells Dataset 4.2.1 Eosinophil Low Eosinophil Count High Eosinophil Count 4.2.2 Lymphocyte Low Lymphocyte Count High Lymphocyte Count 4.2.3 Monocyte Low Monocyte Count High Monocyte Count 4.2.4 Neutrophil Low Neutrophil Count High Neutrophil Count 4.3 Classifying White Blood Cells 4.3.1 EfficientNet Model Structure (EfficientNet Model) Advantage of EfficientNet Model 4.3.2 Experimental Study Preprocessing Data Training Model Results and Evaluation 4.3.3 Conclusion References 5 CNN for Skin Cancer Classification 5.1 Introduction to Skin Cancer 5.1.1 Basal Cell Carcinoma 5.1.2 Squamous Cell Carcinoma 5.1.3 Melanoma 5.2 Skin Cancer Dataset 5.3 Classifying Skin Cancer 5.3.1 Data Pre-processing 5.3.2 Convolution and Pooling Layer 5.3.3 Final Pooling Operation Flatten Global Average Pooling Line Average Pooling Loss Function and Optimizer 5.3.4 Training Training Procedure Result Improvement of the Model 5.3.5 Conclusion References 6 CNN for Diabetic Retinopathy Detection 6.1 Introduction to Diabetic Retinopathy 6.2 Diabetic Retinopathy Dataset 6.2.1 Non-proliferative Diabetic Retinopathy 6.2.2 Proliferative Diabetic Retinopathy 6.3 Classifying Diabetic Retinopathy 6.3.1 Diabetic Retinopathy 6.3.2 Deep Learning and Image Identification 6.3.3 Training Data Preparation Setting of the Experiment 6.3.4 Result and Evaluation Accuracy Loss 6.3.5 The Optimisation of Convolutional Neural Network Improvement of the Model Results After Improvement 6.3.6 Comparison with Other Models 6.3.7 Conclusion References Index