Application of CNN and Hybrid Networks in Medical Images Processing and Cancer Classification

Name: Application of CNN and Hybrid Networks in Medical Images Processing and Cancer Classification
Brand: Cambridge Scholars Publishing
Price: 219.99 EUR
Availability: OnlineOnly

Yuriy Zaychenko Galib Hamidov Bohdan Chapaliuk(Autor*in)

Cambridge Scholars Publishing

1. Auflage

Erschienen am 26. Juli 2023

138 Seiten

E-Book

PDF mit Adobe-DRM

Systemvoraussetzungen

978-1-5275-1540-6 (ISBN)

219,99 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Adobe-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Table of Contents
Preface
Introduction
Chapter One
1.1. The Idea of Convolution
1.2. General Features of CNN
1.3. Architecture of Convolutional Neural Networks
1.3.1. Convolutional Layer
1.3.2. Pooling
1.3.3. Batch Normalization
1.3.4. Method Dropout
1.3.5. Fully Connected Layer
1.4. Algorithms for Optimising the Cost Function in Machine Learning for CNN
1.4.1. Gradient Descent
1.4.2. Adagrad
1.4.3. RMSprop
1.4.4. Adam
1.5. Architectures of Convolutional Neural Networks
1.5.1. VGG16 / VGG19
1.5.2. ResNet50
1.5.3. Inception
1.5.4. CNN Xception
1.5.5. Convolutional Autoencoder
Conclusions
References
Chapter Two
Introduction
2.1. Description of Dataset BreakHis
2.2. Choice CNN Architectures
2.3. Choice of Hyperparameters of Models Training
2.4. Results of Binary Classification of Breast Tumours
2.5. Results of Multiclass Images Classification
Conclusions
References
Chapter Three
3.1. Fuzzy Neural Network NEFClass
3.2. The Algorithms for Training FNN NEFClass
3.3. Experimental Investigations and Analysis of CNN-FNN Network for Breast Tumour Classification and Medical Diagnostics
Conclusion
References
Chapter Four
Introduction
4.1. Review of Related Works
4.2. Convolutional Encoder as a Tool forImages Dimensionality Reduction
4.3. Experimental Results
Conclusion
References
Chapter Five
Introduction
5.1. Related Works
5.1.1. Two-Dimensional Convolutional Neural Networkswith Multi-Instance Learning Task
5.1.2. Recurrent Neural Network with Attention and 2D CNN
5.1.2.1. Recurrent Neural Networks
5.1.2.2. Bidirectional Recurrent Neural Networks
5.1.2.3. Gated Recurrent Neural Networks
5.1.2.4. Attention Mechanism in Computer Vision
5.1.2.5. RADNET. Applying a Bidirectional Recurrent Neural Networkwith an Attention Mechanism
5.1.3. Three-Dimensional Convolutional NeuralNetwork for Lung Cancer Detection
5.2. Data and Datasets
5.3. Data Pre-Processing Steps
5.4. Data Augmentation
5.5. Experiments and Results
5.5.1. DenseNet and Multi-Instance Learning (MIL)Task with Sparse Label Assignment
5.5.2. Recurrent Neural Network with AttentionMechanism for Lung Cancer Detection System
5.5.3. C3D and 3D DenseNet
5.6. Results Summary
References
Chapter Six
6.1. Introduction: State-of-the-Art Analysis of Brain Tumour Classification
6.2. CNN Model for Medical Images Classification
6.3. Dataset Description
6.4. Experimental Investigations and their Analysis
Conclusions
References

Systemvoraussetzungen

Als PDF speichern Als Link merken