Applications of Artificial Intelligence in Medical Imaging provides the description of various biomedical image analysis in disease detection using AI that can be used to incorporate knowledge obtained from different medical imaging devices such as CT, X-ray, PET and ultrasound. The book discusses the use of AI for detection of several cancer types, including brain tumor, breast, pancreatic, rectal, lung colon, and skin. In addition, it explains how AI and deep learning techniques can be used to diagnose Alzheimer's, Parkinson's, COVID-19 and mental conditions.
This is a valuable resource for clinicians, researchers and healthcare professionals who are interested in learning more about AI and its impact in medical/biomedical image analysis.
Author(s): Abdulhamit Subasi
Series: Artificial Intelligence Applications in Healthcare and Medicine
Publisher: Academic Press
Year: 2022
Language: English
Pages: 379
City: London
Front Cover
Applications of Artificial Intelligence in Medical Imaging
Copyright Page
Dedication
Contents
List of contributors
Series preface
Preface
Acknowledgments
1 Introduction to artificial intelligence techniques for medical image analysis
1.1 Introduction
1.2 Artificial intelligence for image classification
1.3 Unsupervised learning (clustering)
1.3.1 Image segmentation with clustering
1.4 Supervised learning
1.4.1 K-nearest neighbor
1.4.1.1 Support vector machine
1.4.2 Decision tree
1.4.3 Random forest
1.4.4 Bagging
1.4.5 Boosting
1.4.6 AdaBoost
1.4.7 XGBoost
1.4.8 Artificial neural networks
1.4.9 Deep learning
1.4.10 The overfitting problem in neural network training
1.4.10.1 Regularization
1.4.11 Convolutional neural networks
1.4.11.1 Functioning of convolutional neural network
1.4.11.2 Padding
1.4.11.3 Strides
1.4.11.4 The Rectified Linear Unit layer
1.4.11.5 Pooling
1.4.11.6 Fully connected layers
1.4.11.7 Training a convolutional network
1.4.11.8 Dropout
1.4.11.9 Early stopping
1.4.11.10 Batch normalization
1.4.12 Recurrent neural networks
1.4.13 Long short-term memory
1.4.14 Data augmentation
1.4.15 Generative adversarial networks
1.4.16 Transfer learning
1.4.16.1 AlexNet
1.4.16.2 Visual geometry group
1.4.16.3 ResNet
1.4.16.4 MobileNet architecture
1.4.16.5 Inception-v4 and Inception-ResNet
1.4.16.6 Xception
1.4.16.7 Densely connected convolutional networks
1.4.16.8 Feature extraction with pretrained models
References
2 Lung cancer detection from histopathological lung tissue images using deep learning
2.1 Introduction
2.2 Literature review
2.3 Artificial intelligence models
2.3.1 Artificial neural networks
2.3.2 Deep learning
2.3.3 Convolutional neural networks
2.4 Lung cancer detection using artificial intelligence
2.4.1 Feature extraction using deep learning
2.4.2 Dimension reduction
2.4.3 Prediction and classification
2.4.4 Experimental data
2.4.5 Performance evaluation measures
2.4.6 Experimental results
2.5 Discussion
2.6 Conclusion
References
3 Magnetic resonance imagining-based automated brain tumor detection using deep learning techniques
3.1 Introduction
3.2 Literature survey
3.3 Deep learning for disease detection
3.3.1 Artificial neural networks
3.3.2 Deep learning
3.3.3 Convolutional neural networks
3.4 Disease detection using artificial intelligence
3.4.1 Feature extraction
3.4.2 Transfer learning
3.4.3 Prediction and classification
3.4.4 Experimental data
3.4.5 Experimental setup
3.4.6 Performance evaluation metrics
3.4.7 Experimental results
3.5 Discussion
3.6 Conclusion
References
4 Breast cancer detection from mammograms using artificial intelligence
4.1 Introduction
4.2 Background and literature review
4.3 Artificial intelligence techniques
4.3.1 Artificial neural networks
4.3.2 Deep learning
4.3.3 Convolutional neural networks
4.4 Breast cancer detection using artificial intelligence
4.4.1 Feature extraction using deep learning
4.4.2 Prediction and classification
4.4.3 Experimental data
4.4.4 Performance evaluation measures
4.4.5 Experimental results
4.4.5.1 Mammographic Image Analysis Society dataset
4.4.5.2 CBIS-DDSM dataset
4.5 Discussion
4.6 Conclusion
References
5 Breast tumor detection in ultrasound images using artificial intelligence
5.1 Introduction
5.2 Background/literature review
5.3 Artificial intelligence techniques
5.3.1 Artificial neural networks
5.3.2 Deep learning
5.3.3 Convolutional neural networks
5.4 Breast tumor detection using artificial intelligence
5.4.1 Feature extraction using deep learning
5.4.2 Prediction and classification
5.4.3 Experimental data
5.4.4 Performance evaluation measures
5.4.4.1 Cohen’s Kappa coefficient
5.4.4.2 Area under the curve score
5.4.5 Experimental results
5.5 Discussion
5.6 Conclusion
References
6 Artificial intelligence-based skin cancer diagnosis
6.1 Introduction
6.2 Literature review
6.3 Machine learning techniques
6.3.1 Artificial neural network
6.3.2 k-nearest neighbor
6.3.3 Support vector machine
6.3.4 Random Forest
6.3.5 XGBoost
6.3.6 AdaBoost
6.3.7 Bagging
6.3.8 Long short-term memory
6.3.9 Bidirectional long short-term memory
6.3.10 Convolutional neural network
6.3.11 Transfer learning
6.4 Results and discussions
6.4.1 Dataset
6.4.2 Experimental setup
6.4.3 Performance metrics
6.4.4 Experimental results
6.4.5 Discussion
6.5 Conclusion
References
7 Brain stroke detection from computed tomography images using deep learning algorithms
7.1 Introduction
7.2 Literature survey in brain stroke detection
7.3 Deep learning methods
7.3.1 AlexNet
7.3.2 GoogleNet
7.3.3 Residual convolutional neural network
7.3.4 VGG-16
7.3.5 VGG-19
7.4 Experimental results
7.4.1 Dataset
7.5 Conclusion
References
8 A deep learning approach for COVID-19 detection from computed tomography scans
8.1 Introduction
8.2 Literature review
8.3 Subjects and data acquisition
8.4 Proposed architecture and transfer learning
8.4.1 ResNet
8.4.2 DenseNet
8.4.3 MobileNet
8.4.4 Xception
8.4.5 Visual geometry group (VGG)
8.4.6 Inception/GoogLeNet
8.5 COVID-19 detection with deep feature extraction
8.5.1 K-nearest neighbors
8.5.2 Support vector machine
8.5.3 Random Forests
8.5.4 Bagging
8.5.5 AdaBoost
8.5.6 XGBoost
8.6 Results and discussions
8.6.1 Performance evaluation measures
8.6.1.1 F1 measure and confusion matrix
8.6.1.2 Receiver operating characteristic (ROC) analysis
8.6.1.3 Kappa statistic
8.6.2 Experimental results
8.6.2.1 Transfer learning
8.6.2.2 Feature extraction with pretrained models
8.6.2.2.1 K-nearest neighbors
8.6.2.2.2 Support vector machine
8.6.2.2.3 Random Forest
8.6.2.2.4 AdaBoost and XGBoost
8.6.2.2.5 Bagging
8.6.3 Discussion
8.7 Conclusion
References
9 Detection and classification of Diabetic Retinopathy Lesions using deep learning
9.1 Introduction
9.2 Literature survey on diabetic retinopathy detection
9.2.1 Traditional diabetic retinopathy detection approach
9.2.2 Binary and multilevel classification
9.2.2.1 Binary classification
9.2.2.2 Multilevel classification
9.2.3 Datasets
9.3 Deep learning methods for diabetic retinopathy detection
9.3.1 Deep neural networks
9.3.2 Convolutional neural networks
9.3.2.1 Layers in convolutional neural network
9.3.3 Transfer learning
9.4 Diabetic retinopathy detection using deep learning
9.4.1 Prediction and classification
9.4.1.1 For Dataset a) Diabetic-Retinopathy Sample_Dataset_Binary
9.4.1.2 For Dataset b) Diabetic Retinopathy 224×224 Gaussian Filtered
9.4.2 Performance evaluation metrics
9.4.3 Experimental results
9.4.3.1 For Dataset a) Diabetic-Retinopathy Sample Dataset Binary
9.4.3.2 For Dataset b) Diabetic Retinopathy 224x224 Gaussian Filtered
9.5 Discussion
9.6 Conclusion
References
Further reading
10 Automated detection of colon cancer using deep learning
10.1 Introduction
10.2 Literature review
10.3 Artificial intelligence for colon cancer detection
10.3.1 Artificial neural networks
10.3.2 Deep learning
10.3.3 Convolutional neural networks
10.4 Disease detection using artificial intelligence
10.4.1 Feature extraction using deep learning
10.4.2 Dimension reduction
10.4.3 Prediction and classification
10.4.4 Experimental data
10.4.5 Performance evaluation measures
10.4.6 Experimental results
10.5 Discussion
10.6 Conclusion
References
11 Brain hemorrhage detection using computed tomography images and deep learning
11.1 Introduction
11.2 Literature survey in brain hemorrhage detection
11.3 Deep learning methods
11.3.1 ResNet-18
11.3.2 EfficientNet-B0
11.3.3 VGG-16
11.3.4 DarkNet-19
11.4 Experimental results
11.4.1 Dataset
11.5 Discussions
11.6 Conclusion
References
12 Artificial intelligence-based retinal disease classification using optical coherence tomography images
12.1 Introduction
12.2 Related work
12.3 Dataset
12.4 Implementation details
12.4.1 Convolutional neural network-based classification
12.4.2 Transfer learning-based classification
12.4.3 Deep feature extraction and machine learning
12.5 Results and discussions
12.6 Discussion
12.7 Conclusion
References
13 Diagnosis of breast cancer from histopathological images with deep learning architectures
13.1 Introduction
13.2 Materials and methods
13.2.1 Dataset
13.2.2 Methods
13.2.2.1 Convolutional neural network-based diagnosis method
13.2.2.2 Pretrained convolutional neural network-based diagnosis method
13.3 Results and discussions
13.3.1 Experimental setup
13.3.2 Experimental results
13.4 Conclusion
References
14 Artificial intelligence based Alzheimer’s disease detection using deep feature extraction
14.1 Introduction
14.2 Background/literature review
14.3 Artificial intelligence models
14.3.1 Deep feature extraction techniques
14.3.2 Classification techniques
14.3.2.1 Artificial neural network
14.3.2.2 K-nearest neighbor
14.3.2.3 Support vector machine
14.3.2.4 Random forest
14.3.2.5 AdaBoost
14.3.2.6 XGBoost
14.4 Alzheimer’s disease detection using artificial intelligence
14.4.1 Experimental data
14.4.2 Performance evaluation measures
14.4.3 Experimental results
14.5 Discussion
14.6 Conclusion
References
Index
Back Cover
